Flood Mapping Using Google Earth Engine (GEE): A Short Review

Flood Mapping, a core application in disaster management and mitigation, is a useful tool for environmental monitoring, flood risk, and flood resilience. Open satellite archives and cloud computing now enable timely, basin-to-nation-scale inundation products. Google Earth Engine (GEE), a cloud-based Geospatial platform, provides unique capabilities in large-scale and real-time flood analysis, supports flood detection and monitoring using optical (Sentinel-2, Landsat) and synthetic aperture radar (Sentinel-1) data. GEE has lowered the operational and technical barriers to flood mapping by collocating global archives and scalable computation. Simple, transparent baselines—adaptive thresholds and change detection—remain powerful starting points, especially when combined with topography-aware masks and morphological cleanup. Machine learning and deep learning deliver gains in complex settings when supported by representative labels and sound validation. This review chapter delivers various flood mapping methodologies including flood change identification, machine learning and thresholding techniques, multi-sensor data integration, and time-series analysis in GEE and its capacity for integrating diverse satellite and hydrological data and summarize practical preprocessing on GEE (cloud/shadow masking, radiometric calibration, speckle mitigation, orbit filtering), feature construction (NDWI/MNDWI, VV/VH ratios, coherence, textures), and post-processing (topography-aware masks and morphological filters). Validation design is treated explicitly, including stratified sampling, spatial cross-validation, confusion-matrix reporting (Precision, Recall, F1/IoU), and strategies for class imbalance. Case studies from 2019 to 2022 of the GEE application in flood mapping in the diverse geographical contexts are highlighted. Exploring numerous literatures, this paper discusses challenges and limitations such as data quality issues, computational constraints, and points out potential gaps, and covers a broad discussion on technological advancement and interdisciplinary collaboration of Artificial Intelligence for the precision and efficacy of flood mapping. Summarizing this chapter signifies the perspective of GEE in ongoing research and inducing emergency operations, risk assessment, and long-term resilience planning across diverse geographies.