Spectroscopy can be used for detecting crop characteristics. A goal of crop spectrum analysis is to extract effective features from spectral data for establishing a detection model. An ideal spectral feature set shoul...Spectroscopy can be used for detecting crop characteristics. A goal of crop spectrum analysis is to extract effective features from spectral data for establishing a detection model. An ideal spectral feature set should have high sensitivity to target parameters but low information redundancy among features.However, feature-selection methods that satisfy both requirements are lacking. To address this issue,in this study, a novel method, the continuous wavelet projections algorithm(CWPA), was developed,which has advantages of both continuous wavelet analysis(CWA) and the successive projections algorithm(SPA) for generating optimal spectral feature set for crop detection. Three datasets collected for crop stress detection and retrieval of biochemical properties were used to validate the CWPA under both classification and regression scenarios. The CWPA generated a feature set with fewer features yet achieving accuracy comparable to or even higher than those of CWA and SPA. With only two to three features identified by CWPA, an overall accuracy of 98% in classifying tea plant stresses was achieved, and high coefficients of determination were obtained in retrieving corn leaf chlorophyll content(R^(2)= 0.8521)and equivalent water thickness(R^(2)= 0.9508). The mechanism of the CWPA ensures that the novel algorithm discovers the most sensitive features while retaining complementarity among features. Its ability to reduce the data dimension suggests its potential for crop monitoring and phenotyping with hyperspectral data.展开更多
This paper is devoted to the development and testing of the optimal procedures for retrieving biophysical crop variables by exploiting the spectral information of current multispectral optical satellite Sentinel-2 and...This paper is devoted to the development and testing of the optimal procedures for retrieving biophysical crop variables by exploiting the spectral information of current multispectral optical satellite Sentinel-2 and Venus and in view of the advent of the new Sino-EU hyperspectral satellite(e.g.,PRISMA,EnMAP,and GF-5).Two different methodologies devoted to the estimation of biophysical crop variables Leaf area index(LAI)and Leaf chlorophyll content(Cab)were evaluated:non-kernel-based and kernel-based Machine Learning Regression Algorithms(MLRA);Sentinel-2 and Venus data comparison for the analysis of the durum wheat-growing season.Results show that for Sentinel-2 data,Gaussian Process Regression(GPR)was the best performing algorithm for both LAI(R 2=0.89 and RMSE=0.59)and Cab(R 2=0.70 and RMSE=8.31).Whereas,for PRISMA simulated data the Kernel Ridge Regression(KRR)was the best performing algorithm among all the other MLRA(R 2=0.91 and RMSE=0.51)for LAI and(R 2=0.83 and RMSE=6.09)for Cab,respectively.Results of Sentinel-2 and Venus data for durum wheat-growing season were consistent with ground truth data and confirm also that SWIR bands,which are used as tie-points in the PROSAIL inversion,are extremely useful for an accurate retrieving of crop biophysical parameters.展开更多
