Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle
The canopy chlorophyll content (CCC) and leaf area index (LAI) are both essential indicators for crop growth monitoring and yield estimation. The PROSAIL model, which couples the properties optique spectrales des feuilles (PROSPECT) and scattering by arbitrarily inclined leaves (SAIL) radiative tran...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2264 |
| _version_ | 1797601824772980736 |
|---|---|
| author | Qi Sun Quanjun Jiao Xidong Chen Huimin Xing Wenjiang Huang Bing Zhang |
| author_facet | Qi Sun Quanjun Jiao Xidong Chen Huimin Xing Wenjiang Huang Bing Zhang |
| author_sort | Qi Sun |
| collection | DOAJ |
| description | The canopy chlorophyll content (CCC) and leaf area index (LAI) are both essential indicators for crop growth monitoring and yield estimation. The PROSAIL model, which couples the properties optique spectrales des feuilles (PROSPECT) and scattering by arbitrarily inclined leaves (SAIL) radiative transfer models, is commonly used for the quantitative retrieval of crop parameters; however, its homogeneous canopy assumption limits its accuracy, especially in the case of multiple crop categories. The adjusted average leaf angle (ALA<sub>adj</sub>), which can be parameterized for a specific crop type, increases the applicability of the PROSAIL model for specific crop types with a non-uniform canopy and has the potential to enhance the performance of PROSAIL-coupled hybrid methods. In this study, the PROSAIL-D model was used to generate the ALA<sub>adj</sub> values of wheat, soybean, and maize crops based on ground-measured spectra, the LAI, and the leaf chlorophyll content (LCC). The results revealed ALA<sub>adj</sub> values of 62 degrees for wheat, 45 degrees for soybean, and 60 degrees for maize. Support vector regression (SVR), random forest regression (RFR), extremely randomized trees regression (ETR), the gradient boosting regression tree (GBRT), and stacking learning (STL) were applied to simulated data of the ALA<sub>adj</sub> in 50-band data to retrieve the CCC and LAI of the crops. The results demonstrated that the estimation accuracy of singular crop parameters, particularly the crop LAI, was greatly enhanced by the five machine learning methods on the basis of data simulated with the ALA<sub>adj</sub>. Regarding the estimation results of mixed crops, the machine learning algorithms using ALA<sub>adj</sub> datasets resulted in estimations of CCC (RMSE: RFR = 51.1 μg cm<sup>−2</sup>, ETR = 54.7 μg cm<sup>−2</sup>, GBRT = 54.9 μg cm<sup>−2</sup>, STL = 48.3 μg cm<sup>−2</sup>) and LAI (RMSE: SVR = 0.91, RFR = 1.03, ETR = 1.05, GBRT = 1.05, STL = 0.97), that outperformed the estimations without using the ALA<sub>adj</sub> (namely CCC RMSE: RFR = 93.0 μg cm<sup>−2</sup>, ETR = 60.1 μg cm<sup>−2</sup>, GBRT = 60.0 μg cm<sup>−2</sup>, STL = 68.5 μg cm<sup>−2</sup> and LAI RMSE: SVR = 2.10, RFR = 2.28, ETR = 1.67, GBRT = 1.66, STL = 1.51). Similar findings were obtained using the suggested method in conjunction with 19-band data, demonstrating the promising potential of this method to estimate the CCC and LAI of crops at the satellite scale. |
| first_indexed | 2024-03-11T04:08:09Z |
| format | Article |
| id | doaj.art-99253262ff984d438a44c3ca1dc55297 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:09Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-99253262ff984d438a44c3ca1dc552972023-11-17T23:37:47ZengMDPI AGRemote Sensing2072-42922023-04-01159226410.3390/rs15092264Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf AngleQi Sun0Quanjun Jiao1Xidong Chen2Huimin Xing3Wenjiang Huang4Bing Zhang5Henan Engineering Technology Research Center of Ecological Protection and Management of the Old Course of Yellow River, Shangqiu Normal University, Shangqiu 476000, ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing 100094, ChinaCollege of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaHenan Engineering Technology Research Center of Ecological Protection and Management of the Old Course of Yellow River, Shangqiu Normal University, Shangqiu 476000, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaThe canopy chlorophyll content (CCC) and leaf area index (LAI) are both essential indicators for crop growth monitoring and yield estimation. The PROSAIL model, which couples the properties optique