Gotowa bibliografia na temat „Chlorophyll Content Prediction”

This study focused on estimating chlorophyll concentration of rice using PROSPECT and support vector machine. The study site is located in West Lake sewage irrigation area of Changchun, Jiliin Province. Reflectance spectrual of rice were measured by ASD3 spectrometer, chlorophyll contents of rice were recorded with a portable chlorophyll meter SPAD-502. Support vector machines and PROSPECT model were adopted to construct hyperspectral models for predicting chlorophyll content. The results indicate that: the hyperspectral prediction model of rice chlorophyll content yields a maximum correlation coefficient of 0.8563, and achieves a smallest RMSE of 9.5106; and the prediction accuracy based on the first derivative spectrum is higher than on the original spectrum. Research of this paper provides a theoretical basis for large scale dynamic prediction of rice chlorophyll content in sewage irrigated area.

A chlorophyll content prediction model for predicting chlorophyll content in the pericarp of Korla fragrant pears was constructed based on harvest maturity and storage time. This model predicts chlorophyll content in the pericarp of fragrant pears after storage by using the error backpropagation neural network (BPNN), generalized regression neural network (GRNN) and adaptive neural fuzzy inference system (ANFIS). The results demonstrate that chlorophyll content in the pericarp of fragrant pears decreased gradually as the harvest time lengthened. The chlorophyll content in the pericarp of fragrant pears with different maturity levels at harvest decreased continuously with the increase in storage time. According to a comparison of the prediction performances of the BPNN and ANFIS models, it was discovered that the trained GRNN and ANFIS models could predict chlorophyll content in the pericarp of fragrant pears. The ANFIS model showed the best prediction performances when the input membership functions were gasuss2mf (RMSE = 0.006; R2 = 0.993), dsigmf (RMSE = 0.007; R2 = 0.992) and psigmf (RMSE = 0.007; R2 = 0.992). The findings of this study can serve as references for determining the delivery quality and timing of Korla fragrant pears.

Chlorophyll fluorescence (CF) has been applied to measure the chlorophyll content of seeds, in order to determine seed maturity, but the high price of equipment limits its wider application. Astragalus seeds were used to explore the applicability of digital image analysis technology to the prediction of seed chlorophyll content and to supply a low cost and alternative method. Our research comprised scanning and extracting the characteristic features of Astragalus seeds, determining the chlorophyll content, and establishing a predictive model of chlorophyll content in Astragalus seeds based on characteristic features. The results showed that the R2 of the MLR prediction model established with multiple features was ≥0.947, and the R2 of the MLP model was ≥0.943. By sorting of two single features, the R and G values, the R2 reached 0.969 and 0.965, respectively. A germination result showed that the lower the chlorophyll content, the higher the quality of the seeds. Therefore, we draw a conclusion that digital image analysis technology can be used to predict effectively the chlorophyll content of Astragalus seeds, and provide a reference for the selection of mature and viable Astragalus seeds.

Light is one of the most important factor in the growth of plants, with the advent and application of biological materials such as different artificial LED source, the new agricultural technology has been rapid development. In this study, first established the gray GM (1,1) prediction model of the pepper seedlings chlorophyll changes under the different light and then compared of the chlorophyll models under the different light. Last the study found that different artificial LED have the different effect and the forecasting curve and prediction model under the blue is optimal for pepper seedling by comparing the chlorophyll curves and predictive models of pepper seedlings under different light, so blue light is the most suitable for the growth of pepper seedlings. The results turned out that accuracy test of the three gray prediction models can achieve the best grade, and the three gray prediction models have the good practical value. Grey prediction theory can be better applied to the study of the plants.

Chlorophyll content is an important indicator for assessing crop health and predicting crop yield. It is possible that chlorophyll content (CC) was quickly and non-destructively estimated by remote sensing. The objective of the experiment was to develop precision agricultural practices for predicting CC of wheat. In this study, we compared some spectral parameters (SPs) and CC with the determination coefficient (R2), and combined these SPs by stepwise regression methods. The results indicated that the 1.45SIPI-1.05PSRI, the R2 value was 0.6589 and corresponding the root mean square error (RMSE) was 1.463, and it can be used to improve the prediction accuracy of CC.