农业系统模型是农业生产多元目标优化管理的重要工具,但由于系统模型过程复杂,参数众多,校正和验证工作一直是模型研究的重点和难点。本文利用RZWQM(Root Zone Water Quality Model)与CERES(Crop Environment Resource Synthesis)的结...农业系统模型是农业生产多元目标优化管理的重要工具,但由于系统模型过程复杂,参数众多,校正和验证工作一直是模型研究的重点和难点。本文利用RZWQM(Root Zone Water Quality Model)与CERES(Crop Environment Resource Synthesis)的结合模型RZWQM-CERES模拟土壤水分及作物产量进行了参数优化和验证,结果表明,RZWQM-CERES在禹城站和栾城站模拟不同灌溉处理土壤贮水量与测定值呈相似的变化趋势,均方根差(RMSE)分别为2.38～2.70cm及3.49～3.73cm;作物产量模拟结果与实测值对土壤水分的响应趋势一致(R2=0.83***,n=22),其中在禹城站模拟小麦和玉米产量的RMSE分别为550kghm?2和580kghm-2,栾城站模拟小麦产量的RMSE为670kghm-2。以上结果表明RZWQM-CERES可作为华北平原模拟和分析土壤水分对作物产量影响的有效工具。本文初步建立了一套适合华北平原作物生产的模型参数,为利用RZWQM-CERES建立农田水分优化调控策略奠定了基础,并探讨了模型评价过程中应注意的问题。展开更多
准确模拟水分胁迫并揭示其对作物生长发育过程的影响,是作物模型应用于田间研究和干旱影响评估的关键。该研究将3种主流水分胁迫算法整合到一个标准平台中,组成土壤含水率模型(average Soil Water Content,SWC)、土壤水分供需比模型(Wat...准确模拟水分胁迫并揭示其对作物生长发育过程的影响,是作物模型应用于田间研究和干旱影响评估的关键。该研究将3种主流水分胁迫算法整合到一个标准平台中,组成土壤含水率模型(average Soil Water Content,SWC)、土壤水分供需比模型(Water Supply to Demand ratio,WS/WD)和相对蒸腾模型(Actual to Potential Transpiration ratio,AT/PT)共3种水分胁迫模拟模型。利用河北吴桥2017—2019年冬小麦水分试验田间观测数据结合2008—2009和2013—2016年水分试验文献资料对模型平台进行参数校准与验证。结果表明,3种模型的模拟结果与实测值均吻合良好,地上部生物量、土壤含水率和产量的归一化均方根误差(Normalized Root Mean Squared Error,NRMSE)分别为14.0%~16.5%、5.1%~8.8%和5.4%~7.7%。3种水分胁迫模型模拟的生长季水分亏缺出现的时间和严重程度不同,但模拟的水分胁迫因子年际间变化一致。雨养条件下,生长季降水量分别决定了SWC、WS/WD和AT/PT模型模拟的年际间水分胁迫因子变异的56%、56%和39%。灌水对产量具有促进作用,但灌水量增加会导致灌水利用效率下降。SWC、WS/WD和AT/PT模型模拟枯水年灌四水(底墒水+起身水+孕穗水+开花水)处理的产量较不灌水分别高163%、132%和92%,灌四水处理的灌水利用效率较灌一水(底墒水)处理分别低26.8%、12.3%和40.0%。在吴桥县冬小麦水分管理决策中,WS/WD模型最优,SWC模型次之,AP/TP模型较差。研究结果可为提升作物模型在冬小麦干旱影响评估和水分管理方面的可信度提供参考。展开更多
基金supported by the National Natural Science Foundation of China (42071420)the Major Special Project for 2025 Scientific,Technological Innovation (Major Scientific and Technological Task Project in Ningbo City)(2021Z048)the National Key Research and Development Program of China(2019YFE0125300)。
文摘Spectroscopy can be used for detecting crop characteristics. A goal of crop spectrum analysis is to extract effective features from spectral data for establishing a detection model. An ideal spectral feature set should have high sensitivity to target parameters but low information redundancy among features.However, feature-selection methods that satisfy both requirements are lacking. To address this issue,in this study, a novel method, the continuous wavelet projections algorithm(CWPA), was developed,which has advantages of both continuous wavelet analysis(CWA) and the successive projections algorithm(SPA) for generating optimal spectral feature set for crop detection. Three datasets collected for crop stress detection and retrieval of biochemical properties were used to validate the CWPA under both classification and regression scenarios. The CWPA generated a feature set with fewer features yet achieving accuracy comparable to or even higher than those of CWA and SPA. With only two to three features identified by CWPA, an overall accuracy of 98% in classifying tea plant stresses was achieved, and high coefficients of determination were obtained in retrieving corn leaf chlorophyll content(R^(2)= 0.8521)and equivalent water thickness(R^(2)= 0.9508). The mechanism of the CWPA ensures that the novel algorithm discovers the most sensitive features while retaining complementarity among features. Its ability to reduce the data dimension suggests its potential for crop monitoring and phenotyping with hyperspectral data.
基金This paper was supported by European Space Agency(ESA)contract 4000121195-Ministry of Science and Technology(MOST),Dragon 4 cooperation(ID:32275).Specifically,Subproject1-Topic1“Algorithm Development Exploiting Multitemporal and Multi Sensor Satellite Data for Improving Crop Classification,Biophysical and Agronomic Variables Retrieval and Yield Prediction”and by the Italian Space Agency(ASI)project PRISCAV(PRISMA Calibration/Validation).
