Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach
Solar-induced chlorophyll fluorescence (SIF), as a direct indicator of vegetation photosynthesis, offers a more accurate measure of plant photosynthetic dynamics than traditional vegetation indices. However, the current SIF satellite products have low spatial resolution, limiting their application i...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/1/133 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589437612064768 |
|---|---|
| author | Jinrui Fan Xiaoping Lu Guosheng Cai Zhengfang Lou Jing Wen |
| author_facet | Jinrui Fan Xiaoping Lu Guosheng Cai Zhengfang Lou Jing Wen |
| author_sort | Jinrui Fan |
| collection | DOAJ |
| description | Solar-induced chlorophyll fluorescence (SIF), as a direct indicator of vegetation photosynthesis, offers a more accurate measure of plant photosynthetic dynamics than traditional vegetation indices. However, the current SIF satellite products have low spatial resolution, limiting their application in fine-scale agricultural research. To address this, we leveraged MODIS data at a 1 km resolution, including bands b1, b2, b3, and b4, alongside indices such as the NDVI, EVI, NIRv, OSAVI, SAVI, LAI, FPAR, and LST, covering October 2018 to May 2020 for Shandong Province, China. Using the Random Forest (RF) model, we downscaled SIF data from 0.05° to 1 km based on invariant spatial scaling theory, focusing on the winter wheat growth cycle. Various machine learning models, including CNN, Stacking, Extreme Random Trees, AdaBoost, and GBDT, were compared, with Random Forest yielding the best performance, achieving R<sup>2</sup> = 0.931, RMSE = 0.052 mW/m<sup>2</sup>/nm/sr, and MAE = 0.031 mW/m<sup>2</sup>/nm/sr for 2018–2019 and R<sup>2</sup> = 0.926, RMSE = 0.058 mW/m<sup>2</sup>/nm/sr, and MAE = 0.034 mW/m<sup>2</sup>/nm/sr for 2019–2020. The downscaled SIF products showed a strong correlation with TanSIF and GOSIF products (R<sup>2</sup> > 0.8), and consistent trends with GPP further confirmed the reliability of the 1 km SIF product. Additionally, a time series analysis of Shandong Province’s wheat-growing areas revealed a strong correlation (R<sup>2</sup> > 0.8) between SIF and multiple vegetation indices, underscoring its utility for regional crop monitoring. |
| format | Article |
| id | doaj-art-e223e61194fc48939cabf4b25efc86b5 |
| institution | Kabale University |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-e223e61194fc48939cabf4b25efc86b52025-01-24T13:16:52ZengMDPI AGAgronomy2073-43952025-01-0115113310.3390/agronomy15010133Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence ApproachJinrui Fan0Xiaoping Lu1Guosheng Cai2Zhengfang Lou3Jing Wen4Key Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines, Ministry of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454000, ChinaKey Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines, Ministry of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454000, ChinaKey Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines, Ministry of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454000, ChinaKey Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines, Ministry of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454000, ChinaKey Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines, Ministry of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454000, ChinaSolar-induced chlorophyll fluorescence (SIF), as a direct indicator of vegetation photosynthesis, offers a more accurate measure of plant photosynthetic dynamics than traditional vegetation indices. However, the current SIF satellite products have low spatial resolution, limiting their application in fine-scale agricultural research. To address this, we leveraged MODIS data at a 1 km resolution, including bands b1, b2, b3, and b4, alongside indices such as the NDVI, EVI, NIRv, OSAVI, SAVI, LAI, FPAR, and LST, covering October 2018 to May 2020 for Shandong Province, China. Using the Random Forest (RF) model, we downscaled SIF data from 0.05° to 1 km based on invariant spatial scaling theory, focusing on the winter wheat growth cycle. Various machine learning models, including CNN, Stacking, Extreme Random Trees, AdaBoost, and GBDT, were compared, with Random Forest yielding the best performance, achieving R<sup>2</sup> = 0.931, RMSE = 0.052 mW/m<sup>2</sup>/nm/sr, and MAE = 0.031 mW/m<sup>2</sup>/nm/sr for 2018–2019 and R<sup>2</sup> = 0.926, RMSE = 0.058 mW/m<sup>2</sup>/nm/sr, and MAE = 0.034 mW/m<sup>2</sup>/nm/sr for 2019–2020. The downscaled SIF products showed a strong correlation with TanSIF and GOSIF products (R<sup>2</sup> > 0.8), and consistent trends with GPP further confirmed the reliability of the 1 km SIF product. Additionally, a time series analysis of Shandong Province’s wheat-growing areas revealed a strong correlation (R<sup>2</sup> > 0.8) between SIF and multiple vegetation indices, underscoring its utility for regional crop monitoring.https://www.mdpi.com/2073-4395/15/1/133solar-induced chlorophyll fluorescencerandom forestdownscalinggross primary productivitywheat growth analysis |
| spellingShingle | Jinrui Fan Xiaoping Lu Guosheng Cai Zhengfang Lou Jing Wen Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach Agronomy solar-induced chlorophyll fluorescence random forest downscaling gross primary productivity wheat growth analysis |
| title | Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach |
| title_full | Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach |
| title_fullStr | Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach |
| title_full_unstemmed | Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach |
| title_short | Multi-Feature Driver Variable Fusion Downscaling TROPOMI Solar-Induced Chlorophyll Fluorescence Approach |
| title_sort | multi feature driver variable fusion downscaling tropomi solar induced chlorophyll fluorescence approach |
| topic | solar-induced chlorophyll fluorescence random forest downscaling gross primary productivity wheat growth analysis |
| url | https://www.mdpi.com/2073-4395/15/1/133 |
| work_keys_str_mv | AT jinruifan multifeaturedrivervariablefusiondownscalingtropomisolarinducedchlorophyllfluorescenceapproach AT xiaopinglu multifeaturedrivervariablefusiondownscalingtropomisolarinducedchlorophyllfluorescenceapproach AT guoshengcai multifeaturedrivervariablefusiondownscalingtropomisolarinducedchlorophyllfluorescenceapproach AT zhengfanglou multifeaturedrivervariablefusiondownscalingtropomisolarinducedchlorophyllfluorescenceapproach AT jingwen multifeaturedrivervariablefusiondownscalingtropomisolarinducedchlorophyllfluorescenceapproach |