Analysis of Driving Factors of Cropland Productivity in Northeast China Using OPGD-SHAP Framework DOI Creative Commons

Runzhao Gao,

Hongyan Cai, Xinliang Xu

et al.

Land, Journal Year: 2025, Volume and Issue: 14(5), P. 1010 - 1010

Published: May 7, 2025

In the context of climate change and ecological degradation, enhancing cropland productivity in Northeast China is essential for ensuring national food security. This study adopted an integrated framework combining optimal parameter-based geographical detector (OPGD) SHapley Additive exPlanations (SHAP) to identify key drivers average total at county level from 2001 2020. Growing-season-based Net Primary Productivity (NPP) was estimated using CASA model represent productivity. Results indicated that natural factors significantly dominated spatial variation productivity, with their interactions amplified through dual-factor or nonlinear enhancements. Various machine learning models were fine-tuned compared, selected subsequent SHAP analysis. The findings revealed erosion intensity exhibited most significant impact on whereas effect precipitation shifted negative positive, a clear threshold around 400 mm—matching boundary between China’s semi-arid semi-humid regions. Low-elevation plains (<300 m) gentle slopes (<0.5°) predominately promoted Interactions fertilizer highlighted need moderate fertilization prevent degradation severely eroded counties. These provide scientific support targeted management aimed achieving sustainable agriculture China.

Language: Английский

Analysis of Driving Factors of Cropland Productivity in Northeast China Using OPGD-SHAP Framework DOI Creative Commons

Runzhao Gao,

Hongyan Cai, Xinliang Xu

et al.

Land, Journal Year: 2025, Volume and Issue: 14(5), P. 1010 - 1010

Published: May 7, 2025

In the context of climate change and ecological degradation, enhancing cropland productivity in Northeast China is essential for ensuring national food security. This study adopted an integrated framework combining optimal parameter-based geographical detector (OPGD) SHapley Additive exPlanations (SHAP) to identify key drivers average total at county level from 2001 2020. Growing-season-based Net Primary Productivity (NPP) was estimated using CASA model represent productivity. Results indicated that natural factors significantly dominated spatial variation productivity, with their interactions amplified through dual-factor or nonlinear enhancements. Various machine learning models were fine-tuned compared, selected subsequent SHAP analysis. The findings revealed erosion intensity exhibited most significant impact on whereas effect precipitation shifted negative positive, a clear threshold around 400 mm—matching boundary between China’s semi-arid semi-humid regions. Low-elevation plains (<300 m) gentle slopes (<0.5°) predominately promoted Interactions fertilizer highlighted need moderate fertilization prevent degradation severely eroded counties. These provide scientific support targeted management aimed achieving sustainable agriculture China.

Language: Английский

Citations

0