Deploying AI-Driven Predictive Modeling and Blockchain Traceability for Climate-Resilient Small-Scale Fisheries in the Western Indian Ocean

Objective: Small-scale fisheries in the Western Indian Ocean face severe threats from climate-induced fish migration and Illegal, Unreported, and Unregulated (IUU) fishing. This study develops an operational framework combining Artificial Intelligence (AI) and blockchain technology to secure the climate resilience, data accuracy, and economic sovereignty of coastal small-scale fishing communities.

Methodology: The framework integrated satellite remote sensing data (Sea Surface Temperature and Chlorophyll-a anomalies) with localized catch metrics from Kenyan Beach Management Units (BMUs). Machine learning models predicted shifting pelagic fish distributions caused by Indian Ocean Dipole fluctuations. Concurrently, a decentralized Hyperledger blockchain architecture was deployed via a mobile application to record catches at the first point of landing, establishing an immutable digital chain of custody.

Results: The AI predictive models forecasted localized fish migrations with an 88% accuracy rate, allowing BMUs to optimize fuel efficiency and safety at sea. On the supply chain front, the blockchain ledger successfully eliminated intermediate documentation fraud, providing total catch transparency. This digital verification reduced IUU vulnerabilities and enabled small-scale fishers to capture a 22% price premium by directly accessing verified, "blue-certified" premium domestic and export markets.

Conclusion: Fusing predictive machine learning with decentralized ledger systems offers a powerful socio-ecological solution for data-poor, climate-vulnerable fisheries. This technological integration replaces slow, legacy data methods with actionable analytics. It provides KMFRI and regional management authorities with a scalable blueprint to advance sustainable marine resource management, enforce seafood traceability, and de-risk blue economy livelihoods across East Africa.