<p>Agricultural drought occurs when soil moisture is insufficient to meet the specific requirements of a given crop during its growth stage, resulting in reduced crop health and yield. Advanced geospatial techniques can effectively monitor and model the spatiotemporal dynamics of agricultural droughts using multiple satellite data products and machine learning (ML) methods, which are accurate, cost-effective, and transferable across space and time. In this study, we comprehensively synthesize the contributions of multi-source remote sensing data and artificial intelligence (AI) approaches (including machine learning and deep learning (DL)) for monitoring, evaluating, and modelling agricultural drought. Additionally, we comprehensively reviewed the latest developments in time-series satellite data analysis, remote-sensing spectral indices, and numerical models used worldwide for rapid, accurate drought monitoring and modeling. Moreover, we critically examined several case studies of drought assessment using ML/DL coupled with satellite data, multi-parametric datasets, and ground-based data to monitor agricultural droughts at local and regional scales and for prediction modelling, owing to their ability to handle complex, non-linear, and large-scale datasets effectively. Overall, big data analytics has great potential for monitoring and assessing agricultural drought using multi-source satellite data, combined with ensemble, hybrid, and physics-based machine learning and deep learning approaches. The review offers a solid theoretical framework and a comprehensive summary of advanced geospatial and ML approaches used for agricultural drought monitoring and modeling, which can be utilized by decision-makers, policy planners, and research organizations to inform policies related to sustainable and climate-smart agriculture.</p>