Estimation of Gross Primary Productivity Using Performance-Optimized Machine Learning Methods for the Forest Ecosystems in China DOI Open Access
Qin Na, Quan Lai, Gang Bao

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(3), P. 518 - 518

Published: March 15, 2025

Gross primary productivity (GPP) quantifies the rate at which plants convert atmospheric carbon dioxide into organic matter through photosynthesis, playing a vital role in terrestrial cycle. Machine learning (ML) techniques excel handling spatiotemporally complex data, facilitating accurate spatial-scale inversion of forest GPP by integrating limited ground flux measurements with Remote Sensing (RS) observations. Enhancing ML algorithm performance for precise estimation is key research focus. This study introduces Random Grid Search Algorithm (RGSA) hyperparameters tuning to improve Forest (RF) and eXtreme Gradient Boosting (XGB) models across four major regions China. Model optimization progressed three stages: Unoptimized (UO) XGB model achieved R2 = 0.77 RMSE 1.42 g Cm−2 d−1; Hyperparameter Optimized (HO) using RGSA improved 5.19% (0.81) reduced 9.15% (1.29 d−1); Variable Combination (HVCO) selected variables (LAI, Temp, NR, VPD, NDVI) further enhanced 0.83 decreased 1.23 d−1. The optimized estimates exhibited high spatial consistency existing high-quality products like GOSIF GPP, GLASS FLUXCOM validating model’s reliability effectiveness. provides crucial insights improving accuracy optimizing methodologies ecosystems

Language: Английский

Greening but enhanced vegetation water stress in the Yellow River Basin: A holistic perspective DOI

Boying Song,

Xiujuan Jiang,

Zening Wu

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 375, P. 124139 - 124139

Published: Jan. 21, 2025

Language: Английский

Citations

0
Estimation of Gross Primary Productivity Using Performance-Optimized Machine Learning Methods for the Forest Ecosystems in China DOI Open Access
Qin Na, Quan Lai, Gang Bao

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(3), P. 518 - 518

Published: March 15, 2025

Gross primary productivity (GPP) quantifies the rate at which plants convert atmospheric carbon dioxide into organic matter through photosynthesis, playing a vital role in terrestrial cycle. Machine learning (ML) techniques excel handling spatiotemporally complex data, facilitating accurate spatial-scale inversion of forest GPP by integrating limited ground flux measurements with Remote Sensing (RS) observations. Enhancing ML algorithm performance for precise estimation is key research focus. This study introduces Random Grid Search Algorithm (RGSA) hyperparameters tuning to improve Forest (RF) and eXtreme Gradient Boosting (XGB) models across four major regions China. Model optimization progressed three stages: Unoptimized (UO) XGB model achieved R2 = 0.77 RMSE 1.42 g Cm−2 d−1; Hyperparameter Optimized (HO) using RGSA improved 5.19% (0.81) reduced 9.15% (1.29 d−1); Variable Combination (HVCO) selected variables (LAI, Temp, NR, VPD, NDVI) further enhanced 0.83 decreased 1.23 d−1. The optimized estimates exhibited high spatial consistency existing high-quality products like GOSIF GPP, GLASS FLUXCOM validating model’s reliability effectiveness. provides crucial insights improving accuracy optimizing methodologies ecosystems

Language: Английский

Citations

0