Статті в журналах з теми "Flood forecasting Statistical methods"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Flood forecasting Statistical methods.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Flood forecasting Statistical methods".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Mandryk, Oleg, Andriy Oliynyk, Roman Mykhailyuk, and Lidiia Feshanych. "Flood Development Process Forecasting Based on Water Resources Statistical Data." Grassroots Journal of Natural Resources 4, no. 2 (May 30, 2021): 65–76. http://dx.doi.org/10.33002/nr2581.6853.040205.
Повний текст джерелаАнотація:
The Ukrainian Carpathians is the territory with a great threat of floods. This is due to natural and climatic conditions of this region, which is characterized by mountainous terrain, high density of hydrological network and a significant amount of precipitation. Amount of precipitation here ranges from 600 mm on plains to 1,600 mm on mountain tops. The main factors of floods occurrence are excessive precipitation, low water permeability of soil and a high proportion of low-permeability rocks (flysch layers with a predominance of clay layers). Therefore, catastrophic floods in the region were also observed in previous centuries, when the anthropogenic impact on the environment, including forest ecosystems, was not comparable with the current one. Any flood is characterized by a period of development, a period of its critical (maximum) intensity and a period of decline. In the present paper, based on the use of methods for approximating the curves and the results of experimental studies of flood waters, a method of mathematical description and forecasting of the flood development is suggested. The recommended direction of further research may be related to the development of experimental means to determine the parameters that affect the process of flood formation.
2
Margaryan, Varduhi, Ekaterina Gaidukova, and Gennady Tsibulskii. "Methods for long-term forecasting of water availability in spring floods (r. Arpa – p. Jermuk)." E3S Web of Conferences 333 (2021): 02007. http://dx.doi.org/10.1051/e3sconf/202133302007.
Повний текст джерелаАнотація:
The article discusses the main physical and geographical factors, affecting the runoff of spring floods in the Arpa rivers catchment in the station Jermuk. Also the article discusses the development of a methodology for long-term forecasting of runoff volume of spring flood (WIV–VI) of river Arpa, station Jermuk. The study used data of water discharges of Arpa river catchment (station Jermuk), air temperature, precipitation, reserve water in snow at meteostation Jermuk. A linear correlation was also revealed between the values of the annual runoff and runoff of spring floods in Arpa river catchment, which can be used to predict the annual runoff. To predict the volume of spring flood runoff, regression method and obtained multivariate correlation dependencies. Assessment of statistical significance and stability the proposed models showed their «satisfactory» quality and the possibility of using in the practice of engineering and hydrological forecasts.
3
Šaur, David, and Lukáš Pavlík. "Comparison of accuracy of forecasting methods of convective precipitation." MATEC Web of Conferences 210 (2018): 04035. http://dx.doi.org/10.1051/matecconf/201821004035.
Повний текст джерелаАнотація:
This article is focused on the comparison of the accuracy of quantitative, numerical, statistical and nowcasting forecasting methods of convective precipitation including three flood events that occurred in the Zlin region in the years 2015 - 2017. Quantitative prediction is applied to the Algorithm of Storm Prediction for outputs “The probability of convective precipitation and The statistical forecast of convective precipitation”. The quantitative prediction of the probability of convective precipitation is primarily compared with the precipitation forecasts calculated by publicly available NWP models; secondary to statistical and nowcasting predictions. The statistical prediction is computed on the historical selection criteria and is intended as a complementary prediction to the first algorithm output. The nowcasting prediction operates with radar precipitation measurements, specifically with X-band meteorological radar outputs of the Zlín Region. Compared forecasting methods are used for the purposes of verification and configuration prediction parameters for accuracy increase of algorithm outputs.
4
Atashi, Vida, Hamed Taheri Gorji, Seyed Mojtaba Shahabi, Ramtin Kardan, and Yeo Howe Lim. "Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North." Water 14, no. 12 (June 20, 2022): 1971. http://dx.doi.org/10.3390/w14121971.
Повний текст джерелаАнотація:
The Red River of the North is vulnerable to floods, which have caused significant damage and economic loss to inhabitants. A better capability in flood-event prediction is essential to decision-makers for planning flood-loss-reduction strategies. Over the last decades, classical statistical methods and Machine Learning (ML) algorithms have greatly contributed to the growth of data-driven forecasting systems that provide cost-effective solutions and improved performance in simulating the complex physical processes of floods using mathematical expressions. To make improvements to flood prediction for the Red River of the North, this paper presents effective approaches that make use of a classical statistical method, a classical ML algorithm, and a state-of-the-art Deep Learning method. Respectively, the methods are seasonal autoregressive integrated moving average (SARIMA), Random Forest (RF), and Long Short-Term Memory (LSTM). We used hourly level records from three U.S. Geological Survey (USGS), at Pembina, Drayton, and Grand Forks stations with twelve years of data (2007–2019), to evaluate the water level at six hours, twelve hours, one day, three days, and one week in advance. Pembina, at the downstream location, has a water level gauge but not a flow-gauging station, unlike the others. The floodwater-level-prediction results show that the LSTM method outperforms the SARIMA and RF methods. For the one-week-ahead prediction, the RMSE values for Pembina, Drayton, and Grand Forks are 0.190, 0.151, and 0.107, respectively. These results demonstrate the high precision of the Deep Learning algorithm as a reliable choice for flood-water-level prediction.
5
Wu, Jian, Haixing Liu, Guozhen Wei, Tianyu Song, Chi Zhang, and Huicheng Zhou. "Flash Flood Forecasting Using Support Vector Regression Model in a Small Mountainous Catchment." Water 11, no. 7 (June 27, 2019): 1327. http://dx.doi.org/10.3390/w11071327.
Повний текст джерелаАнотація:
Flash floods in mountainous catchments are often caused by the rainstorm, which may result in more severe consequences than plain area floods due to less timescale and a fast-flowing front of water and debris. Flash flood forecasting is a huge challenge for hydrologists and managers due to its instantaneity, nonlinearity, and dependency. Among different methods of flood forecasting, data-driven models have become increasingly popular in recent years due to their strong ability to simulate nonlinear hydrological processes. This study proposed a Support Vector Regression (SVR) model, which is a powerful artificial intelligence-based model originated from statistical learning theory, to forecast flash floods at different lead times in a small mountainous catchment. The lagged average rainfall and runoff are identified as model input variables, and the time lags associated with the model input variables are determined by the hydrological concept of the time of response. There are 69 flash flood events collected from 1984 to 2012 in a mountainous catchment in China and then used for the model training and testing. The contribution of the runoff variables to the predictions and the phase lag of model outputs are analyzed. The results show that: (i) the SVR model has satisfactory predictive performances for one to three-hours ahead forecasting; (ii) the lagged runoff variables have a more significant effect on the predictions than the rainfall variables; and (iii) the phase lag (time difference) of prediction results significantly exists in both two- and three-hours-ahead forecasting models, however, the input rainfall information can assist in mitigating the phase lag of peak flow.
6
Le, Tuan Hoang, and Dung Anh To. "A Modified Semi-parametric Regression Model For Flood Forecasting." Science and Technology Development Journal 18, no. 2 (June 30, 2015): 95–105. http://dx.doi.org/10.32508/stdj.v18i2.1078.
Повний текст джерелаАнотація:
In recent years, inundation, one of natural calamities, occurs frequently and fiercely. We are sustained severe losses in the floods every year. Therefore, the development of control methods to determine, analyze, model and predict the floods is indispensable and urgent. In this paper, we propose a justified semiparametric regression model for flood water levels forecasting. The new model has three components. The first one is parametric elements of the model. They are water level, precipitation, evaporation, air-humidity and groundmoisture values, etc. There is a complex connection among these parametrics. Several innovated regression models have been offered and experimented for this complicated relationship. The second one is a non-parametric ingredient of our model. We use the Arnak S. Dalalyan et al.’s effective dimension-reduction subspace algorithm and some modified algorithms in neural networks to deal with it. They are altered back-propagation method and ameliorated cascade correlation algorithm. Besides, we also propose a new idea to modify the conjugate gradient one. These actions will help us to smooth the model’s non-parametric constituent easily and quickly. The last component is the model’s error. The whole elements are essential inputs to operational flood management. This work is usually very complex owing to the uncertain and unpredictable nature of underlying phenomena. Flood-waterlevels forecasting, with a lead time of one and more days, was made using a selected sequence of past water-level values observed at a specific location. Time-series analytical method is also utilized to build the model. The results obtained indicate that, with a new semiparametric regression one and the effective dimension-reduction subspace algorithm, together with some improved algorithms in neural network, the estimation power of the modern statistical model is reliable and auspicious, especially for flood forecasting/modeling.
7
Chen, Xinchi, Liping Zhang, Christopher James Gippel, Lijie Shan, Shaodan Chen, and Wei Yang. "Uncertainty of Flood Forecasting Based on Radar Rainfall Data Assimilation." Advances in Meteorology 2016 (2016): 1–12. http://dx.doi.org/10.1155/2016/2710457.
Повний текст джерелаАнотація:
Precipitation is the core data input to hydrological forecasting. The uncertainty in precipitation forecast data can lead to poor performance of predictive hydrological models. Radar-based precipitation measurement offers advantages over ground-based measurement in the quantitative estimation of temporal and spatial aspects of precipitation, but errors inherent in this method will still act to reduce the performance. Using data from White Lotus River of Hubei Province, China, five methods were used to assimilate radar rainfall data transformed from the classifiedZ-Rrelationship, and the postassimilation data were compared with precipitation measured by rain gauges. The five sets of assimilated rainfall data were then used as input to the Xinanjiang model. The effect of precipitation data input error on runoff simulation was analyzed quantitatively by disturbing the input data using the Breeding of Growing Modes method. The results of practical application demonstrated that the statistical weight integration and variational assimilation methods were superior. The corresponding performance in flood hydrograph prediction was also better using the statistical weight integration and variational methods compared to the others. It was found that the errors of radar rainfall data disturbed by the Breeding of Growing Modes had a tendency to accumulate through the hydrological model.
