Decoding Agricultural Drought Resilience: A Triple-Validated Random Forest Framework Integrating Multi-Source Remote Sensing for High-Resolution Monitoring in the North China Plain DOI Creative Commons
Xianyong Meng, Song Zhang, Guoqing Wang

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(8), P. 1404 - 1404

Published: April 15, 2025

Agricultural drought poses a severe threat to food security in the North China Plain, necessitating accurate and timely monitoring approaches. This study presents novel assessment framework that innovatively integrates multiple remote sensing indices through an optimized random forest algorithm, achieving unprecedented accuracy regional monitoring. The introduces three key innovations: (1) systematic integration of six drought-related factors including vegetation condition index (VCI), temperature (TCI), precipitation (PCI), land cover type (LC), aspect (ASPECT), available water capacity (AWC); (2) algorithm configuration with 100 decision trees enhanced feature extraction capability; (3) robust triple-validation strategy combining standardized evapotranspiration (SPEI), comprehensive meteorological (CI), soil moisture verification. demonstrates exceptional performance R2 values consistently above 0.80 for monthly assessments, reaching 0.86 during autumn 0.73 summer seasons. Particularly, it achieves 87% mild (−1.0 < SPEI ≤ −0.5) 85% moderate (−1.5 −1.0) detection. 20-year (2000–2019) spatiotemporal analysis reveals events dominated region (23.7% total occurrences), significant intensification 2010–2012 2014–2016 periods. Summer frequency peaked at 12–15 months south-central Shandong (37°N, 117°E) eastern Henan (34°N, 114°E). framework’s high spatial resolution (1 km) validation protocol establish reliable foundation agricultural resource management, offering transferable methodology worldwide.

Language: Английский

CO-ResNetRS50-SSL: Enhanced convolution and semi-supervised learning for accurate rice growth stage recognition in complex field conditions DOI
Changqing Yan,

Gui Hua Yang,

Zeyun Liang

et al.

European Journal of Agronomy, Journal Year: 2025, Volume and Issue: 168, P. 127631 - 127631

Published: April 8, 2025

Language: Английский

Citations

0
Decoding Agricultural Drought Resilience: A Triple-Validated Random Forest Framework Integrating Multi-Source Remote Sensing for High-Resolution Monitoring in the North China Plain DOI Creative Commons
Xianyong Meng, Song Zhang, Guoqing Wang

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(8), P. 1404 - 1404

Published: April 15, 2025

Agricultural drought poses a severe threat to food security in the North China Plain, necessitating accurate and timely monitoring approaches. This study presents novel assessment framework that innovatively integrates multiple remote sensing indices through an optimized random forest algorithm, achieving unprecedented accuracy regional monitoring. The introduces three key innovations: (1) systematic integration of six drought-related factors including vegetation condition index (VCI), temperature (TCI), precipitation (PCI), land cover type (LC), aspect (ASPECT), available water capacity (AWC); (2) algorithm configuration with 100 decision trees enhanced feature extraction capability; (3) robust triple-validation strategy combining standardized evapotranspiration (SPEI), comprehensive meteorological (CI), soil moisture verification. demonstrates exceptional performance R2 values consistently above 0.80 for monthly assessments, reaching 0.86 during autumn 0.73 summer seasons. Particularly, it achieves 87% mild (−1.0 < SPEI ≤ −0.5) 85% moderate (−1.5 −1.0) detection. 20-year (2000–2019) spatiotemporal analysis reveals events dominated region (23.7% total occurrences), significant intensification 2010–2012 2014–2016 periods. Summer frequency peaked at 12–15 months south-central Shandong (37°N, 117°E) eastern Henan (34°N, 114°E). framework’s high spatial resolution (1 km) validation protocol establish reliable foundation agricultural resource management, offering transferable methodology worldwide.

Language: Английский

Citations

0