AI-driven multi-source data fusion for algal bloom severity classification in small inland water bodies: Leveraging Sentinel-2, DEM, and NOAA climate data
Ioannis Nasios
TL;DR
This work presents a multi-source data fusion framework for classifying cyanobacterial bloom severity in inland waters by combining Sentinel-2 optical imagery, Copernicus DEM, and NOAA HRRR climate data via Google Earth Engine and Microsoft Planetary Computer. It employs a trio of models—Random Forest, LightGBM, and a neural network with image, climate-timeseries, and tabular submodels—whose predictions are ensembled and mapped to severity through an optimization step. The approach achieves competitive region-based RMSE on the private leaderboard, with key findings showing the strong value of NIR/SWIR Sentinel-2 bands, DEM altitude, and climatological features, and demonstrates the benefit of fusing diverse data sources and AI paradigms. While effective within the U.S. context, the work discusses global applicability and proposes a monitoring system capable of live updates and alerting for high-severity blooms.
Abstract
Harmful algal blooms are a growing threat to inland water quality and public health worldwide, creating an urgent need for efficient, accurate, and cost-effective detection methods. This research introduces a high-performing methodology that integrates multiple open-source remote sensing data with advanced artificial intelligence models. Key data sources include Copernicus Sentinel-2 optical imagery, the Copernicus Digital Elevation Model (DEM), and NOAA's High-Resolution Rapid Refresh (HRRR) climate data, all efficiently retrieved using platforms like Google Earth Engine (GEE) and Microsoft Planetary Computer (MPC). The NIR and two SWIR bands from Sentinel-2, the altitude from the elevation model, the temperature and wind from NOAA as well as the longitude and latitude were the most important features. The approach combines two types of machine learning models, tree-based models and a neural network, into an ensemble for classifying algal bloom severity. While the tree models performed strongly on their own, incorporating a neural network added robustness and demonstrated how deep learning models can effectively use diverse remote sensing inputs. The method leverages high-resolution satellite imagery and AI-driven analysis to monitor algal blooms dynamically, and although initially developed for a NASA competition in the U.S., it shows potential for global application. The complete code is available for further adaptation and practical implementation, illustrating the convergence of remote sensing data and AI to address critical environmental challenges (https://github.com/IoannisNasios/HarmfulAlgalBloomDetection).