8
Abdul Majid, M., M. Hafidz Omar, M. Salmi M. Noorani, and F. Abdul Razak. "River-flood forecasting methods: the context of the Kelantan River in Malaysia." IOP Conference Series: Earth and Environmental Science 880, no. 1 (October 1, 2021): 012021. http://dx.doi.org/10.1088/1755-1315/880/1/012021.
Повний текст джерелаАнотація:
Abstract River-flood forecasting is among the most important feasible non-structural approaches used in reducing economic losses and alleviating human sufferings. In spite of uncertainty in the forecasting of natural disasters, the current prevailing methods developed in many parts of the world in the recent history has made good progress to a great extent. The advancement is attributed mainly due to the availability of high-resolution weather data and the use of sophisticated computer modelling algorithms. However, it is desirable to conduct exploratory review studies to further improving the current state of affairs. The present paper reviews briefly the river-flood forecasting methods currently used worldwide with a specific focus in the context of the Kelantan River in Malaysia. Flooding in Malaysia is recurrent covering a large inhabited area compared with other natural disasters. Some of the popularly used methods in the literature such as statistical methods machine learning and methods based on chaos theory have been reviewed, The paper will also attempt to explore the future direction for research and development that might be useful specifically for dealing with the recurrent rivers flooding in Malaysia. A reasonably acceptable prediction of river streamflow is significantly important in disaster management and water resources management.
9
Palash, Wahid, Yudan Jiang, Ali S. Akanda, David L. Small, Amin Nozari, and Shafiqul Islam. "A Streamflow and Water Level Forecasting Model for the Ganges, Brahmaputra, and Meghna Rivers with Requisite Simplicity." Journal of Hydrometeorology 19, no. 1 (January 2018): 201–25. http://dx.doi.org/10.1175/jhm-d-16-0202.1.
Повний текст джерелаАнотація:
A forecasting lead time of 5–10 days is desired to increase the flood response and preparedness for large river basins. Large uncertainty in observed and forecasted rainfall appears to be a key bottleneck in providing reliable flood forecasting. Significant efforts continue to be devoted to developing mechanistic hydrological models and statistical and satellite-driven methods to increase the forecasting lead time without exploring the functional utility of these complicated methods. This paper examines the utility of a data-based modeling framework with requisite simplicity that identifies key variables and processes and develops ways to track their evolution and performance. Findings suggest that models with requisite simplicity—relying on flow persistence, aggregated upstream rainfall, and travel time—can provide reliable flood forecasts comparable to relatively more complicated methods for up to 10 days lead time for the Ganges, Brahmaputra, and upper Meghna (GBM) gauging locations inside Bangladesh. Forecasting accuracy improves further by including weather-model-generated forecasted rainfall into the forecasting scheme. The use of water level in the model provides equally good forecasting accuracy for these rivers. The findings of the study also suggest that large-scale rainfall patterns captured by the satellites or weather models and their “predictive ability” of future rainfall are useful in a data-driven model to obtain skillful flood forecasts up to 10 days for the GBM basins. Ease of operationalization and reliable forecasting accuracy of the proposed framework is of particular importance for large rivers, where access to upstream gauge-measured rainfall and flow data are limited, and detailed modeling approaches are operationally prohibitive and functionally ineffective.
10
Le, Tuan Hoang, and Dung Anh To. "Short-term flood forecasting with an amended semi-parametric regression ensemble model." Science and Technology Development Journal 20, K2 (June 30, 2017): 117–25. http://dx.doi.org/10.32508/stdj.v20ik2.457.
Повний текст джерелаАнотація:
Flood forecasting is very important research topic in disaster prevention and reduction. The characteristics of flood involve a rather complex systematic dynamic under the influence of different meteorological factors including linear and non-linear patterns. Recently there are many novel forecasting methods of improving the forecasting accuracy. This paper explores the potential and effect of the semiparametric regression to modelize flood water-level and to forecast the inundation of Mekong Delta in Vietnam. The semi-parametric regression technique is a combination of a parametric regression approach and a non-parametric regression concept. In the process of model building, three altered linear regression models are applied for the parametric component. They are stepwise multiple linear regression, partial least squares solution and multirecursive regression method. They are used to capture flood’s linear characteristics. The nonparametric part is solved by a modified estimation of a smooth function. Furthermore, some justified nonlinear regression models based on artificial neural network are also able to obtain flood’s non-linear characteristics. They help us to smooth the model's non-parametric constituent easily and quickly. The last element is the model's error. Then the semiparametric regression is used for ensemble model based on the principle component analysis technique. Flood water-level forecasting, with a lead time of one and more days, has been made by using a selected sequence of past water-level values and some relevant factors observed at a specific location. Time-series analytical method is utilized to build the model. Obtained empirical results indicate that the prediction by using the amended semi-parametric regression ensemble model is generally better than those obtained by using the other models presented in this study in terms of the same evaluation measurements. Our findings reveal that the estimation power of the modern statistical model is reliable and auspicious. The proposed model here can be used as a promising alternative forecasting tool for flood to achieve better forecasting accuracy and to optimize prediction quality further.
11
Mahabir, C., F. E. Hicks, C. Robichaud, and A. Robinson Fayek. "Forecasting breakup water levels at Fort McMurray, Alberta, using multiple linear regression." Canadian Journal of Civil Engineering 33, no. 9 (September 1, 2006): 1227–38. http://dx.doi.org/10.1139/l06-067.
Повний текст джерелаАнотація:
Spring breakup on northern rivers can result in ice jams that present severe flood risk to adjacent communities. Such events can occur extremely rapidly, leaving little or no advanced warning to residents. Fort McMurray, Alberta, is one such community, and at present no forecasting model exists for this site. Many of the previous studies regarding ice jam flood forecasting methods, in general, cite the lack of a comprehensive database as an obstacle to statistical modelling. This paper documents the development of an extensive database containing 106 variables, and covering the period from 1972 to 2004, that was created for ice jam forecasting on the Athabasca River. Through multiple linear regression analysis, equations were developed to model the maximum water level during spring breakup. The optimal model contained a combination of hydrological and meteorological data collected from early fall until the day before river ice breakup. The number of historical years of data, rather than the scope of variables, was found to be the major limitation in verifying the results presented in this study.Key words: river ice, breakup jam, multiple linear regression.
12
Rijal, Krishna Prasad. "Comparative Study of Flood Calculation Approaches, a Case Study of East Rapti River Basin, Nepal." Hydro Nepal: Journal of Water, Energy and Environment 15 (October 22, 2014): 60–64. http://dx.doi.org/10.3126/hn.v15i0.11296.
Повний текст джерелаАнотація:
Various approaches to high flood calculation have been used to inform the design of hydraulic structures and flood protection works in Nepal. To assess potential flood volumes, a variety of methods and calculations are employed and the highest figure is adopted as correct so as to err on the side of safety. This approach, while safe, can result in excessively uneconomic design. As well, this approach erodes the designer’s confidence in the process to determine the potential flood volume and perpetuates such sub-optimal approaches. Through the case study of East Rapti River, this paper tries to shed light on various ungauged basin approaches of flood prediction currently in practice. It also compares the relative performance of those approaches using statistical methods and observed data. From the study, Jha PCJ method (1996) yielded a comparable result with the gauged basin methods. A remarkably notable fact obtained is that all the ungauged basin methods except rational method underestimated the flood discharge as compared to that obtained from the frequency analysis based on measured data sets. Overall, our study concludes that flood forecasting on ungauged basins cannot be recommended because a number of assumptions and personal judgments influence each of the prediction methods. Therefore, a more radical shift to basin specific intensive research is desirableDOI: http://dx.doi.org/10.3126/hn.v15i0.11296HYDRO Nepal JournalJournal of Water, Energy and EnvironmentVolume: 15, 2014, JulyPage: 60-64
13
Olsson, J., C. B. Uvo, K. Foster, and W. Yang. "Initial assessment of a multi-model approach to spring flood forecasting in Sweden." Hydrology and Earth System Sciences Discussions 12, no. 6 (June 23, 2015): 6077–113. http://dx.doi.org/10.5194/hessd-12-6077-2015.
Повний текст джерелаАнотація:
Abstract. Hydropower is a major energy source in Sweden and proper reservoir management prior to the spring flood onset is crucial for optimal production. This requires useful forecasts of the accumulated discharge in the spring flood period (i.e. the spring-flood volume, SFV). Today's SFV forecasts are generated using a model-based climatological ensemble approach, where time series of precipitation and temperature from historical years are used to force a calibrated and initialised set-up of the HBV model. In this study, a number of new approaches to spring flood forecasting, that reflect the latest developments with respect to analysis and modelling on seasonal time scales, are presented and evaluated. Three main approaches, represented by specific methods, are evaluated in SFV hindcasts for three main Swedish rivers over a 10-year period with lead times between 0 and 4 months. In the first approach, historically analogue years with respect to the climate in the period preceding the spring flood are identified and used to compose a reduced ensemble. In the second, seasonal meteorological ensemble forecasts are used to drive the HBV model over the spring flood period. In the third approach, statistical relationships between SFV and the large-sale atmospheric circulation are used to build forecast models. None of the new approaches consistently outperform the climatological ensemble approach, but for specific locations and lead times improvements of 20–30 % are found. When combining all forecasts in a weighted multi-model approach, a mean improvement over all locations and lead times of nearly 10 % was indicated. This demonstrates the potential of the approach and further development and optimisation into an operational system is ongoing.
