Fusing Multi- and Hyperspectral Satellite Data for Harmful Algal Bloom Monitoring with Self-Supervised and Hierarchical Deep Learning
We present a self-supervised machine learning framework for detecting and mapping the severity and speciation of harmful algal blooms (HABs) using multi-sensor satellite data. By fusing reflectance data from operational polar-orbiting satellite-based instruments (VIIRS, MODIS, OLCI, and OCI) with TROPOMI solar-induced fluorescence (SIF), our framework, called SIT-FUSE, generates HAB severity and speciation products without requiring per-instrument labeled datasets. The framework employs self-supervised representation learning and hierarchical deep clustering to segment phytoplankton cell abundance and species into interpretable classes, validated against in-situ data from the Gulf of Mexico and Southern California (2018-2025). Results show strong agreement with total phytoplankton, Karena brevis, and Pseudo-nitzschia spp. measurements. This work advances scalable HAB monitoring in environments where ground truth observations are limited, while enabling exploratory analysis via hierarchical embeddings - a critical step toward operationalizing self-supervised learning for global aquatic biogeochemistry.
Code (0)
등록된 구현이 없습니다.
Tasks
Self-Supervised LearningRepresentation LearningDeep ClusteringSimilar Papers 제목 키워드 기반
Predicting Soil Properties from Hyperspectral Satellite Images
The AI4EO HYPERVIEW challenge seeks machine learning methods that predict agriculturally relevant soil parameters (K, Mg, P2O5, pH) from airborne hyperspectral images. We present a hybrid model fusing Random Forest an…
Seeing Beyond the VisibleA Multibranch Convolutional Neural Network for Hyperspectral Unmixing
Hyperspectral unmixing remains one of the most challenging tasks in the analysis of such data. Deep learning has been blooming in the field and proved to outperform other classic unmixing techniques, and can be effective…
Earth ObservationHyperspectral UnmixingPansharpening of PRISMA products for archaeological prospection
Hyperspectral data recorded from satellite platforms are often ill-suited for geo-archaeological prospection due to low spatial resolution. The established potential of hyperspectral data from airborne sensors in identif…
PansharpeningAdvancements in Data Processing and Calibration for the Hyperspectral Imaging Satellite (HySIS)
Hyperspectral imaging is a powerful tool for Earth exploration, allowing for detailed analysis of spectral features. India has launched a dedicated hyperspectral Earth observation satellite capable of capturing data acro…
Earth ObservationImage GenerationSemantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning
Satellites are increasingly adopting on-board AI to optimize operations and increase autonomy through in-orbit inference. The use of Deep Learning (DL) models for segmentation in hyperspectral imagery offers advantages f…
Deep LearningImage SegmentationSegmentationSemantic Segmentation