Floods from space: How remote sensing, AI, and cloud platforms are reshaping Disaster Risk Reduction

This review addresses the need for a systematic and decision-oriented synthesis of how space-borne remote sensing has evolved toward integrated flood monitoring and disaster risk reduction frameworks. Moving beyond conventional sensor inventories, the study examines sensor integration pathways, temporal evolution, and decision relevance. Four research questions guide the analysis: (RQ1) how space-borne sensors have been applied and advanced in flood studies, (RQ2) how multi-sensor fusion architectures have evolved, (RQ3) what limitations persist, and (RQ4) what future directions are emerging. Following PRISMA guidelines, 176 peer-reviewed studies published between 2001 and 2024 were systematically analysed.

Quantitative synthesis indicates a marked post-2018 increase in multi-sensor approaches, alongside a growing share of studies adopting fusion frameworks. Synthetic Aperture Radar (SAR)-centred integration systems represent a dominant share of recent applications; most commonly combined with precipitation products and digital elevation models. Analytical synthesis further indicates that SAR plays a central role in flood detection, while precipitation and topographic data provide key hydrological drivers and terrain constraints. These findings indicate a transition from static flood mapping toward process-aware, multi-sensor, and algorithm-driven flood intelligence systems. The review also highlights the growing role of artificial intelligence and cloud-based platforms in enabling scalable, near-real-time flood analysis. It concludes that future flood resilience increasingly depends on the coordinated integration of space-borne observations, advanced analytics, and operational decision-support architectures. This synthesis provides a unifying framework to guide next-generation flood monitoring and disaster risk reduction under accelerating climate change.