14
Olsson, J., C. B. Uvo, K. Foster, and W. Yang. "Technical Note: Initial assessment of a multi-method approach to spring-flood forecasting in Sweden." Hydrology and Earth System Sciences 20, no. 2 (February 10, 2016): 659–67. http://dx.doi.org/10.5194/hess-20-659-2016.
Повний текст джерелаАнотація:
Abstract. Hydropower is a major energy source in Sweden, and proper reservoir management prior to the spring-flood onset is crucial for optimal production. This requires accurate forecasts of the accumulated discharge in the spring-flood period (i.e. the spring-flood volume, SFV). Today's SFV forecasts are generated using a model-based climatological ensemble approach, where time series of precipitation and temperature from historical years are used to force a calibrated and initialized set-up of the HBV model. In this study, a number of new approaches to spring-flood forecasting that reflect the latest developments with respect to analysis and modelling on seasonal timescales are presented and evaluated. Three main approaches, represented by specific methods, are evaluated in SFV hindcasts for the Swedish river Vindelälven over a 10-year period with lead times between 0 and 4 months. In the first approach, historically analogue years with respect to the climate in the period preceding the spring flood are identified and used to compose a reduced ensemble. In the second, seasonal meteorological ensemble forecasts are used to drive the HBV model over the spring-flood period. In the third approach, statistical relationships between SFV and the large-sale atmospheric circulation are used to build forecast models. None of the new approaches consistently outperform the climatological ensemble approach, but for early forecasts improvements of up to 25 % are found. This potential is reasonably well realized in a multi-method system, which over all forecast dates reduced the error in SFV by ∼ 4 %. This improvement is limited but potentially significant for e.g. energy trading.
15
Sarafanov, Mikhail, Yulia Borisova, Mikhail Maslyaev, Ilia Revin, Gleb Maximov, and Nikolay O. Nikitin. "Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River." Water 13, no. 24 (December 7, 2021): 3482. http://dx.doi.org/10.3390/w13243482.
Повний текст джерелаАнотація:
The paper presents a hybrid approach for short-term river flood forecasting. It is based on multi-modal data fusion from different sources (weather stations, water height sensors, remote sensing data). To improve the forecasting efficiency, the machine learning methods and the Snowmelt-Runoff physical model are combined in a composite modeling pipeline using automated machine learning techniques. The novelty of the study is based on the application of automated machine learning to identify the individual blocks of a composite pipeline without involving an expert. It makes it possible to adapt the approach to various river basins and different types of floods. Lena River basin was used as a case study since its modeling during spring high water is complicated by the high probability of ice-jam flooding events. Experimental comparison with the existing methods confirms that the proposed approach reduces the error at each analyzed level gauging station. The value of Nash–Sutcliffe model efficiency coefficient for the ten stations chosen for comparison is 0.80. The other approaches based on statistical and physical models could not surpass the threshold of 0.74. Validation for a high-water period also confirms that a composite pipeline designed using automated machine learning is much more efficient than stand-alone models.
16
Tiampo, Kristy F., Lingcao Huang, Conor Simmons, Clay Woods, and Margaret T. Glasscoe. "Detection of Flood Extent Using Sentinel-1A/B Synthetic Aperture Radar: An Application for Hurricane Harvey, Houston, TX." Remote Sensing 14, no. 9 (May 8, 2022): 2261. http://dx.doi.org/10.3390/rs14092261.
Повний текст джерелаАнотація:
The increasing number of flood events combined with coastal urbanization has contributed to significant economic losses and damage to buildings and infrastructure. Development of higher resolution SAR flood mapping that accurately identifies flood features at all scales can be incorporated into operational flood forecasting tools, improving response and resilience to large flood events. Here, we present a comparison of several methods for characterizing flood inundation using a combination of synthetic aperture radar (SAR) remote sensing data and machine learning methods. We implement two applications with SAR GRD data, an amplitude thresholding technique applied, for the first time, to Sentinel-1A/B SAR data, and a machine learning technique, DeepLabv3+. We also apply DeepLabv3+ to a false color RGB characterization of dual polarization SAR data. Analyses at 10 m pixel spacing are performed for the major flood event associated with Hurricane Harvey and associated inundation in Houston, TX in August of 2017. We compare these results with high-resolution aerial optical images over this time period, acquired by the NOAA Remote Sensing Division. We compare the results with NDWI produced from Sentinel-2 images, also at 10 m pixel spacing, and statistical testing suggests that the amplitude thresholding technique is the most effective, although the machine learning analysis is successful at reproducing the inundation shape and extent. These results demonstrate the effectiveness of flood inundation mapping at unprecedented resolutions and its potential for use in operational emergency hazard response to large flood events.
17
Sahoo, A., and D. K. Ghose. "Application of Hybrid Support Vector Machine model for Streamflow Prediction in Barak valley, India." IOP Conference Series: Earth and Environmental Science 1032, no. 1 (June 1, 2022): 012016. http://dx.doi.org/10.1088/1755-1315/1032/1/012016.
Повний текст джерелаАнотація:
Abstract Forecasting streamflow (Qflow) is vital in flood and water management, determining potential of river water flow, agricultural practices, hydropower generation, and environmental flow study. This research aims to explore capability of hybrid support vector machines (SVM) with Whale Optimisation Algorithm (WOA) model for forecasting streamflow at Badarpur Ghat gauging station of Barak river basin and evaluate its enactment with the conventional SVM model. Root mean squared error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NSE) statistical measures are considered as evaluating standards. Assessment of outcomes indicates that the optimization algorithm could enhance the accurateness of standalone SVM model in monthly streamflow forecasting. Compared to conventional artificial intelligence methods without a data pre-processing system, the comparatively good performance of applied hybrid model gives an effective alternate to achieve better precision in streamflow forecasting. Results confirm that enhanced SVM model can better process a multifaceted hydrogeological data set, have higher prediction accuracy, and possess better generalisation capability.
18
Kholoptsev, Alexander, Sergei Podporin, and Evgeniy OlKhovik. "Impact of Floods in the Kolyma River Delta on Navigation Conditions in the East Siberian Sea." E3S Web of Conferences 363 (2022): 01004. http://dx.doi.org/10.1051/e3sconf/202236301004.
Повний текст джерелаАнотація:
Problem of improving the quality of medium- and long-term forecasting of changes in ice conditions in the Northern Sea Route, and in particular in the east Siberian sea, where one of the methods of selecting waterways is the passage of ships in areas of ice-covered polynya. The hypothesis is verified that during the summer months, such changes may be significantly influenced by the timing of the onset of high water in the Kolyma River delta. Data from the global reanalysis GLORYS12v1 supported by the European Copernicus Marine Service were used as factual material on the ice cover and levels of the East Siberian Sea in the months of May to October 1993-2019. The analysis is based on mathematical models of the NEMO family verified by satellite altimetry data. Using the developed methodology, the dates of abrupt changes in level and sea ice extent on the Kolyma River estuarine seashore have been estimated for selected periods of the year. The study uses statistical methods to confirm the validity of the stated hypothesis for a number of areas of the East Siberian Sea, through which the shipping routes of the Northern Sea Route pass. It has been established that the greatest influence of flood timing on ice conditions and navigation conditions in such areas takes place in July. It is shown that early floods in the Kolyma delta generally lead to improvement of ice conditions, while late floods lead to complication of ice conditions. The identified relationships are recommended for use in forecasting changes in ice conditions. It has been suggested that with further climate warming and shifting of flood dates to earlier dates, the complication of ice conditions due to freezing of the formed polynya is not excluded.
19
Yeditha, Pavan Kumar, Venkatesh Kasi, Maheswaran Rathinasamy, and Ankit Agarwal. "Forecasting of extreme flood events using different satellite precipitation products and wavelet-based machine learning methods." Chaos: An Interdisciplinary Journal of Nonlinear Science 30, no. 6 (June 2020): 063115. http://dx.doi.org/10.1063/5.0008195.
Повний текст джерела
20
Bogner, K., F. Pappenberger, and H. L. Cloke. "Technical Note: The Normal Quantile Transformation and its application in a flood forecasting system." Hydrology and Earth System Sciences Discussions 8, no. 5 (October 17, 2011): 9275–97. http://dx.doi.org/10.5194/hessd-8-9275-2011.
Повний текст джерелаАнотація:
Abstract. The Normal Quantile Transform (NQT) has been used in many hydrological and meteorological applications in order to make the Cumulated Density Function (CDF) of the observed, simulated and forecast river discharge, water level or precipitation data Gaussian. It is also the heart of the meta-Gaussian model for assessing the total predictive uncertainty of the Hydrological Uncertainty Processor (HUP) developed by Krzysztofowicz. In the field of geo-statistics this transformation is better known as Normal-Score Transform. In this paper some possible problems caused by small sample sizes for the applicability in flood forecasting systems will be discussed and illustrated by examples. For the practical implementation commands and examples from the freely available and widely used statistical computing language R (R Development Core Team, 2011) will be given (represented in Courier font) and possible solutions are suggested by combining extreme value analysis and non-parametric regression methods.
21
Tayyab, Muhammad, Jianzhong Zhou, Xiaofan Zeng, and Rana Adnan. "Discharge Forecasting By Applying Artificial Neural Networks At The Jinsha River Basin, China." European Scientific Journal, ESJ 12, no. 9 (March 30, 2016): 108. http://dx.doi.org/10.19044/esj.2016.v12n9p108.