Accurate measurement of canopy chlorophyll content (CCC) is essential for the understanding of terrestrial ecosystem dynamics through monitoring and evaluating properties such as carbon and water flux, productivity, light use efficiency as well as nutritional and environmental stresses. Information on the amount and distribution of CCC helps to assess and report biodiversity indicators related to ecosystem processes and functional aspects. Therefore, measuring CCC continuously and globally from earth observation data is critical to monitor the status of the biosphere. However, generic and robust methods for regional and global mapping of CCC are not well defined. This study aimed at examining the spatiotemporal consistency and scalability of selected methods for CCC mapping across biomes. Four methods (i.e., radiative transfer models (RTMs) inversion using a look-up table (LUT), the biophysical processor approach integrated into the Sentinel application platform (SNAP toolbox), simple ratio vegetation index (SRVI), and partial least square regression (PLSR)) were evaluated. Similarities and differences among CCC products generated by applying the four methods on actual Sentinel-2 data in four biomes (temperate forest, tropical forest, wetland, and Arctic tundra) were examined by computing statistical measures and spatiotemporal consistency pairwise comparisons. Pairwise comparison of CCC predictions by the selected methods demonstrated strong agreement. The highest correlation (R2 = 0.93, RMSE = 0.4371 g/m2) was obtained between CCC predictions of PROSAIL inversion by LUT and SNAP toolbox approach in a wetland when a single Sentinel-2 image was used. However, when time-series data were used, it was PROSAIL inversion against SRVI (R2 = 0.88, RMSE = 0.19) that showed greatest similarity to the single date predictions (R2 = 0.83, RMSE = 0.17 g/m2) in this biome. Generally, the CCC products obtained using the SNAP toolbox approach resulted in a systematic over/under-estimation of CCC. RTMs inversion by LUT (INFORM and PROSAIL) resulted in a non-biased, spatiotemporally consistent prediction of CCC with a range closer to expectations. Therefore, the RTM inversion using LUT approaches particularly, INFORM for ‘forest’ and PROSAIL for ‘short vegetation’ ecosystems, are recommended for CCC mapping from Sentinel-2 data for worldwide mapping of CCC. Additional validation of the two RTMs with field data of CCC across biomes is required in the future.

The unmanned aerial vehicles (UAV) have become a better solution for agricultural growers due to advanced features such as minimal maintenance costs, quick set-up time, low acquisition costs, and live data capturing. Near-ground remote sensing (drone) has opened up new agronomic opportunities for better crop management. This study predicted the seed cotton yield for a cotton field area located at Tamil Nadu Agricultural University, Coimbatore. Pearson correlation analysis and regression analysis were done for ground truth data and vegetation indices for validation and accuracy and also to find the best-performing indices. It was concluded that the Wide Dynamic Range Vegetation Index (WDRVI) showed a better correlation coefficient (R=0.959) with LAI ground truth data (R2=0.919). In contrast, the Modified Chlorophyll Absorption Ratio Index (MCARI) showed a better correlation coefficient (R=0.919) with SPAD chlorophyll ground truth data (R2=0.845). Then the best performing indices WDRVI and MCARI were further used for generating the yield model. High spatial resolution drone imageries for determining LAI and chlorophyll are reliable and rapid, as per the study. It helps to determine the LAI and chlorophyll at a spatial scale and their influence on yield production. This yield prediction was technical support for the widespread adoption and application of unmanned aerial vehicle (UAV) remote sensing in large-scale precision agriculture.

