REDNET-ML: A Multi-Sensor Machine Learning Pipeline for Harmful Algal Bloom Risk Detection Along the Omani Coast

TL;DR

REDNET-ML presents a comprehensive machine learning pipeline that integrates multi-sensor satellite data and advanced modeling techniques to detect harmful algal bloom risks along the Omani coast, supporting operational decision-making.

Contribution

It introduces a reproducible, multi-sensor fusion pipeline with a novel decision fusion model and rigorous evaluation strategies for HAB risk detection.

Findings

High AUROC and AUPRC scores demonstrate effective detection.

Calibration curves show well-calibrated risk probabilities.

Drift analysis reveals distribution shifts over recent years.

Abstract

Harmful algal blooms (HABs) can threaten coastal infrastructure, fisheries, and desalination dependent water supplies. This project (REDNET-ML) develops a reproducible machine learning pipeline for HAB risk detection along the Omani coastline using multi sensor satellite data and non leaky evaluation. The system fuses (i) Sentinel-2 optical chips (high spatial resolution) processed into spectral indices and texture signals, (ii) MODIS Level-3 ocean color and thermal indicators, and (iii) learned image evidence from object detectors trained to highlight bloom like patterns. A compact decision fusion model (CatBoost) integrates these signals into a calibrated probability of HAB risk, which is then consumed by an end to end inference workflow and a risk field viewer that supports operational exploration by site (plant) and time. The report documents the motivation, related work, methodological choices (including label mining and strict split strategies), implementation details, and a critical evaluation using AUROC/AUPRC, confusion matrices, calibration curves, and drift analyses that quantify distribution shift in recent years.