Повний текст джерелаАнотація:
Flood prediction methods play an important role in providing early warnings to government offices. The ability to predict future river flows helps people anticipate and plan for upcoming flooding, preventing deaths and decreasing property destruction. Different hydrological models supporting these predictions have different characteristics, driven by available data and the research area. This study applied three different types of Artificial Neural Networks (ANN) and an autoregressive model to study the Jinsha river basin (JRB), in the upper part of the Yangtze River in China. The three ANN techniques include feedforward back propagation neural networks (FFBPNN), generalized regression neural networks (GRNN), and the radial basis function neural networks (RBFNN). Artificial Neural Networks (ANN) has shown Great deal of accuracy as compared to statistical autoregressive (AR) model because statistical model cannot able to simulate the non-linear pattern. The results varied across the cases used in the study; based on available data and the study area, FFBPNN showed the best applicability, compared to other techniques.
22
Waller, Joanne A., Javier García-Pintado, David C. Mason, Sarah L. Dance, and Nancy K. Nichols. "Technical note: Assessment of observation quality for data assimilation in flood models." Hydrology and Earth System Sciences 22, no. 7 (July 23, 2018): 3983–92. http://dx.doi.org/10.5194/hess-22-3983-2018.
Повний текст джерелаАнотація:
Abstract. The assimilation of satellite-based water level observations (WLOs) into 2-D hydrodynamic models can keep flood forecasts on track or be used for reanalysis to obtain improved assessments of previous flood footprints. In either case, satellites provide spatially dense observation fields, but with spatially correlated errors. To date, assimilation methods in flood forecasting either incorrectly neglect the spatial correlation in the observation errors or, in the best of cases, deal with it by thinning methods. These thinning methods result in a sparse set of observations whose error correlations are assumed to be negligible. Here, with a case study, we show that the assimilation diagnostics that make use of statistical averages of observation-minus-background and observation-minus-analysis residuals are useful to estimate error correlations in WLOs. The average estimated correlation length scale of 7 km is longer than the expected value of 250 m. Furthermore, the correlations do not decrease monotonically; this unexpected behaviour is shown to be the result of assimilating some anomalous observations. Accurate estimates of the observation error statistics can be used to support quality control protocols and provide insight into which observations it is most beneficial to assimilate. Therefore, the understanding gained in this paper will contribute towards the correct assimilation of denser datasets.
23
Kholoptsev, Aleksandr V., and Sergey A. Podporin. "IMPACT OF FLOODS IN THE KOLYMA RIVER DELTA ON NAVIGATION CONDITIONS IN THE EAST SIBERIAN SEA." Vestnik Gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S. O. Makarova 14, no. 4 (September 13, 2022): 563–70. http://dx.doi.org/10.21821/2309-5180-2022-14-4-563-570.
Повний текст джерелаАнотація:
The problem of improving the quality of medium- and long-term forecasting of changes in the ice situation on the Northern Sea Route, and in particular in the East Siberian Sea, where one of the methods for choosing waterways is the passage of vessels in the areas of flaw polynya, is considered. The hypothesis that in the summer months such changes can be significantly affected by the terms of floods onset in the Kolyma River Delta is tested. The data of the GLORYS12v1 global reanalysis supported by the Copernicus Marine Service are used as factual material on the ice cover and levels of the East Siberian Sea in the months from May to October of 1993-2019. The reanalysis is based on mathematical models of the NEMO family, verified using altimetry data from satellite measurements. Using the developed methodology for the selected periods of the year, the dates of sharp changes in the level and ice cover on the pre-estuary seaside of the Kolyma River are estimated. Using statistical methods, the validity of the stated hypothesis for a number of the East Siberian Sea areas, along which the shipping lanes of the Northern Sea Route pass, is confirmed. It has been established that the greatest influence of the floods terms on the ice situation and navigation conditions in such areas takes place in July. It has been shown that early floods in the Kolyma delta generally lead to an improvement in the ice situation, and late floods lead to its complication. The identified relationships are recommended for use in forecasting changes in ice conditions. The assumption that with further climate warming and a shift in the flood terms to earlier dates, it is possible that the ice conditions will become more complicated due to the freezing of the formed polynya, is made.
24
Palchevsky, E. V., and V. V. Antonov. "Decision Support System based on Application of the Second Generation Neural Network." Programmnaya Ingeneria 13, no. 6 (June 22, 2022): 301–8. http://dx.doi.org/10.17587/prin.13.301-308.
Повний текст джерелаАнотація:
The issue of the feasibility of using existing statistical and hydrological methods for short-term and early forecasting in the framework of forecasting the levels of water rise in water bodies is considered: a comparative review is given, which describes their advantages and disadvantages. In the course of analyzing the shortcomings of these methods, the problem of operational and early (advance) forecasting of water rise levels was identified. To solve this problem, a decision support system is proposed for predicting the water rise levels in advance, based on a neural network (intelligent) analysis of retrospective data (date, water level, air temperature, atmospheric pressure and wind speed) to calculate the water level values for 5 days in advance. The artificial neural network itself is based on the freely distributed library of machine learning programs "TensorFlow", and a modified backpropagation method is used as training, the main difference of which is an increase in the learning rate of an artificial neural network. The results of the analysis of the effectiveness showed that the proposed decision support system is more accurate (the error between the real and calculated values does not exceed 2.10 %), compared to existing common methods/systems (8.36 %). This will allow to give the necessary time to special services for the implementation of flood control measures to prepare for the protection of technical facilities of enterprises.
25
Kadim, Maher Abd Ameer, Isam Issa Omran, and Alaa Ali Salman Al-Taai. "Optimization of the Nonlinear Muskingum Model Parameters for the River Routing, Tigris River a Case Study." International Journal of Design & Nature and Ecodynamics 16, no. 6 (December 21, 2021): 649–56. http://dx.doi.org/10.18280/ijdne.160605.
Повний текст джерелаАнотація:
Flood forecasting and management are one of the most important strategies necessary for water resource and decision planners in combating flood problems. The Muskingum model is one of the most popular and widely used applications for the purpose of predicting flood routing. The particle swarm optimization (PSO) methodology was used to estimate the coefficients of the nonlinear Muskingum model in this study, comparing the results with the methods of genetic algorithm (GA), harmony search (HS), least-squares method (LSM), and Hook-Jeeves (HJ). The average monthly inflow for the Tigris River upstream at the Al-Mosul dam was selected as a case study for estimating the Muskingum model's parameters. The analytical and statistical results showed that the PSO method is the best application and corresponds to the results of the Muskingum model, followed by the genetic algorithm method, according to the following general descending sequence: PSO, GA, LSM, HJ, HS. The PSO method is characterized by its accurate results and does not require many assumptions and conditions for its application, which facilitates its use a lot in the subject of hydrology. Therefore, it is better to recommend further research in the use of this method in the implementation of future studies and applications.
26
Dokus, A. O., and ZH R. Shakirzanova. "Zoning of the Southern Buh River Basin Under the Conditions of Spring Flood Formation." 36, no. 36 (December 28, 2021): 8–21. http://dx.doi.org/10.26565/1992-4224-2021-36-01.
Повний текст джерелаАнотація:
The Southern Buh river basin is located in three natural zones of Ukraine and is heterogeneous in terms of physical and geographical conditions of river runoff formation. Purpose. Carry out hydrological zoning of the Southern Buh river basin with the allocation of areas with the same conditions for the spring floods formation by a set of morphometric characteristics of rivers and their basins and hydrometeorological and agrometeorological factors. Methods. Using a statistical model of factor analysis (R-modification) the most significant factors from the totality of all features were identified. There are two factors – the first describes 38% of the total variance of all factors (latitude of catchment centers, average height of catchments, wetlands, water reserves in the snow cover, precipitation of snowmelt and maximum depth of soil freezing), and the second – 21% (river length, catchment area and the amount of precipitation that fell after snowmelt). Factor loads were used for further grouping of basins using the method of cluster analysis. Results. As a result of territory zoning, two hydrological districts with sub-districts (district I and district II with sub-districts IIa, IIb, IIc) were identified. Area I covers the area from the source to hydrological post on the Southern Buh river basin – Trostyanchik village. Downstream and to the river mouth, the territory covers area II, which is divided into three sub-areas (sub-area IIa, IIb, IIc). Data from small rivers between the Dniester and the Southern Buh are involved in the hydrographical network. The boundaries of hydrological districts in the Southern Buh river basin were drawn along the watersheds of rivers, taking into account the physical and geographical zoning of the territory and involving in the analysis of maps of soil cover and vegetation in the basin. The hydrological zoning of the Southern Buh river basin under the conditions of spring flood formation is in good agreement with the zoning of the plain territory of Ukraine, which was performed by different authors over time. Conclusions. The use of statistical methods in the work allowed to clarify the boundaries of existing districts and identify new sub-districts in the Southern Buh river basin. The analyzed natural conditions have shown that within the limits of hydrological zoning they have certain features of spring floods formation. Such features will be used in the substantiation of the regional method of long-term forecasting of the characteristics of spring flood in the Southern Buh river basin.
27
MARGARYAN, Varduhi, Ekaterina GAIDUKOVA, Igor Vinokurov, and Nikolay RESHIN. "On assessment and management of hydrological risks during spring flood in the River Arpa Basin (Republic of Armenia)." Sustainable Development of Mountain Territories 14, no. 2 (June 30, 2022): 240–51. http://dx.doi.org/10.21177/1998-4502-2022-14-2-240-251.
