AI-Driven Multi-Sensor Earth Observation for Water Quality and Aquatic Ecosystem Monitoring

Water ecosystems face mounting pressure from climate change, land-use change, pollution, and overuse, threatening water security and ecosystem health worldwide. Earth observation now offers an unprecedented ability to track these changes, but progress is limited by two persistent challenges: fusing heterogeneous data sources (optical, SAR, hyperspectral, UAV) that differ in resolution and revisit frequency, and building AI models that are accurate, transferable across sites, and interpretable enough to support real management decisions.This Research Topic focuses on methods that combine multi-sensor data fusion with AI to monitor water quality and aquatic ecosystem dynamics at operational scale. We welcome studies that pair remote sensing with in-situ data, address model transferability across regions or seasons, or use explainable AI to build trust in automated water assessments.Topics of interest include:Water quality retrieval (optically and non-optically active constituents, harmful algal blooms) combining in-situ and remote sensing dataMulti-source data fusion (optical, SAR, hyperspectral, thermal, UAV) for water quality or aquatic vegetation mappingExplainable AI and uncertainty quantification for water-related classification and detection tasksTime-series and long-term monitoring of water quality or ecosystem change using cloud-based geospatial platformsDetection of submerged/invasive aquatic vegetation and coastline dynamics using AI-based approaches Topic editors: Nur Yagmur Aydin, Alejandro Román Vázquez, Susana Flecha, Filiz Bektas Balcik Source: https://www.frontiersin.org/research-topics/83470/ai-driven-multi-sensor-earth-observation-for-water-quality-and-aquatic-ecosystem-monitoring