Oil palm nutrient content is investigated with using chlorophyll as a representative factor correlated with NIR spectroscopy spectral absorbance. NIR spectroscopy method of sampling have been tested to overcome time consuming, complex chemical analysis procedure and invasive sampling method in order to identify chlorophyll content in an oil palm tree. Spectral absorbance data from range 900 nm to 1700 nm and chlorophyll data, then tested through five pre-processing methods which is Savitzky-Golay Smoothing (SGS), Multiplicative Scatter Correction (MSC), Single Normal Variation (SNV), First Derivative (1D) and also Second Derivative (2D) using Partial Least Square (PLS) regression prediction model to evaluate the correlation between both data. The overall results show, SGS has the best performance for preprocessing method with the results, the coefficient of determination (R2) values of 0.9998 and root mean square error (RMSE) values of 0.0639. In summary, correlation of NIR spectral absorbance data and chlorophyll can be achieved using a PLS regression model with SGS pre-processing technique. Thus, we can conclude that NIR spectroscopy method can be used to identify chlorophyll content in oil palm with using time saving, simple sampling and non-invasive method.

Apple (Malus ×domestica L. Borkh.) growers need tools to predict the efficacy of chemical thinners that are applied to induce fruitlet abscission to aid in crop load management decisions. Recently, reflectance spectroscopy-based models to predict fruitlet abscission rates were developed. Using spectroscopy, persisting fruitlets had lower reflectance in the red-light (∼600 nm) and near infrared (∼950 nm) regions than abscising fruitlets. The goal of this study was to better understand how reflectance models distinguished between fruitlets that ultimately persisted or abscised. Individual models for the difference and ratio of each combination of wavelengths were developed to identify key wavelengths for abscission prediction from reflectance models. Accuracy for wavelength difference and ratio models was improved for all model prediction dates when reflectance (R) from R640–675 was subtracted from or divided by R675–696. This spectra region indicates differences in chlorophyll content between persisting and abscising fruitlets. Calculation of the chlorophyll concentration index (R522–579:R640–700) from nondestructively measured spectra supported this result. Chlorophyll concentration index was higher for fruitlets that ultimately persisted than abscised fruitlets (P < 0.01) for all measurement dates –1 to 9 days after thinner (DAT) in both years, except –1 DAT in 2021 (P = 0.468). Plant water index (R950–970:R890–900) was lower for persisting than abscising fruitlets for 3 to 9 DAT in 2021 (P < 0.001) and on –1 (P < 0.01) and 9 DAT (P < 0.001) in 2022. The relationship of fruit size and plant pigment (anthocyanins or chlorophyll) content in fruitlets to reflectance spectra between persisting and abscising fruitlets was also followed. Fruitlet persistence or abscission was predicted from developed models for destructively sampled fruitlets using measured reflectance spectra. Whole-fruit chlorophyll content was numerically higher in fruitlets predicted to persist than abscise for all collection dates. Higher total chlorophyll was correlated to a larger fruit size in persisting than abscising fruitlets. This higher chlorophyll content led to a lower reflectance of red light and was a key factor in model development. These results indicate that chlorophyll and water content can distinguish physiological parameters between persisting and abscising fruitlets.

