Scholarlink

<p>Agricultural drought poses a persistent threat to food security in Katsina State, a semiarid region of northern Nigeria, yet the relative contributions of thermal stress and moisture deficit to vegetation health remain poorly understood. In this study, spatiotemporal agricultural drought dynamics from 2000 to 2025 were assessed using the vegetation health index (VHI), integrating MODIS-derived NDVI and land surface temperature (LST), CHIRPS rainfall, ERA5-Land soil moisture, and SRTM topographic data. A random forest regression model, interpreted with SHAP values, was employed to quantify the influence of biophysical drivers on vegetation health. The results indicate severe drought conditions in the early 2000s, with marked improvement after 2015 associated with lower thermal stress and improved vegetation conditions. The model demonstrated strong predictive performance (R<sup>2</sup> = 0.89; root mean square error (RMSE) = 8.29), identifying the LST as the dominant predictor of the VHI (59.3%), whereas rainfall exerted weaker direct effects (14.9%), reflecting the mediating role of soil moisture and temperature interactions in this semiarid system. These results suggest that early warning and adaptation strategies for drought in semiarid northern Nigeria should prioritize thermal stress indicators alongside conventional rainfall metrics.</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

Spatiotemporal Assessment of Agricultural Drought in Semiarid Northern Nigeria Using MODIS Data and Explainable Random Forest (2000–2025)

  • 期刊论文

  • 发表日期：

    2026年7月14日

查看全文
  • Muhammad Lawal Abubakar,
  • Asmau M. Ahmed,
  • Sidikatu Aliyu,
  • Saadatu Umaru Baba,
  • Muhammad Sambo Ahmed,
  • Khalid Ibrahim Richifa

摘要

Agricultural drought poses a persistent threat to food security in Katsina State, a semiarid region of northern Nigeria, yet the relative contributions of thermal stress and moisture deficit to vegetation health remain poorly understood. In this study, spatiotemporal agricultural drought dynamics from 2000 to 2025 were assessed using the vegetation health index (VHI), integrating MODIS-derived NDVI and land surface temperature (LST), CHIRPS rainfall, ERA5-Land soil moisture, and SRTM topographic data. A random forest regression model, interpreted with SHAP values, was employed to quantify the influence of biophysical drivers on vegetation health. The results indicate severe drought conditions in the early 2000s, with marked improvement after 2015 associated with lower thermal stress and improved vegetation conditions. The model demonstrated strong predictive performance (R2 = 0.89; root mean square error (RMSE) = 8.29), identifying the LST as the dominant predictor of the VHI (59.3%), whereas rainfall exerted weaker direct effects (14.9%), reflecting the mediating role of soil moisture and temperature interactions in this semiarid system. These results suggest that early warning and adaptation strategies for drought in semiarid northern Nigeria should prioritize thermal stress indicators alongside conventional rainfall metrics.