文摘This paper is devoted to the development and testing of the optimal procedures for retrieving biophysical crop variables by exploiting the spectral information of current multispectral optical satellite Sentinel-2 and Venus and in view of the advent of the new Sino-EU hyperspectral satellite(e.g.,PRISMA,EnMAP,and GF-5).Two different methodologies devoted to the estimation of biophysical crop variables Leaf area index(LAI)and Leaf chlorophyll content(Cab)were evaluated:non-kernel-based and kernel-based Machine Learning Regression Algorithms(MLRA);Sentinel-2 and Venus data comparison for the analysis of the durum wheat-growing season.Results show that for Sentinel-2 data,Gaussian Process Regression(GPR)was the best performing algorithm for both LAI(R 2=0.89 and RMSE=0.59)and Cab(R 2=0.70 and RMSE=8.31).Whereas,for PRISMA simulated data the Kernel Ridge Regression(KRR)was the best performing algorithm among all the other MLRA(R 2=0.91 and RMSE=0.51)for LAI and(R 2=0.83 and RMSE=6.09)for Cab,respectively.Results of Sentinel-2 and Venus data for durum wheat-growing season were consistent with ground truth data and confirm also that SWIR bands,which are used as tie-points in the PROSAIL inversion,are extremely useful for an accurate retrieving of crop biophysical parameters.
文摘农业系统模型是农业生产多元目标优化管理的重要工具,但由于系统模型过程复杂,参数众多,校正和验证工作一直是模型研究的重点和难点。本文利用RZWQM(Root Zone Water Quality Model)与CERES(Crop Environment Resource Synthesis)的结合模型RZWQM-CERES模拟土壤水分及作物产量进行了参数优化和验证,结果表明,RZWQM-CERES在禹城站和栾城站模拟不同灌溉处理土壤贮水量与测定值呈相似的变化趋势,均方根差(RMSE)分别为2.38～2.70cm及3.49～3.73cm;作物产量模拟结果与实测值对土壤水分的响应趋势一致(R2=0.83***,n=22),其中在禹城站模拟小麦和玉米产量的RMSE分别为550kghm?2和580kghm-2,栾城站模拟小麦产量的RMSE为670kghm-2。以上结果表明RZWQM-CERES可作为华北平原模拟和分析土壤水分对作物产量影响的有效工具。本文初步建立了一套适合华北平原作物生产的模型参数,为利用RZWQM-CERES建立农田水分优化调控策略奠定了基础,并探讨了模型评价过程中应注意的问题。
文摘准确模拟水分胁迫并揭示其对作物生长发育过程的影响,是作物模型应用于田间研究和干旱影响评估的关键。该研究将3种主流水分胁迫算法整合到一个标准平台中,组成土壤含水率模型(average Soil Water Content,SWC)、土壤水分供需比模型(Water Supply to Demand ratio,WS/WD)和相对蒸腾模型(Actual to Potential Transpiration ratio,AT/PT)共3种水分胁迫模拟模型。利用河北吴桥2017—2019年冬小麦水分试验田间观测数据结合2008—2009和2013—2016年水分试验文献资料对模型平台进行参数校准与验证。结果表明,3种模型的模拟结果与实测值均吻合良好,地上部生物量、土壤含水率和产量的归一化均方根误差(Normalized Root Mean Squared Error,NRMSE)分别为14.0%~16.5%、5.1%~8.8%和5.4%~7.7%。3种水分胁迫模型模拟的生长季水分亏缺出现的时间和严重程度不同,但模拟的水分胁迫因子年际间变化一致。雨养条件下,生长季降水量分别决定了SWC、WS/WD和AT/PT模型模拟的年际间水分胁迫因子变异的56%、56%和39%。灌水对产量具有促进作用,但灌水量增加会导致灌水利用效率下降。SWC、WS/WD和AT/PT模型模拟枯水年灌四水(底墒水+起身水+孕穗水+开花水)处理的产量较不灌水分别高163%、132%和92%,灌四水处理的灌水利用效率较灌一水(底墒水)处理分别低26.8%、12.3%和40.0%。在吴桥县冬小麦水分管理决策中,WS/WD模型最优,SWC模型次之,AP/TP模型较差。研究结果可为提升作物模型在冬小麦干旱影响评估和水分管理方面的可信度提供参考。