Повний текст джерелаАнотація:
Introduction. Issues of formation of maximum expenses and their forecast, risk extreme flow rates on the rivers of Armenia represents a significant interest for consumers of water resources. The works of scientists of the Republic of Armenia are devoted to the solution of this problem: (Vardanyan T. G., Muradyan Z. Z., 2014), forecasting the maximum water flow for the Jermuk hydrological station on the Arpa River (Misakyan A. E., Azizyan L. V., Azizyan A. O., 2014), assessment of long-term fluctuations of the maximum runoff of rivers in the mountainous territories of Armenia in the context of global changes climate (Margaryan V. G., Ovcharuk V. A., Goptsy M. V. Borovskaya G. A., 2020). This paper analyzes the risks of extreme spring runoff river flood Arpa (Republic of Armenia) related to degree assessment the danger of flood waves. Problem solving can help prevent economic damage and loss of life, and raise issue of extreme runoff risk management. Unlike listed works, this study uses longer series of actual observations and a certain section of the river. Purpose of research. Assessment and management of hydrological risks during the period spring flood in the river basin Arpa. Methods. The work used the methods: of mathematical-statistical, extrapolation, analysis, analogy, correlation. Results. Correlations between the values of the modulus of extreme costs 1 and 10 % security and weighted average height drainage basin, as well as the relatively close relationship between the average values of extreme costs for the periods 2001–2020 and 1981–2000 biennium, integral curve of extreme flow rates of floods in the section Yeghegnadzor of the Arpa River. These dependencies can be used to preliminary estimates of the maximum runoff of the spring flood unexplored rivers of the considered territory. To manage and planning of extreme water resources, multifactorial dependencies that can be applied when making forecasts. The rate of extreme flow rates of the spring flood has been calculated, coefficients of variability (Cv) and skewness (Cs), absolute maximum costs of various security. Conclusion. Average values of extreme water flow rates of the river. Arpa for the period 2001–2020 mostly inferior or slightly higher than average values for the period 1981–2000. In the Arpa river basin from 1981 to 2020 year mainly there is a tendency of decreasing extreme river flow, that is, the degree of risk of extreme expenses.
28
Zhou, Z. G., P. Tang, and M. Zhou. "ESTIMATING RELIABILITY OF DISTURBANCES IN SATELLITE TIME SERIES DATA BASED ON STATISTICAL ANALYSIS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B3 (June 9, 2016): 549–54. http://dx.doi.org/10.5194/isprs-archives-xli-b3-549-2016.
Повний текст джерелаАнотація:
Normally, the status of land cover is inherently dynamic and changing continuously on temporal scale. However, disturbances or abnormal changes of land cover — caused by such as forest fire, flood, deforestation, and plant diseases — occur worldwide at unknown times and locations. Timely detection and characterization of these disturbances is of importance for land cover monitoring. Recently, many time-series-analysis methods have been developed for near real-time or online disturbance detection, using satellite image time series. However, the detection results were only labelled with “Change/ No change” by most of the present methods, while few methods focus on estimating reliability (or confidence level) of the detected disturbances in image time series. To this end, this paper propose a statistical analysis method for estimating reliability of disturbances in new available remote sensing image time series, through analysis of full temporal information laid in time series data. The method consists of three main steps. (1) Segmenting and modelling of historical time series data based on Breaks for Additive Seasonal and Trend (BFAST). (2) Forecasting and detecting disturbances in new time series data. (3) Estimating reliability of each detected disturbance using statistical analysis based on Confidence Interval (CI) and Confidence Levels (CL). The method was validated by estimating reliability of disturbance regions caused by a recent severe flooding occurred around the border of Russia and China. Results demonstrated that the method can estimate reliability of disturbances detected in satellite image with estimation error less than 5% and overall accuracy up to 90%.
29
Zhou, Z. G., P. Tang, and M. Zhou. "ESTIMATING RELIABILITY OF DISTURBANCES IN SATELLITE TIME SERIES DATA BASED ON STATISTICAL ANALYSIS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B3 (June 9, 2016): 549–54. http://dx.doi.org/10.5194/isprsarchives-xli-b3-549-2016.
Повний текст джерелаАнотація:
Normally, the status of land cover is inherently dynamic and changing continuously on temporal scale. However, disturbances or abnormal changes of land cover — caused by such as forest fire, flood, deforestation, and plant diseases — occur worldwide at unknown times and locations. Timely detection and characterization of these disturbances is of importance for land cover monitoring. Recently, many time-series-analysis methods have been developed for near real-time or online disturbance detection, using satellite image time series. However, the detection results were only labelled with “Change/ No change” by most of the present methods, while few methods focus on estimating reliability (or confidence level) of the detected disturbances in image time series. To this end, this paper propose a statistical analysis method for estimating reliability of disturbances in new available remote sensing image time series, through analysis of full temporal information laid in time series data. The method consists of three main steps. (1) Segmenting and modelling of historical time series data based on Breaks for Additive Seasonal and Trend (BFAST). (2) Forecasting and detecting disturbances in new time series data. (3) Estimating reliability of each detected disturbance using statistical analysis based on Confidence Interval (CI) and Confidence Levels (CL). The method was validated by estimating reliability of disturbance regions caused by a recent severe flooding occurred around the border of Russia and China. Results demonstrated that the method can estimate reliability of disturbances detected in satellite image with estimation error less than 5% and overall accuracy up to 90%.
30
Dawson, C. W., and R. L. Wilby. "Hydrological modelling using artificial neural networks." Progress in Physical Geography: Earth and Environment 25, no. 1 (March 2001): 80–108. http://dx.doi.org/10.1177/030913330102500104.
Повний текст джерелаАнотація:
This review considers the application of artificial neural networks (ANNs) to rainfall-runoff modelling and flood forecasting. This is an emerging field of research, characterized by a wide variety of techniques, a diversity of geographical contexts, a general absence of intermodel comparisons, and inconsistent reporting of model skill. This article begins by outlining the basic principles of ANN modelling, common network architectures and training algorithms. The discussion then addresses related themes of the division and preprocessing of data for model calibration/validation; data standardization techniques; and methods of evaluating ANN model performance. A literature survey underlines the need for clear guidance in current modelling practice, as well as the comparison of ANN methods with more conventional statistical models. Accordingly, a template is proposed in order to assist the construction of future ANN rainfall-runoff models. Finally, it is suggested that research might focus on the extraction of hydrological ‘rules’ from ANN weights, and on the development of standard performance measures that penalize unnecessary model complexity.
31
Fang, Wei, Yu Sha, and Victor S. Sheng. "Survey on the Application of Artificial Intelligence in ENSO Forecasting." Mathematics 10, no. 20 (October 14, 2022): 3793. http://dx.doi.org/10.3390/math10203793.
Повний текст джерелаАнотація:
Climate disasters such as floods and droughts often bring heavy losses to human life, national economy, and public safety. El Niño/Southern Oscillation (ENSO) is one of the most important inter-annual climate signals in the tropics and has a global impact on atmospheric circulation and precipitation. To address the impact of climate change, accurate ENSO forecasts can help prevent related climate disasters. Traditional prediction methods mainly include statistical methods and dynamic methods. However, due to the variability and diversity of the temporal and spatial evolution of ENSO, traditional methods still have great uncertainty in predicting ENSO. In recent years, with the rapid development of artificial intelligence technology, it has gradually penetrated into all aspects of people’s lives, and the climate field has also benefited. For example, deep learning methods in artificial intelligence can automatically learn and train from a large amount of sample data, obtain excellent feature representation, and effectively improve the performance of various learning tasks. It is widely used in computer vision, natural language processing, and other fields. In 2019, Ham et al. used a convolutional neural network (CNN) model in ENSO forecasting 18 months in advance, and the winter ENSO forecasting skill could reach 0.64, far exceeding the dynamic model with a forecasting skill of 0.5. The research results were regarded as the pioneering work of deep learning in the field of weather forecasting. This paper introduces the traditional ENSO forecasting methods and focuses on summarizing the various latest artificial intelligence methods and their forecasting effects for ENSO forecasting, so as to provide useful reference for future research by researchers.
32
Lin, Chun-Cheng, Rou-Xuan He, and Wan-Yu Liu. "Considering Multiple Factors to Forecast CO2 Emissions: A Hybrid Multivariable Grey Forecasting and Genetic Programming Approach." Energies 11, no. 12 (December 7, 2018): 3432. http://dx.doi.org/10.3390/en11123432.
Повний текст джерелаАнотація:
Development of technology and economy is often accompanied by surging usage of fossil fuels. Global warming could speed up air pollution and cause floods and droughts, not only affecting the safety of human beings, but also causing drastic economic changes. Therefore, the trend of carbon dioxide emissions and the factors affecting growth of emissions have drawn a lot of attention in all countries in the world. Related studies have investigated many factors that affect carbon emissions such as fuel consumption, transport emissions, and national population. However, most of previous studies on forecasting carbon emissions hardly considered more than two factors. In addition, conventional statistical methods of forecasting carbon emissions usually require some assumptions and limitations such as normal distribution and large dataset. Consequently, this study proposes a two-stage forecasting approach consisting of multivariable grey forecasting model and genetic programming. The multivariable grey forecasting model at the first stage enjoys the advantage of introducing multiple factors into the forecasting model, and can accurately make prediction with only four or more samples. However, grey forecasting may perform worse when the data is nonlinear. To overcome this problem, the second stage is to adopt genetic programming to establish the error correction model to reduce the prediction error. To evaluating performance of the proposed approach, the carbon dioxide emissions in Taiwan from 2000 to 2015 are forecasted and analyzed. Experimental comparison on various combinations of multiple factors shows that the proposed forecasting approach has higher accuracy than previous approaches.
33
Foster, Kean, Cintia Bertacchi Uvo, and Jonas Olsson. "The development and evaluation of a hydrological seasonal forecast system prototype for predicting spring flood volumes in Swedish rivers." Hydrology and Earth System Sciences 22, no. 5 (May 18, 2018): 2953–70. http://dx.doi.org/10.5194/hess-22-2953-2018.
