Meteorological Drought Forecast using Deep Learning and Ensemble Machine Learning: A systematic review literature

Abstract

Meteorological drought is commonly defined as a prolonged deficiency in precipitation relative to the climatological norm for a given region. However, limitations in robustly quantifying and monitoring drought severity continue to impede decision-making across multiple sectors. Conventional tools, have exhibited substantial limitations in terms of accuracy, spatial–temporal resolution, and generalizability. This paper presents a systematic literature review (SLR) focusing on emerging applications of machine learning (ML) and deep learning (DL) to prediction and monitoring meteorological drought, conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol. An initial pool of 79 peer-reviewed articles published between 2021 and 2025 were identified. The review process examined the articles based on predefined inclusion and exclusion criteria, 19 studies were ultimately retained for detailed analysis. Quality assessment scores for these studies ranged from 71.4% to 100%. The review highlights the increasing use of hybrid ML and DL models, which combine modeling paradigms, as an effective strategy to improve drought forecasting performance, exhibit strong predictive capabilities and offer a compelling alternative to traditional single-model approaches.