Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information
Leaf chlorophyll content (LCC) is vital for photosynthesis and ecosystem functioning; it influences carbon, water, and energy exchanges while serving as an indicator of photosynthetic activity and nitrogen levels in precision agriculture. Hyperspectral data enable precise LCC monitoring by extractin...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124005223 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595384698929152 |
|---|---|
| author | Nigela Tuerxun Sulei Naibi Jianghua Zheng Renjun Wang Lei Wang Binbin Lu Danlin Yu |
| author_facet | Nigela Tuerxun Sulei Naibi Jianghua Zheng Renjun Wang Lei Wang Binbin Lu Danlin Yu |
| author_sort | Nigela Tuerxun |
| collection | DOAJ |
| description | Leaf chlorophyll content (LCC) is vital for photosynthesis and ecosystem functioning; it influences carbon, water, and energy exchanges while serving as an indicator of photosynthetic activity and nitrogen levels in precision agriculture. Hyperspectral data enable precise LCC monitoring by extracting spectral indices through optimal band combination (OBC) and predicting LCC with machine learning. However, OBC faces dimensionality issues, and machine learning models often overlook geographical influences, potentially reducing prediction accuracy. This study hypothesizes that developing spectral indices from important wavelengths and integrating geospatial data into machine learning models can address these issues and increase prediction accuracy. To test this hypothesis, a framework was developed that first uses elastic net (EN) and the successive projection algorithm (SPA) for wavelength selection, followed by spectral index creation with OBC and ranking with random forest (RF). Support vector regression (SVR), random forest regression (RFR), and geographically weighted least squares support vector regression (GWLS-SVR) were then used to assess the prediction accuracy. Finally, the optimal variables and regression model were identified. The results revealed that the EN- and SPA-based indices had stronger correlations and importance than defined indices. The double-difference index (DDn) and the anti-reflectance index (ARI) are the most robust three-dimensional and two-dimensional spectral indices, respectively. GWLS-SVR requires fewer indices (1–4) to achieve optimal results, with EN-DDn (2R519-R775-R936)-GWLS-SVR performing best (R2 = 0.95, RMSE = 0.61, PBIAS = -0.02). This research presents a robust framework with strong adaptability for estimating LCC in a specific study area and region, demonstrating substantial potential for the precise estimation of agroforestry vegetation parameters. |
| format | Article |
| id | doaj-art-32c7963dcdf44538be0da8d2a30f1f04 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-32c7963dcdf44538be0da8d2a30f1f042025-01-19T06:24:42ZengElsevierEcological Informatics1574-95412025-03-0185102980Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial informationNigela Tuerxun0Sulei Naibi1Jianghua Zheng2Renjun Wang3Lei Wang4Binbin Lu5Danlin Yu6College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, PR China; Xinjiang Key Laboratory of Oasis Ecology, Xinjiang University, Urumqi 830046, PR ChinaState Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, PR China; University of Chinese Academy of Sciences, Beijing 100049, PR China; Department of Geography, Ghent University, Ghent 9000, Belgium; Sino-Belgian Joint Laboratory for Geo-Information, Ghent, Urumqi, PR ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, PR China; Xinjiang Key Laboratory of Oasis Ecology, Xinjiang University, Urumqi 830046, PR China; Corresponding author at: College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, PR China.College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, PR China; Xinjiang Key Laboratory of Oasis Ecology, Xinjiang University, Urumqi 830046, PR ChinaInstitute of Modern Forestry, Xinjiang Academy of Forestry Sciences, Urumqi 830063, PR ChinaInstitute of Remote Sensing Information Engineering, Wuhan University, Wuhan 430072, PR ChinaDepartment of Earth and Environmental Studies, Montclair State University, NJ 07043, USALeaf chlorophyll content (LCC) is vital for photosynthesis and ecosystem functioning; it influences carbon, water, and energy exchanges while serving as an indicator of photosynthetic activity and nitrogen levels in precision agriculture. Hyperspectral data enable precise LCC monitoring by extracting spectral indices through optimal band combination (OBC) and predicting LCC with machine learning. However, OBC faces dimensionality issues, and machine learning models often overlook geographical influences, potentially reducing prediction accuracy. This study hypothesizes that developing spectral indices from important wavelengths and integrating geospatial data into machine learning models can address these issues and increase prediction accuracy. To test this hypothesis, a framework was developed that first uses elastic net (EN) and the successive projection algorithm (SPA) for wavelength selection, followed by spectral index creation with OBC and ranking with random forest (RF). Support vector regression (SVR), random forest regression (RFR), and geographically weighted least squares support vector regression (GWLS-SVR) were then used to assess the prediction accuracy. Finally, the optimal variables and regression model were identified. The results revealed that the EN- and SPA-based indices had stronger correlations and importance than defined indices. The double-difference index (DDn) and the anti-reflectance index (ARI) are the most robust three-dimensional and two-dimensional spectral indices, respectively. GWLS-SVR requires fewer indices (1–4) to achieve optimal results, with EN-DDn (2R519-R775-R936)-GWLS-SVR performing best (R2 = 0.95, RMSE = 0.61, PBIAS = -0.02). This research presents a robust framework with strong adaptability for estimating LCC in a specific study area and region, demonstrating substantial potential for the precise estimation of agroforestry vegetation parameters.http://www.sciencedirect.com/science/article/pii/S1574954124005223GWLS-SVR modelHyperspectral dataJujubeSPAD valuesSpectral indices |
| spellingShingle | Nigela Tuerxun Sulei Naibi Jianghua Zheng Renjun Wang Lei Wang Binbin Lu Danlin Yu Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information Ecological Informatics GWLS-SVR model Hyperspectral data Jujube SPAD values Spectral indices |
| title | Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information |
| title_full | Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information |
| title_fullStr | Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information |
| title_full_unstemmed | Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information |
| title_short | Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information |
| title_sort | accurate estimation of jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information |
| topic | GWLS-SVR model Hyperspectral data Jujube SPAD values Spectral indices |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124005223 |
| work_keys_str_mv | AT nigelatuerxun accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation AT suleinaibi accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation AT jianghuazheng accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation AT renjunwang accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation AT leiwang accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation AT binbinlu accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation AT danlinyu accurateestimationofjujubeleafchlorophyllcontentusingoptimizedspectralindicesandmachinelearningmethodsintegratinggeospatialinformation |