Fusing Multi- and Hyperspectral Satellite Data for Harmful Algal Bloom Monitoring with Self-Supervised and Hierarchical Deep Learning

2025/10/03 by LaHaye, Nicholas, Luis, Kelly M., Gierach, Michelle M.
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2510.02763

Abstract

We present a self-supervised machine learning framework for detecting and mapping harmful algal bloom (HAB) severity and speciation using multi-sensor satellite data. By fusing reflectance data from operational instruments (VIIRS, MODIS, Sentinel-3, PACE) 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, hierarchical deep clustering to segment phytoplankton concentrations and speciations 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, Karenia brevis, Alexandrium spp., and Pseudo-nitzschia spp. measurements. This work advances scalable HAB monitoring in label-scarce environments while enabling exploratory analysis via hierarchical embeddings: a critical step toward operationalizing self-supervised learning for global aquatic biogeochemistry.

Citations

• Harnessing Self-Supervised Deep Learning and Geostationary Remote Sensing for Advancing Wildfire and Associated Air Quality Monitoring: Improved Smoke and Fire Front Masking using GOES and TEMPO Radiance Data
• Development and Application of Self-Supervised Machine Learning for Smoke Plume and Active Fire Identification from the FIREX-AQ Datasets
• PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• OMNI: Open-endedness via Models of human Notions of Interestingness
• Comparing Foundation Models using Data Kernels
• Micrograph segmentations for DDEVD
• Segment Anything
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
• Gaussian-Bernoulli RBMs Without Tears
• Masked Autoencoders Are Scalable Vision Learners
• Array programming with NumPy
• Bootstrap your own latent: A new approach to self-supervised Learning
• Learnergy: Energy-based Machine Learners
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• SciPy 1.0: fundamental algorithms for scientific computing in Python
• Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
• Invariant Information Clustering for Unsupervised Image Classification\n and Segmentation
• On Calibration of Modern Neural Networks

Related

• AI-driven multi-source data fusion for algal bloom severity classification in small inland water bodies: Leveraging Sentinel-2, DEM, and NOAA climate data
• Seg the HAB: Language-Guided Geospatial Algae Bloom Reasoning and Segmentation
• Toward elucidating accessory pigments in intense phytoplankton blooms using hyperspectral satellite remote sensing in support of harmful algal bloom (HAB) monitoring
• HABNet: Machine Learning, Remote Sensing Based Detection and Prediction of Harmful Algal Blooms
• Variational Autoencoder Framework for Hyperspectral Retrievals (Hyper-VAE) of Phytoplankton Absorption and Chlorophyll a in Coastal Waters for NASA's EMIT and PACE Missions