Повний текст джерелаАнотація:
Abstract. Hydropower makes up nearly half of Sweden's electrical energy production. However, the distribution of the water resources is not aligned with demand, as most of the inflows to the reservoirs occur during the spring flood period. This means that carefully planned reservoir management is required to help redistribute water resources to ensure optimal production and accurate forecasts of the spring flood volume (SFV) is essential for this. The current operational SFV forecasts use a historical ensemble approach where the HBV model is forced with historical observations of precipitation and temperature. In this work we develop and test a multi-model prototype, building on previous work, and evaluate its ability to forecast the SFV in 84 sub-basins in northern Sweden. The hypothesis explored in this work is that a multi-model seasonal forecast system incorporating different modelling approaches is generally more skilful at forecasting the SFV in snow dominated regions than a forecast system that utilises only one approach. The testing is done using cross-validated hindcasts for the period 1981–2015 and the results are evaluated against both climatology and the current system to determine skill. Both the multi-model methods considered showed skill over the reference forecasts. The version that combined the historical modelling chain, dynamical modelling chain, and statistical modelling chain performed better than the other and was chosen for the prototype. The prototype was able to outperform the current operational system 57 % of the time on average and reduce the error in the SFV by ∼ 6 % across all sub-basins and forecast dates.
34
Kumar, Dilip, and Rajib Kumar Bhattacharjya. "Evaluating two GIS-based semi-distributed hydrological models in the Bhagirathi-Alkhnanda River catchment in India." Water Policy 22, no. 6 (October 20, 2020): 991–1014. http://dx.doi.org/10.2166/wp.2020.159.
Повний текст джерелаАнотація:
Abstract The hydrological models are used for simulating the runoff of a river basin based on available rainfall data and other parameters. Over the years, several hydrological models have been developed in different parts of the world. Two such semi-distributed hydrologic models are SWAT and HEC-HMS. In this study, a comparative analysis has been carried out to evaluate the performance of these two distributed hydrological models as a flood forecasting tool. The Alkhnanda and Bhagirathi rivers, which flow into the Tehri Reservoir, Uttarakhand and pass through Tehri, Uttarkashi and Chamoli districts of Uttarakhand, India, are selected for the analysis. The performance of these two models is evaluated by using standard statistical methods. The comparative analysis of these two models shows that the SWAT model is performing slightly better in comparison to the HEC-HMS model, especially in the lean period. The underestimation of peak discharge may be due to the contribution of significant snowmelt discharge during the rainy season. The models are also used to predict future discharge under different climate change scenarios. The future prediction shows that the peak discharge of Alkhnanda may be increased by 27 and 47% under RCP4.5 and RCP8.5, respectively.
35
Li, Xiao, Liping Zhang, Sidong Zeng, Zhenyu Tang, Lina Liu, Qin Zhang, Zhengyang Tang, and Xiaojun Hua. "Predicting Monthly Runoff of the Upper Yangtze River Based on Multiple Machine Learning Models." Sustainability 14, no. 18 (September 6, 2022): 11149. http://dx.doi.org/10.3390/su141811149.
Повний текст джерелаАнотація:
Accurate monthly runoff prediction is significant to extreme flood control and water resources management. However, traditional statistical models without multi-variable input may fail to capture runoff changes effectively due to the dual effect of climate change and human activities. Here, we used five multi-input machine learning (ML) models to predict monthly runoff, where multiple global circulation indexes and surface meteorological indexes were selected as explanatory variables by the stepwise regression or copula entropy methods. Moreover, four univariate models were adopted as benchmarks. The multi-input ML models were tested at two typical hydrological stations (i.e., Gaochang and Cuntan) in the Upper Yangtze River. The results indicate that the LSTM_Copula (long short-term memory model combined with copula entropy method) model outperformed other models in both hydrological stations, while the GRU_Step (gate recurrent unit model combined with stepwise regression method) model and the RF_Copula (random forest model combined with copula entropy method) model also showed satisfactory performances. In addition, the ML models with multi-variable input provided better predictability compared with four univariate statistical models, and the MAPE (mean absolute percentage error), RMSE (root mean square error), NSE (Nash–Sutcliffe efficiency coefficient), and R (Pearson’s correlation coefficient) values were improved by 5.10, 4.16, 5.34, and 0.43% for the Gaochang Station, and 10.84, 17.28, 13.68, and 3.55% for the Cuntan Station, suggesting the proposed ML approaches are practically applicable to monthly runoff forecasting in large rivers.
36
Shakirova, A. I., A. V. Kochergin, O. R. Sitnikov, and L. N. Gorina. "Forecast of the development of an emergency at hydraulic structures of the Republic of Tatarstan." IOP Conference Series: Earth and Environmental Science 937, no. 3 (December 1, 2021): 032020. http://dx.doi.org/10.1088/1755-1315/937/3/032020.
Повний текст джерелаАнотація:
Abstract At present, a large number of hydraulic structures have been erected on the territory of the Republic of Tatarstan, which are classified as hydrodynamic hazardous facilities. Accidents at these facilities are sources of man-made emergencies. A number of hydraulic structures on the territory have been in operation without reconstruction for more than 70 years. The problem of ensuring the safety of hydraulic structures remains not fully understood and relevant today. Basically all hydraulic structures are located within or above settlements and are objects of increased risk. The consequences of a catastrophic flood can be aggravated by accidents at potentially dangerous facilities falling into its zone. The damage caused by such floods can amount to tens of millions of rubles. Incomplete destruction of the dam, when the safe operation of the structure is no longer possible, can lead to serious economic losses as a result of the cessation of energy production, hydraulic regulation and water collection in the reservoir. Careful monitoring is required in order to identify any possible emergencies. One of the solutions in this situation is the use of various methods for predicting emergency situations at hydraulic structures. In this regard, in the work, the authors have adapted a mathematical model based on Markov chains, which is distinguished by the efficiency of calculations and a high degree of approximation to statistical data. This model makes it possible to predict the state of hydraulic structures when the data on the water level and the volume of infiltration in the hydraulic structure changes. Based on the adapted model, the results of forecasting the water level for real hydraulic structures were obtained.
37
Matte, Simon, Marie-Amélie Boucher, Vincent Boucher, and Thomas-Charles Fortier Filion. "Moving beyond the cost–loss ratio: economic assessment of streamflow forecasts for a risk-averse decision maker." Hydrology and Earth System Sciences 21, no. 6 (June 19, 2017): 2967–86. http://dx.doi.org/10.5194/hess-21-2967-2017.
Повний текст джерелаАнотація:
Abstract. A large effort has been made over the past 10 years to promote the operational use of probabilistic or ensemble streamflow forecasts. Numerous studies have shown that ensemble forecasts are of higher quality than deterministic ones. Many studies also conclude that decisions based on ensemble rather than deterministic forecasts lead to better decisions in the context of flood mitigation. Hence, it is believed that ensemble forecasts possess a greater economic and social value for both decision makers and the general population. However, the vast majority of, if not all, existing hydro-economic studies rely on a cost–loss ratio framework that assumes a risk-neutral decision maker. To overcome this important flaw, this study borrows from economics and evaluates the economic value of early warning flood systems using the well-known Constant Absolute Risk Aversion (CARA) utility function, which explicitly accounts for the level of risk aversion of the decision maker. This new framework allows for the full exploitation of the information related to a forecasts' uncertainty, making it especially suited for the economic assessment of ensemble or probabilistic forecasts. Rather than comparing deterministic and ensemble forecasts, this study focuses on comparing different types of ensemble forecasts. There are multiple ways of assessing and representing forecast uncertainty. Consequently, there exist many different means of building an ensemble forecasting system for future streamflow. One such possibility is to dress deterministic forecasts using the statistics of past error forecasts. Such dressing methods are popular among operational agencies because of their simplicity and intuitiveness. Another approach is the use of ensemble meteorological forecasts for precipitation and temperature, which are then provided as inputs to one or many hydrological model(s). In this study, three concurrent ensemble streamflow forecasting systems are compared: simple statistically dressed deterministic forecasts, forecasts based on meteorological ensembles, and a variant of the latter that also includes an estimation of state variable uncertainty. This comparison takes place for the Montmorency River, a small flood-prone watershed in southern central Quebec, Canada. The assessment of forecasts is performed for lead times of 1 to 5 days, both in terms of forecasts' quality (relative to the corresponding record of observations) and in terms of economic value, using the new proposed framework based on the CARA utility function. It is found that the economic value of a forecast for a risk-averse decision maker is closely linked to the forecast reliability in predicting the upper tail of the streamflow distribution. Hence, post-processing forecasts to avoid over-forecasting could help improve both the quality and the value of forecasts.
38
Wang, Shuyi, Mohammad Reza Najafi, Alex J. Cannon, and Amir Ali Khan. "Uncertainties in Riverine and Coastal Flood Impacts under Climate Change." Water 13, no. 13 (June 27, 2021): 1774. http://dx.doi.org/10.3390/w13131774.