In the recent years, remote sensing data or images have great potential for continuous spatial and temporal monitoring of Earth surface features. In case of optical remote sensing, hyperspectral (HS) data contains abundant spectral information and these information are advantageous for various applications. However, high-dimensional HS data handling is a very challenging task. Different techniques are proposed as a part of this thesis to handle the HS data in a computationally efficient manner and to achieve better performance for land cover classification and chlorophyll content prediction. Prior to start the HS data application, multispectral (MS) data are also analyzed in this thesis for crop classification. Multi-temporal MS data is used for crop classification. Landsat-8 operational land imager (OLI) sensor data are considered as MS data in this work. Surface reflectances and derived normalized difference indices (NDIs) of multi-temporal MS bands are combinedly used for the crop classification. Different dimensionality reduction techniques, viz. feature selection (FS) (e.g. random forest (RF) and partial informational correlation (PIC) measure-based), linear (e.g. principal component analysis (PCA) and independent component analysis) and nonlinear feature extraction (FE) (e.g. kernel PCA and Autoencoder), to be employed on the multi-temporal surface reflectances and NDIs datasets, are evaluated to detect the most favorable features. Subsequently, the detected features are used in a promising nonparametric classifier, support vector machine (SVM), for crop classification. It is found that all the evaluated FE techniques, employed on the multi-temporal datasets, resulted in better performance compared to FS-based approaches. PCA, being a simple and efficient FE algorithm, is well-suited in crop classification in terms of computational complexity and classification performances. Multi-temporal images are proved to be more advantageous compared to the single-date imagery for crop identification. HS data comprises of continuous spectral responses of hundreds of narrow spectral bands with very fine spectral resolution or bandwidth, which offer feature identification and classification with high accuracy. HS data are enriched with highly resourceful abundant spectral bands compared to only 5-10 spectral bands of MS data. However, analyzing and interpreting these ample amounts of data is a challenging task. Optimal spectral bands or features should be chosen or extracted to address the issue of redundancy and to capitalize on the absolute advantages of HS data. FS and FE are two broad categories of dimensionality reduction techniques. In this thesis, a FS and a FE-based computationally efficient dimensionality reduction technique is proposed for land cover classification. PIC-based HS band selection approach is proposed as a FS-based dimensionality reduction technique for classification of land cover types. PIC measure is more skillful compared to mutual information for estimation of non-parametric conditional dependency. In this proposed approach, HS narrow-bands are selected in an innovative way utilizing the PIC. Firstly, HS bands are divided into different spectral groups or segments using normalized mutual information (NMI) and then PIC is employed to each spectral group for optimal band selection. This approach is more efficient in terms of computational time and in generalizing the applicability of selected spectral bands. Further, these optimal spectral bands are used in the SVM and RF classifier for classification of land cover types and performance evaluation. The proposed FS-based dimensionality reduction approach is compared with different state-of-the-art techniques for land cover classification. The proposed methodology improved the classification performances compared to the existing techniques and the advancement in performances are proven to be statistically significant. In the recent years, deep learning-based FE techniques are very popular and also proven to be effective in extraction of apt features from the high-dimensional data. However, these techniques are computationally expensive. A computationally efficient FE-based dimensionality reduction approach, NMI-based segmented stacked auto-encoder (S-SAE), is proposed for extraction of spectral features from the HS data. These spectral features are consecutively utilized for creation of spatial features and later both spectral and spatial features are used in the classifier models (i.e. SVM and RF) for land cover classification. The proposed HS image classification approach reduces the complexity and computational time compared to the available techniques. A non-parametric dependency measure (i.e. NMI) based spectral segmentation is proposed instead of linear and parametric dependency measure to take care of the both linear and nonlinear inter-band dependencies for spectral segmentation of the HS bands. Then extended morphological profiles (EMPs) are created corresponding to segmented spectral features to assimilate the spatial information in the spectral-spatial classification approach. Two non-parametric classifiers, SVM with Gaussian kernel and RF are used for classification of the three most popularly used HS datasets. The experiments performed with the proposed methodology provide encouraging results compared to numerous existing approaches. HS data are proven to be more resourceful compared to MS data for object detection, classification and several other applications. However, absence of any space-borne HS sensor and high cost and limited obtainability of airborne sensors-based images limit the use of HS data. Transformation of readily available MS data into quasi-HS data can be a feasible solution for this issue. A deep learning-based regression algorithm, convolutional neural network regression (CNNR), is proposed as part of this thesis for MS (i.e. Landsat-7/8) to quasi-HS (i.e. quasi-Hyperion) data transformation. CNNR model introduces the advantages of nonlinear modelling and assimilation of spatial information in the regression-based modelling. The proposed CNNR model is compared with the pseudo-HS image transformation algorithm (PHITA), stepwise linear regression (SLR), and support vector regression (SVR) models by evaluating the quality of the quasi-Hyperion data. Several statistical metrics are calculated to compare each band’s reflectance values as well as spectral reflectance curve of each pixel of the quasi-Hyperion data with that of the original Hyperion data. The developed models and generated quasi-Hyperion data are also evaluated with application to crop classification. Analyzing the results of all the experiments, it is evident that CNNR model is more efficient compared to PHITA, SLR, and SVR in creating the quasi-Hyperion data and this transformed data are proven to be resourceful for crop classification application. The proposed CNNR model-based MS to quasi-HS data transformation approach can be used as a viable alternative for different applications in the absence of original HS images. HS data are investigated for estimation of chlorophyll content, which is one of the essential biochemical parameters to assess the growth process of the fruit trees. This study developed a model for estimation of canopy averaged chlorophyll content (CACC) of pear trees using the convolutional auto-encoder (CAE) features of HS data. This study also demonstrated the inspection of anomaly among the trees by employing multi-dimensional scaling (MDS) on the CAE features and detected the outlier trees, prior to fit nonlinear regression models. These outlier trees are excluded from further experiments which helped in improving the prediction performance of CACC. Gaussian process regression (GPR) and support vector regression (SVR) techniques are investigated as nonlinear regression models and used for prediction of CACC. The CAE features are proven to be providing better prediction of CACC, compared to the direct use of HS bands or vegetation indices as predictors. Training of the regression models, excluding the outlier trees, improved the CACC prediction performance. It is evident from the experiments that GPR can predict the CACC with better accuracy compared to SVR. In addition, the reliability of the tree canopy masks, which are utilized for averaging the features’ values for a particular tree, is also evaluated.

