Remote Sensing, GIS and Machine Learning for Agricultural Drought Intelligence: Evidence from California, Northern Nigeria and Rajasthan

Abstract: Agricultural drought remains one of the most significant environmental challenges affecting food security, water resource availability, and agricultural productivity, particularly in semi-arid regions. Recent advances in remote sensing, Geographic Information Systems (GIS), and machine learning have provided innovative approaches for monitoring, predicting, and managing drought conditions with greater spatial and temporal accuracy. This study evaluates the effectiveness of integrating remote sensing, GIS, and machine learning techniques for agricultural drought intelligence using evidence from California (United States), Northern Nigeria, and Rajasthan (India). A quantitative research design based on secondary data was adopted, utilizing Landsat and MODIS satellite imagery, meteorological records, vegetation indices, and geospatial datasets published up to 2018. Descriptive statistics, correlation analysis, multiple regression, and machine learning algorithms, including Random Forest and Support Vector Machine, were employed to assess drought detection and prediction performance. The findings indicate that integrating remote sensing with GIS significantly enhances drought monitoring, while machine learning algorithms improve prediction accuracy by effectively analyzing complex environmental datasets. Comparative analysis further reveals regional differences in drought severity, technological capacity, and environmental conditions, highlighting the importance of location-specific drought management strategies. The study concludes that combining remote sensing, GIS, and machine learning provides a reliable framework for agricultural drought intelligence, supporting evidence-based decision-making, sustainable water resource management, and climate-resilient agricultural planning in drought-prone regions.

Keywords: Agricultural drought, Remote sensing, Geographic Information Systems (GIS), Machine learning, Precision agriculture, Landsat, MODIS.