The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity

Sun-induced chlorophyll fluorescence (SIF) is an important indicator of vegetation photosynthesis. While remote sensing enables large-scale monitoring of SIF, existing products face the challenge of trade-offs between temporal and spatial resolutions, limiting their applications. To select the optim...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenyu Hu, Pinhua Xie, Zhaokun Hu, Ang Li, Haoxuan Feng
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2642
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770518644785152
author Chenyu Hu
Pinhua Xie
Zhaokun Hu
Ang Li
Haoxuan Feng
author_facet Chenyu Hu
Pinhua Xie
Zhaokun Hu
Ang Li
Haoxuan Feng
author_sort Chenyu Hu
collection DOAJ
description Sun-induced chlorophyll fluorescence (SIF) is an important indicator of vegetation photosynthesis. While remote sensing enables large-scale monitoring of SIF, existing products face the challenge of trade-offs between temporal and spatial resolutions, limiting their applications. To select the optimal model for SIF data downscaling, we used a consistent dataset combined with vegetation physiological and meteorological parameters to evaluate four different regression methods in this study. The XGBoost model demonstrated the best performance during cross-validation (R<sup>2</sup> = 0.84, RMSE = 0.137 mW/m<sup>2</sup>/nm/sr) and was, therefore, selected to downscale GOME-2 SIF data. The resulting high-resolution SIF product (HRSIF) has a temporal resolution of 8 days and a spatial resolution of 0.05° × 0.05°. The downscaled product shows high fidelity to the original coarse SIF data when aggregated (correlation = 0.76). The reliability of the product was ensured through cross-validation with ground-based and satellite observations. Moreover, the finer spatial resolution of HRSIF better matches the footprint of eddy covariance flux towers, leading to a significant improvement in the correlation with tower-based gross primary productivity (GPP). Specifically, in the mixed forest vegetation type with the best performance, the R<sup>2</sup> increased from 0.66 to 0.85, representing an increase of 28%. This higher-precision product will support more effective ecosystem monitoring and research.
format Article
id doaj-art-797e3a8a2df6469481083f83401bd0c7
institution DOAJ
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-797e3a8a2df6469481083f83401bd0c72025-08-20T03:02:58ZengMDPI AGRemote Sensing2072-42922025-07-011715264210.3390/rs17152642The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem ProductivityChenyu Hu0Pinhua Xie1Zhaokun Hu2Ang Li3Haoxuan Feng4School of Environmental Science and Optoelectronic Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Environmental Science and Optoelectronic Technology, University of Science and Technology of China, Hefei 230026, ChinaKey Laboratory of Environmental Optical and Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Environmental Optical and Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaSchool of Environmental Science and Optoelectronic Technology, University of Science and Technology of China, Hefei 230026, ChinaSun-induced chlorophyll fluorescence (SIF) is an important indicator of vegetation photosynthesis. While remote sensing enables large-scale monitoring of SIF, existing products face the challenge of trade-offs between temporal and spatial resolutions, limiting their applications. To select the optimal model for SIF data downscaling, we used a consistent dataset combined with vegetation physiological and meteorological parameters to evaluate four different regression methods in this study. The XGBoost model demonstrated the best performance during cross-validation (R<sup>2</sup> = 0.84, RMSE = 0.137 mW/m<sup>2</sup>/nm/sr) and was, therefore, selected to downscale GOME-2 SIF data. The resulting high-resolution SIF product (HRSIF) has a temporal resolution of 8 days and a spatial resolution of 0.05° × 0.05°. The downscaled product shows high fidelity to the original coarse SIF data when aggregated (correlation = 0.76). The reliability of the product was ensured through cross-validation with ground-based and satellite observations. Moreover, the finer spatial resolution of HRSIF better matches the footprint of eddy covariance flux towers, leading to a significant improvement in the correlation with tower-based gross primary productivity (GPP). Specifically, in the mixed forest vegetation type with the best performance, the R<sup>2</sup> increased from 0.66 to 0.85, representing an increase of 28%. This higher-precision product will support more effective ecosystem monitoring and research.https://www.mdpi.com/2072-4292/17/15/2642Sun-induced chlorophyll fluorescencemachine learningXGBoost modeldownscaling
spellingShingle Chenyu Hu
Pinhua Xie
Zhaokun Hu
Ang Li
Haoxuan Feng
The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity
Remote Sensing
Sun-induced chlorophyll fluorescence
machine learning
XGBoost model
downscaling
title The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity
title_full The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity
title_fullStr The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity
title_full_unstemmed The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity
title_short The Downscaled GOME-2 SIF Based on Machine Learning Enhances the Correlation with Ecosystem Productivity
title_sort downscaled gome 2 sif based on machine learning enhances the correlation with ecosystem productivity
topic Sun-induced chlorophyll fluorescence
machine learning
XGBoost model
downscaling
url https://www.mdpi.com/2072-4292/17/15/2642
work_keys_str_mv AT chenyuhu thedownscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT pinhuaxie thedownscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT zhaokunhu thedownscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT angli thedownscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT haoxuanfeng thedownscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT chenyuhu downscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT pinhuaxie downscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT zhaokunhu downscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT angli downscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity
AT haoxuanfeng downscaledgome2sifbasedonmachinelearningenhancesthecorrelationwithecosystemproductivity