Operational polar-orbiting environmental satellites launched in the early 1960s were designed for daily weather monitoring around the world. In the early years, they were mostly applied for cloud monitoring and for advancing skills in satellite data applications. The new era was opened with the series of TIROS-N launched in 1978, which has continued until present. These satellites have such instruments as the advanced very high resolution radiometer (AVHRR) and the TIROS operational vertical sounder (TOVS), which included a microwave sounding unit (MSU), a stratospheric sounding unit (SSU), and high-resolution infrared radiation sounder/2 (HIRS/2). These instruments helped weather forecasters improve their skills. AVHRR instruments were also useful for observing and monitoring earth surface. Specific advances were achieved in understanding vegetation distribution. Since the late 1980s, experience gained in interpreting vegetation conditions from satellite images has helped develop new applications for detecting phenomenon such as drought and its impacts on agriculture. The objective of this chapter is to introduce AVHRR indices that have been useful for detecting most unusual droughts in the world during 1990–2000, a decade identified by the United Nations as the International Decade for Natural Disasters Reduction. Radiances measured by the AVHRR instrument onboard National Oceanic Atmospheric Administration (NOAA) polar-orbiting satellites can be used to monitor drought conditions because of their sensitivity to changes in leaf chlorophyll, moisture content, and thermal conditions (Gates, 1970; Myers, 1970). Over the last 20 years, these radiances were converted into indices that were used as proxies for estimating various vegetation conditions (Kogan, 1997, 2001, 2002). The indices became indispensable sources of information in the absence of in situ data, whose measurements and delivery are affected by telecommunication problems, difficult access to environmentally marginal areas, economic disturbances, and political or military conflicts. In addition, indices have advantage over in situ data in terms of better spatial and temporal coverage and faster data availability. The AVHRR-based indices used for monitoring vegetation can be divided into two groups: two-channel indices, and three-channel indices.

