Leveraging Machine Learning and Earth Observation for Agricultural Drought Propagation in North-Central Nigeria

Drought has become a major threat among extreme weather events impacting ecosystems, the economy, food production, and livelihoods. Since the beginning of this century, it has significantly affected Nigeria's economy by reducing agricultural productivity and internally generated revenue. In Northern Nigeria, the shift from meteorological to agricultural drought has not been adequately monitored, particularly concerning future predictions using Artificial Intelligence (AI) and Remote Sensing (RS) methods. Therefore, this study employs AI and EO techniques to analyse and forecast the spatiotemporal dynamics of agricultural drought propagation in North-Central Nigeria from 2000 to 2024. The Vegetation Condition Index (VCI), the Temperature Condition Index (TCI), the Temperature Vegetation Drought Index (TVDI), and the Standardized Precipitation Evapotranspiration Index (SPEI) were used to evaluate vegetation health, temperature variation, and drought severity during the study period. For the machine learning component, Gradient Boosting Regressor was used to predict drought events over five years using cross-validation methods. This study confirms persistent drought events in 2011, 2015, and 2022, with the propagation of meteorological to agricultural drought in 2015, as indicated by VCI, TCI, and TVDI. The integration of AI and EO approaches for drought propagation assessment could enhance climate resilience efforts (SDGs 2, 13 & 15) and provide a framework for drought mitigation strategies in regions prone to drought recurrence, including the study area.