Повний текст джерелаАнотація:
Climate change can affect different drivers of flooding in low-lying coastal areas of the world, challenging the design and planning of communities and infrastructure. The concurrent occurrence of multiple flood drivers such as high river flows and extreme sea levels can aggravate such impacts and result in catastrophic damages. In this study, the individual and compound effects of riverine and coastal flooding are investigated at Stephenville Crossing located in the coastal-estuarine region of Newfoundland and Labrador (NL), Canada. The impacts of climate change on flood extents and depths and the uncertainties associated with temporal patterns of storms, intensity–duration–frequency (IDF) projections, spatial resolution, and emission scenarios are assessed. A hydrologic model and a 2D hydraulic model are set up and calibrated to simulate the flood inundation for the historical (1976–2005) as well as the near future (2041–2070) and far future (2071–2100) periods under Representative Concentration Pathways (RCPs) 4.5 and 8.5. Future storm events are generated based on projected IDF curves from convection-permitting Weather Research and Forecasting (WRF) climate model simulations, using SCS, Huff, and alternating block design storm methods. The results are compared with simulations based on projected IDF curves derived from statistically downscaled Global Climate Models (GCMs). Both drivers of flooding are projected to intensify in the future, resulting in higher risks of flooding in the study area. Compound riverine and coastal flooding results in more severe inundation, affecting the communities on the coastline and the estuary area. Results show that the uncertainties associated with storm hyetographs are considerable, which indicate the importance of accurate representation of storm patterns. Further, simulations based on projected WRF-IDF curves show higher risks of flooding compared to the ones associated with GCM-IDFs.
39
Alperen, Cagri Inan, Guillaume Artigue, Bedri Kurtulus, Séverin Pistre, and Anne Johannet. "A Hydrological Digital Twin by Artificial Neural Networks for Flood Simulation in Gardon de Sainte-Croix Basin, France." IOP Conference Series: Earth and Environmental Science 906, no. 1 (November 1, 2021): 012112. http://dx.doi.org/10.1088/1755-1315/906/1/012112.
Повний текст джерелаАнотація:
Abstract Understanding, simulating and forecasting dynamic and nonlinear natural phenomena are necessary in a climate change context and increased sensitivity of societies to natural hazards. Nevertheless, even though powerful computing tools and algorithms have been widely used to understand and to predict natural disasters, these tasks are still challenging for scientists. Indeed, one of the most dangerous natural phenomena, flash floods keep being a challenge for modelers, despite (i) the existence of some effective hydrological simulating tools, and (ii) the increasing availability of descriptive data, especially rainfall and discharge. In particular, on one hand, environmental data contain an important amount of noise leading to additional uncertainties and on the other hand, physically based models strongly depend on assumptions about the behavior of the basin, that is often more variable in space and time than what is modelled. With the objective of applying data assimilation to improve forecasting properties of the physical model, it is necessary to dispose of a differentiable model. In order to mitigate this issue, a hybrid physical and statistical approach is proposed in this study. It was shown in previous works that deep neural networks are able to identify any differentiable function by using the universal approximation property. Deep neural networks are also good candidates to perform the digital twin of the physical model. Thus, three different neural networks models were designed in this study, and each one is implementing a different type of non-linear filter model, in order to achieve the dynamic character of the catchment area (recurrent, feedforward and static models). The study area is located in the Gardon de Sainte-Croix basin (France), which is known for its sudden and violent floods that caused casualties and a lot of damage. The chosen physical-based model is semi distributed conceptual hydrological SOCONT model, RS Minerve (https://www.crealp.ch/down/rsm/install2/archives.html). Neural networks design was done by using a rigorous complexity selection and regularization methods to promote a good generalization. The three models obtained were thus compared. The feed forward model gave the best results on tests events (Nash score=0.98−0.99), making full use of the inputs with previous observed discharges whereas the recurrent model gave interesting results representing satisfactorily the dynamics of the physical model (Nash score=0.8−0.97). The static model, whose inputs contain only rainfall, is less efficient, showing the importance of dynamics in that kind of system (Nash score=0.62−0.84). Beyond data assimilation, these results open paths of inquiry for building digital twins of physical model, allowing also a great reduction of computing time.
40
Mazzarella, Vincenzo, Ida Maiello, Vincenzo Capozzi, Giorgio Budillon, and Rossella Ferretti. "Comparison between 3D-Var and 4D-Var data assimilation methods for the simulation of a heavy rainfall case in central Italy." Advances in Science and Research 14 (August 11, 2017): 271–78. http://dx.doi.org/10.5194/asr-14-271-2017.
Повний текст джерелаАнотація:
Abstract. This work aims to provide a comparison between three dimensional and four dimensional variational data assimilation methods (3D-Var and 4D-Var) for a heavy rainfall case in central Italy. To evaluate the impact of the assimilation of reflectivity and radial velocity acquired from Monte Midia Doppler radar into the Weather Research Forecasting (WRF) model, the quantitative precipitation forecast (QPF) is used.The two methods are compared for a heavy rainfall event that occurred in central Italy on 14 September 2012 during the first Special Observation Period (SOP1) of the HyMeX (HYdrological cycle in Mediterranean EXperiment) campaign. This event, characterized by a deep low pressure system over the Tyrrhenian Sea, produced flash floods over the Marche and Abruzzo regions, where rainfall maxima reached more than 150 mm 24 h−1.To identify the best QPF, nine experiments are performed using 3D-Var and 4D-Var data assimilation techniques. All simulations are compared in terms of rainfall forecast and precipitation measured by the gauges through three statistical indicators: probability of detection (POD), critical success index (CSI) and false alarm ratio (FAR). The assimilation of conventional observations with 4D-Var method improves the QPF compared to 3D-Var. In addition, the use of radar measurements in 4D-Var simulations enhances the performances of statistical scores for higher rainfall thresholds.
41
Singh, Abhinav Kumar, Pankaj Kumar, Rawshan Ali, Nadhir Al-Ansari, Dinesh Kumar Vishwakarma, Kuldeep Singh Kushwaha, Kanhu Charan Panda, et al. "An Integrated Statistical-Machine Learning Approach for Runoff Prediction." Sustainability 14, no. 13 (July 5, 2022): 8209. http://dx.doi.org/10.3390/su14138209.
Повний текст джерелаАнотація:
Nowadays, great attention has been attributed to the study of runoff and its fluctuation over space and time. There is a crucial need for a good soil and water management system to overcome the challenges of water scarcity and other natural adverse events like floods and landslides, among others. Rainfall–runoff (R-R) modeling is an appropriate approach for runoff prediction, making it possible to take preventive measures to avoid damage caused by natural hazards such as floods. In the present study, several data-driven models, namely, multiple linear regression (MLR), multiple adaptive regression splines (MARS), support vector machine (SVM), and random forest (RF), were used for rainfall–runoff prediction of the Gola watershed, located in the south-eastern part of the Uttarakhand. The rainfall–runoff model analysis was conducted using daily rainfall and runoff data for 12 years (2009 to 2020) of the Gola watershed. The first 80% of the complete data was used to train the model, and the remaining 20% was used for the testing period. The performance of the models was evaluated based on the coefficient of determination (R2), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), and percent bias (PBAIS) indices. In addition to the numerical comparison, the models were evaluated. Their performances were evaluated based on graphical plotting, i.e., time-series line diagram, scatter plot, violin plot, relative error plot, and Taylor diagram (TD). The comparison results revealed that the four heuristic methods gave higher accuracy than the MLR model. Among the machine learning models, the RF (RMSE (m3/s), R2, NSE, and PBIAS (%) = 6.31, 0.96, 0.94, and −0.20 during the training period, respectively, and 5.53, 0.95, 0.92, and −0.20 during the testing period, respectively) surpassed the MARS, SVM, and the MLR models in forecasting daily runoff for all cases studied. The RF model outperformed in all four models’ training and testing periods. It can be summarized that the RF model is best-in-class and delivers a strong potential for the runoff prediction of the Gola watershed.
42
King, Fraser, Andre R. Erler, Steven K. Frey, and Christopher G. Fletcher. "Application of machine learning techniques for regional bias correction of snow water equivalent estimates in Ontario, Canada." Hydrology and Earth System Sciences 24, no. 10 (October 14, 2020): 4887–902. http://dx.doi.org/10.5194/hess-24-4887-2020.
Повний текст джерелаАнотація:
Abstract. Snow is a critical contributor to Ontario's water-energy budget, with impacts on water resource management and flood forecasting. Snow water equivalent (SWE) describes the amount of water stored in a snowpack and is important in deriving estimates of snowmelt. However, only a limited number of sparsely distributed snow survey sites (n=383) exist throughout Ontario. The SNOw Data Assimilation System (SNODAS) is a daily, 1 km gridded SWE product that provides uniform spatial coverage across this region; however, we show here that SWE estimates from SNODAS display a strong positive mean bias of 50 % (16 mm SWE) when compared to in situ observations from 2011 to 2018. This study evaluates multiple statistical techniques of varying complexity, including simple subtraction, linear regression and machine learning methods to bias-correct SNODAS SWE estimates using absolute mean bias and RMSE as evaluation criteria. Results show that the random forest (RF) algorithm is most effective at reducing bias in SNODAS SWE, with an absolute mean bias of 0.2 mm and RMSE of 3.64 mm when compared with in situ observations. Other methods, such as mean bias subtraction and linear regression, are somewhat effective at bias reduction; however, only the RF method captures the nonlinearity in the bias and its interannual variability. Applying the RF model to the full spatio-temporal domain shows that the SWE bias is largest before 2015, during the spring melt period, north of 44.5∘ N and east (downwind) of the Great Lakes. As an independent validation, we also compare estimated snowmelt volumes with observed hydrographs and demonstrate that uncorrected SNODAS SWE is associated with unrealistically large volumes at the time of the spring freshet, while bias-corrected SWE values are highly consistent with observed discharge volumes.
43
Zhao, J. H., Z. Y. Dong, and M. L. Zhao. "A statistical model for flood forecasting." Australasian Journal of Water Resources 13, no. 1 (January 2009): 43–52. http://dx.doi.org/10.1080/13241583.2009.11465359.
Повний текст джерела
44
Sviyazov, Evgeniy M., and Andrey L. Vetrov. "NUMERICAL MODELING OF HEAVY SUMMER RAINFALLS WITH DIFFERENT GRID SPACING OF THE REGULAR GRID STEP." Географический вестник = Geographical bulletin, no. 4(59) (2021): 73–83. http://dx.doi.org/10.17072/2079-7877-2021-4-73-83.