Commercial agriculture has come under increasing pressure to reduce nitrogen fertilizer inputs in order to minimize potential nonpoint source pollution of ground and surface waters. This has resulted in increased interest in site specific fertilizer management. One way to solve pollution problems would be to determine crop nutrient needs in real time, using remote detection, and regulating fertilizer dispensed by an applicator. By detecting actual plant needs, only the additional nitrogen necessary to optimize production would be supplied. This research aimed to develop techniques for real time assessment of nitrogen status of corn using a mobile sensor with the potential to regulate nitrogen application based on data from that sensor. Specifically, the research first attempted to determine the system parameters necessary to optimize reflectance spectra of corn plants as a function of growth stage, chlorophyll and nitrogen status. In addition to that, an adaptable, multispectral sensor and the signal processing algorithm to provide real time, in-field assessment of corn nitrogen status was developed. Spectral characteristics of corn leaves reflectance were investigated in order to estimate the nitrogen status of the plants, using a commercial laboratory spectrometer. Statistical models relating leaf N and reflectance spectra were developed for both greenhouse and field plots. A basis was established for assessing nitrogen status using spectral reflectance from plant canopies. The combined effect of variety and N treatment was studied by measuring the reflectance of three varieties of different leaf characteristic color and five different N treatments. The variety effect on the reflectance at 552 nm was not significant (a = 0.01), while canonical discriminant analysis showed promising results for distinguishing different variety and N treatment, using spectral reflectance. Ambient illumination was found inappropriate for reliable, one-beam spectral reflectance measurement of the plants canopy due to the strong spectral lines of sunlight. Therefore, artificial light was consequently used. For in-field N status measurement, a dark chamber was constructed, to include the sensor, along with artificial illumination. Two different approaches were tested (i) use of spatially scattered artificial light, and (ii) use of collimated artificial light beam. It was found that the collimated beam along with a proper design of the sensor-beam geometry yielded the best results in terms of reducing the noise due to variable background, and maintaining the same distance from the sensor to the sample point of the canopy. A multispectral sensor assembly, based on a linear variable filter was designed, constructed and tested. The sensor assembly combined two sensors to cover the range of 400 to 1100 nm, a mounting frame, and a field data acquisition system. Using the mobile dark chamber and the developed sensor, as well as an off-the-shelf sensor, in- field nitrogen status of the plants canopy was measured. Statistical analysis of the acquired in-field data showed that the nitrogen status of the com leaves can be predicted with a SEP (Standard Error of Prediction) of 0.27%. The stage of maturity of the crop affected the relationship between the reflectance spectrum and the nitrogen status of the leaves. Specifically, the best prediction results were obtained when a separate model was used for each maturity stage. In-field assessment of the nitrogen status of corn leaves was successfully carried out by non contact measurement of the reflectance spectrum. This technology is now mature to be incorporated in field implements for on-line control of fertilizer application.

Background Transplanting vegetable seedlings to final spacing in the greenhouse is common practice. At the time of transplanting, the transpiring leaf area is a small fraction of the ground area and its cooling effect is rather limited. A preliminary modeling study suggested that if water supply from root to canopy is not limiting, a sparse crop could maintain about the same canopy temperature as a mature crop, at the expense of a considerably higher transpiration flux per leaf (and root) area. The objectives of this project were (1) to test the predictions of the model, (2) to select suitable cooling methods, and (3) to compare the drought resistance of differently prepared seedlings. Procedure Plants were grown in several configurations in high heat load environments, which were moderated by various environmental control methods. The difference between the three experimental locations was mainly in terms of scale, age of plants, and environmental control. Young potted plants were tested for a few days in small growth chambers at Technion and Newe Ya'ar. At NCSU, tomato plants of different ages and planting densities were compared over a whole growing season under conditions similar to commercial greenhouses. Results Effect of spacing: Densely spaced plants transpired less per plant and more per unit ground area than sparsely spaced plants. The canopy temperature of the densely spaced plants was lower. Air temperature was lower and humidity higher in the compartments with the densely spaced plants. The difference between species is mainly in the canopy-to-air Bowen ratio, which is positive for pepper and negative for tomato. Effect of cooling methods: Ventilation and evaporative pad cooling were found to be effective and synergitic. Air mixing turned out to be very ineffective, indicating that the canopy-to-air transfer coefficient is not the limiting factor in the ventilation process. Shading and misting, both affecting the leaf temperature directly, proved to be very effective canopy cooling methods. However, in view of their side effects, they should only be considered as emergency measures. On-line measures of stress: Chlorophyll fluorescence was shown to accurately predict photosynthesis. This is potentially useful as a rapid, non-contact way of assessing canopy heat stress. Normalized canopy temperature and transpiration rate were shown to correlate with water stress. Drought resistance of seedlings: Comparison between normal seedlings and partially defoliated ones, all subjected to prolonged drought, indicated that removing about half of the lowermost leaves prior to transplanting, may facilitate adjustment to the more stressful conditions in the greenhouse. Implications The results of this experimental study may lead to: (1) An improved model for a sparse canopy in a greenhouse. (2) A better ventilation design procedure utilizing improved estimates of the evaporation coefficient for different species and plant configurations. (3) A test for the stress resistance of transplants.