spectrales des feuilles (PROSPECT) and scattering by arbitrarily inclined leaves (SAIL) radiative transfer models, is commonly used for the quantitative retrieval of crop parameters; however, its homogeneous canopy assumption limits its accuracy, especially in the case of multiple crop categories. The adjusted average leaf angle (ALA<sub>adj</sub>), which can be parameterized for a specific crop type, increases the applicability of the PROSAIL model for specific crop types with a non-uniform canopy and has the potential to enhance the performance of PROSAIL-coupled hybrid methods. In this study, the PROSAIL-D model was used to generate the ALA<sub>adj</sub> values of wheat, soybean, and maize crops based on ground-measured spectra, the LAI, and the leaf chlorophyll content (LCC). The results revealed ALA<sub>adj</sub> values of 62 degrees for wheat, 45 degrees for soybean, and 60 degrees for maize. Support vector regression (SVR), random forest regression (RFR), extremely randomized trees regression (ETR), the gradient boosting regression tree (GBRT), and stacking learning (STL) were applied to simulated data of the ALA<sub>adj</sub> in 50-band data to retrieve the CCC and LAI of the crops. The results demonstrated that the estimation accuracy of singular crop parameters, particularly the crop LAI, was greatly enhanced by the five machine learning methods on the basis of data simulated with the ALA<sub>adj</sub>. Regarding the estimation results of mixed crops, the machine learning algorithms using ALA<sub>adj</sub> datasets resulted in estimations of CCC (RMSE: RFR = 51.1 μg cm<sup>−2</sup>, ETR = 54.7 μg cm<sup>−2</sup>, GBRT = 54.9 μg cm<sup>−2</sup>, STL = 48.3 μg cm<sup>−2</sup>) and LAI (RMSE: SVR = 0.91, RFR = 1.03, ETR = 1.05, GBRT = 1.05, STL = 0.97), that outperformed the estimations without using the ALA<sub>adj</sub> (namely CCC RMSE: RFR = 93.0 μg cm<sup>−2</sup>, ETR = 60.1 μg cm<sup>−2</sup>, GBRT = 60.0 μg cm<sup>−2</sup>, STL = 68.5 μg cm<sup>−2</sup> and LAI RMSE: SVR = 2.10, RFR = 2.28, ETR = 1.67, GBRT = 1.66, STL = 1.51). Similar findings were obtained using the suggested method in conjunction with 19-band data, demonstrating the promising potential of this method to estimate the CCC and LAI of crops at the satellite scale.https://www.mdpi.com/2072-4292/15/9/2264crop chlorophyllcrop LAIPROSAILaverage leaf anglemachine learning |
| spellingShingle | Qi Sun Quanjun Jiao Xidong Chen Huimin Xing Wenjiang Huang Bing Zhang Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle Remote Sensing crop chlorophyll crop LAI PROSAIL average leaf angle machine learning |
| title | Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle |
| title_full | Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle |
| title_fullStr | Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle |
| title_full_unstemmed | Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle |
| title_short | Machine Learning Algorithms for the Retrieval of Canopy Chlorophyll Content and Leaf Area Index of Crops Using the PROSAIL-D Model with the Adjusted Average Leaf Angle |
| title_sort | machine learning algorithms for the retrieval of canopy chlorophyll content and leaf area index of crops using the prosail d model with the adjusted average leaf angle |
| topic | crop chlorophyll crop LAI PROSAIL average leaf angle machine learning |
| url | https://www.mdpi.com/2072-4292/15/9/2264 |
| work_keys_str_mv | AT qisun machinelearningalgorithmsfortheretrievalofcanopychlorophyllcontentandleafareaindexofcropsusingtheprosaildmodelwiththeadjustedaverageleafangle AT quanjunjiao machinelearningalgorithmsfortheretrievalofcanopychlorophyllcontentandleafareaindexofcropsusingtheprosaildmodelwiththeadjustedaverageleafangle AT xidongchen machinelearningalgorithmsfortheretrievalofcanopychlorophyllcontentandleafareaindexofcropsusingtheprosaildmodelwiththeadjustedaverageleafangle AT huiminxing machinelearningalgorithmsfortheretrievalofcanopychlorophyllcontentandleafareaindexofcropsusingtheprosaildmodelwiththeadjustedaverageleafangle AT wenjianghuang machinelearningalgorithmsfortheretrievalofcanopychlorophyllcontentandleafareaindexofcropsusingtheprosaildmodelwiththeadjustedaverageleafangle AT bingzhang machinelearningalgorithmsfortheretrievalofcanopychlorophyllcontentandleafareaindexofcropsusingtheprosaildmodelwiththeadjustedaverageleafangle |