Повний текст джерелаАнотація:
Climate warming is causing an increase in the total moisture content on the planet and in the number of heavy rainfall cases. Many of these result in severe flooding, victims, and destruction of infrastructure. The aim of the study is to establish the possibility of improving the quality of heavy precipitation forecasting by reducing the step of the computational grid in the mathematical model of the atmosphere. The article presents the results of a study of extreme summer precipitation in the Ural Kama region for the period from 1979 to 2015. The statistical characteristics of 37 precipitation cases with an intensity of more than 50 mm in 12 hours were analyzed. Computational experiments were performed on the WRF-ARW regional atmospheric model. The meteorological conditions for the occurrence of heavy rain in town of Gubakha with an extreme intensity of 114,5 mm in 12 hours were taken as a special case for the study. A qualitative assessment of the simulation results showed that for the selected case, the model correctly reproduced the general structure of heavy rains, but significantly shifted it eastward. A quantitative assessment of the forecast quality was conducted for numerical forecast of heavy precipitation based on the WRF-ARW model at a grid step of 3 km and 7,2 km. The quality of the model was evaluated based on the forecast accuracy not only at the measurement point but also in the vicinity within a radius of 50 km. It was found that there was no significant improvement in the quality of the forecast of high-intensity precipitation when switching to a smaller grid step according to both the first and second assessment methods. The results obtained can be taken into account when preparing forecasts of heavy rains occurrence and when developing flood forecast techniques.
45
Malinin, V. N., S. M. Gordeeva, Yu V. Mitina, and O. I. Shevchuk. "Results of sea level studies at RSHU." HYDROMETEOROLOGY AND ECOLOGY. PROCEEDINGS OF THE RUSSIAN STATE HYDROMETEOROLOGICAL UNIVERSITY, no. 60 (2020): 269–305. http://dx.doi.org/10.33933/2074-2762-2020-60-269-305.
Повний текст джерелаАнотація:
Study of sea level is being developed at RSHU in several directions: global, regional and local. The global one includes the study of the patterns of interannual fluctuations of the global sea level (GLS), identification of their genesis and development of a set of methods for its long-term forecast. Two approaches to the genesis of GLS are considered. In foreign studies, changes in GLS are determined by changes in the water mass of various cryosphere components, land water reserves and steric level fluctuations. Another approach, implemented at RSHU, is to assess contributions of various factors using the equation of the freshwater balance of the World Ocean as the sum of eustatic and steric factors. A physical-statistical method for two-decade GLS forecasting, based on delay in the GLS response to air temperature over the ocean, has been developed, as well as the GLS projections at the end of the century for climatic scenarios according to the CMIP5 project have been provided. In the regional context, the main attention is paid to identifying the genesis of the interannual variability of the Caspian Sea level with the aim of its long-term forecasting. The entire chain of cause-and-effect relationships in the North Atlantic-atmosphere-Volga basin-Caspian level system is discussed. It has been established that, as a result of the intensification of cyclonic activity in the North Atlantic, especially in the Norwegian Sea, caused by the processes of large-scale interaction between the ocean and the atmosphere, there is an increase in evaporation and in the zonal transfer of water vapour to Europe and then to the Volga basin. Therefore, more precipitation falls in the runoff-forming zone of the basin, the annual runoff of the Volga and the level of the Caspian Sea increasing. The reverse is observed with weakening of cyclonic activity in the North Atlantic. In view of this, the level of the Caspian Sea is an integral indicator of largescale moisture exchange in the ocean-atmosphere-land system. The article discusses the features of interannual sea level fluctuations in Kronstadt since 1836. A simple two-parameter model for forecasting sea level by the end of the 21st century is proposed for major climate scenarios, the predictors being the GSL and the North Atlantic Oscillation. According to the most realistic forecast, the level in Kronstadt may rise to 34-59 cm (Baltic system) by the end of the century, while according to the “pessimistic” one — to 80-90 cm (Baltic system). The estimates of the extreme storm surge at which the level rise north of the Gorskaya can reach 600 cm (Baltic system) are given. The effect of flooding from storm surges is especially strong near Sestroretsk. The total area of possible flooding of the Kurortny district at a 4-m high surge wave exceeds 1260 hectares, all the beaches being completely lost. The trajectories of flood cyclones and their role for periods of climate warming and cooling are considered
46
Han, Shasha, and Paulin Coulibaly. "Bayesian flood forecasting methods: A review." Journal of Hydrology 551 (August 2017): 340–51. http://dx.doi.org/10.1016/j.jhydrol.2017.06.004.
Повний текст джерела
47
Lee, Byong-Ju, and Sangil Kim. "Gridded Flash Flood Risk Index Coupling Statistical Approaches and TOPLATS Land Surface Model for Mountainous Areas." Water 11, no. 3 (March 11, 2019): 504. http://dx.doi.org/10.3390/w11030504.
Повний текст джерелаАнотація:
This study presents the development of a statistical flash flood risk index model, which is currently operating in research mode for flash flood risk forecasting in ungauged mountainous areas. The grid-based statistical flash flood risk index, with temporal and spatial resolutions of 1 h and 1 km, respectively, has been developed to simulate the flash flood risk index leading to flash flood casualties using hourly rainfall, surface flow, and soil water content in the previous 6 h. The statistical index model employs factor analysis and multi-linear regression to analyze its gridded hydrological components that are obtained from the TOPMODEL-based Land Atmosphere Transfer Scheme (TOPLATS). The performance of the developed index model has been evaluated in estimating flash flooding in ungauged mountain valleys and small streams. Numerical results show that the approach simulated 38 flash flood catastrophes in the Seoul Capital Region with 71% accuracy; therefore, this approach is potentially adequate for flash flood risk forecasting.
48
Hao, Qun, Ying Na Sun, and Ning Jiang. "Uncertainty Analysis of Flood Forecasting in River Channel." Advanced Materials Research 550-553 (July 2012): 2489–92. http://dx.doi.org/10.4028/www.scientific.net/amr.550-553.2489.
Повний текст джерелаАнотація:
In this paper, the stochastic differential equations theory was used to analyze the uncertainty of flood forecasting in river channel based on the forward algorithm of linear characteristic. And then a river channel flood forecasting model, in which the coefficient of storage and discharge was regarded as a random variable, was built. The statistical characteristics of outflow process could be taken part in theory by the built river channel flood forecasting model when the coefficient of storage obeyed a kind of normal distribution. Storage coefficient is random variable in the model. The results showed that the uncertainty degree of outflow process could be made through considering the uncertainty of river channel flood forecasting, which would provide some references for making decision in flood control.
49
Mistry, Shivangi, and Falguni Parekh. "Flood Forecasting Using Artificial Neural Network." IOP Conference Series: Earth and Environmental Science 1086, no. 1 (September 1, 2022): 012036. http://dx.doi.org/10.1088/1755-1315/1086/1/012036.
Повний текст джерелаАнотація:
Abstract The process of assessing the timing, amount, and period of flood events based on observed features of a river basin is known as flood forecasting. Floods cause lots of damage to properties and create a risk to human life. Flood forecasting is critical for developing appropriate flood risk management strategies, reducing flood hazards, evacuating people from flood-prone areas. The main objective of this study is to apply artificial neural networks for forecasting of river flow in the Deo River, located in Gujarat. Rainfall and discharge are the parameters considered for model development. The developed model is validated to test the accuracy of the model. Trained and validated models are evaluated using performance indices. Six alternative flood prediction models have been developed using ANN. These models are developed based on various training algorithms. A single layer feed forward back-propagation neural network with six different training algorithms (Scaled conjugate gradient, Levenberg Marquardt, Resilient back-propagation, Conjugate gradient, and Cascade forward back propagation, Bayesian regularization) was developed, with 70% of the data used for training and 30% for validation. The created models’ performance is assessed using statistical performance parameters. The best performance was obtained with an ANN model developed using the Cascade forward back-propagation training algorithm, which had a coefficient of correlation (r) of 0.83, a coefficient of determination (R2) of 0.70, and a root mean squared error (RMSE) of 5.58 for training and a coefficient of correlation (r) of 0.89, a coefficient of determination (R2) of 0.70, and a root mean squared error (RMSE) of 7.27 for validation. The forecast inflow is very close to the observed values. This study shows that ANN can be used to successfully predict floods, and the model developed can be used by flood control departments across the country for flood forecasting.
50
Nguyen, Dinh Ty, and Shien-Tsung Chen. "Real-Time Probabilistic Flood Forecasting Using Multiple Machine Learning Methods." Water 12, no. 3 (March 12, 2020): 787. http://dx.doi.org/10.3390/w12030787.
Повний текст джерелаАнотація:
Probabilistic flood forecasting, which provides uncertain information in the forecasting of floods, is practical and informative for implementing flood-mitigation countermeasures. This study adopted various machine learning methods, including support vector regression (SVR), a fuzzy inference model (FIM), and the k-nearest neighbors (k-NN) method, to establish a probabilistic forecasting model. The probabilistic forecasting method is a combination of a deterministic forecast produced using SVR and a probability distribution of forecast errors determined by the FIM and k-NN method. This study proposed an FIM with a modified defuzzification scheme to transform the FIM’s output into a probability distribution, and k-NN was employed to refine the probability distribution. The probabilistic forecasting model was applied to forecast flash floods with lead times of 1–3 hours in Yilan River, Taiwan. Validation results revealed the deterministic forecasting to be accurate, and the probabilistic forecasting was promising in view of a forecasted hydrograph and quantitative assessment concerning the confidence level.