Scholarlink

<p>The effect of land cover changes on annual peak discharge is evaluated using a novel method combining principal component analysis (PCA) and random forest regression (RF). This approach calculates original feature contributions by multiplying absolute PCA loadings with RF-derived component importances, enabling direct attribution of discharge variations to specific land cover types in each subbasin, which represents an integration unexplored in prior PCA–RF applications. The PCA–RF method is applied in the basin upstream of Golestan Dam, Iran. It uses multitemporal Landsat imagery for NDVI-based land cover classification, annual instantaneous peak discharge data from hydrometric stations, and elevation data for subbasin delineation over a limited period (post-2003, due to data constraints). Despite limitations like scarce hydrometric data and a short collection period, the method analyzes relationships between land cover classes and floods in subbasins. Remote sensing provides spatial vegetation patterns, organized via GIS; PCA reduces dimensionality and identifies key factors; RF models nonlinear relationships with high accuracy (<i>R</i><sup>2</sup> 0.78–0.90, per SHAP insights). Quantitatively, urban/barren lands dominated in Tangerah (26.3%) and Hajji Qushan (30.9%) and thin vegetation in Galikash (26.9%) and Tamar Gorgan (26.8%), with dense vegetation lowest in Hajji Qushan (2%). Findings confirm land cover changes significantly impact flood peaks, varying spatially: Urban/barren lands accelerate runoff, and vegetation mitigates it. The PCA–RF method captures these dynamics despite constraints and offers policymakers insights for flood risk reduction, vegetation restoration, urban runoff control, sustainable management, and adaptive planning. Furthermore, this work provides insights into the interactions between land cover changes and flood risks that assist policymakers and land managers in developing effective strategies for flood risk reduction, water resource management, and sustainable use practices.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Assessing land cover change impact on peak discharge using principal component analysis and random forest with remote sensing data assimilation

  • 期刊论文

  • 发表日期：

    2026年8月3日

查看全文
  • Seyed-Mahdi Salar-Khorasani,
  • Omid Bozorg-Haddad,
  • Hugo A. Loáiciga

摘要

The effect of land cover changes on annual peak discharge is evaluated using a novel method combining principal component analysis (PCA) and random forest regression (RF). This approach calculates original feature contributions by multiplying absolute PCA loadings with RF-derived component importances, enabling direct attribution of discharge variations to specific land cover types in each subbasin, which represents an integration unexplored in prior PCA–RF applications. The PCA–RF method is applied in the basin upstream of Golestan Dam, Iran. It uses multitemporal Landsat imagery for NDVI-based land cover classification, annual instantaneous peak discharge data from hydrometric stations, and elevation data for subbasin delineation over a limited period (post-2003, due to data constraints). Despite limitations like scarce hydrometric data and a short collection period, the method analyzes relationships between land cover classes and floods in subbasins. Remote sensing provides spatial vegetation patterns, organized via GIS; PCA reduces dimensionality and identifies key factors; RF models nonlinear relationships with high accuracy (R2 0.78–0.90, per SHAP insights). Quantitatively, urban/barren lands dominated in Tangerah (26.3%) and Hajji Qushan (30.9%) and thin vegetation in Galikash (26.9%) and Tamar Gorgan (26.8%), with dense vegetation lowest in Hajji Qushan (2%). Findings confirm land cover changes significantly impact flood peaks, varying spatially: Urban/barren lands accelerate runoff, and vegetation mitigates it. The PCA–RF method captures these dynamics despite constraints and offers policymakers insights for flood risk reduction, vegetation restoration, urban runoff control, sustainable management, and adaptive planning. Furthermore, this work provides insights into the interactions between land cover changes and flood risks that assist policymakers and land managers in developing effective strategies for flood risk reduction, water resource management, and sustainable use practices.