EventsThe 2nd International Online Conference on Marine Science and Engineering
Published
This submission belongs to the session S5. Marine Environmental Science and Pollution of the event The 2nd International Online Conference on Marine Science and Engineering
Published date
18 Nov, 2026
Academic Editor
author-avatarGiuseppe Suaria
Citation
Fahim Sufi, Interpretable AI for Global Ocean Health Forecasting and Marine Environmental Risk Stratification Using the Ocean Health Index, in Proceedings of The 2nd International Online Conference on Marine Science and Engineering, 23 November–25 November 2026, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

Interpretable AI for Global Ocean Health Forecasting and Marine Environmental Risk Stratification Using the Ocean Health Index

image
1. Office of CTO, COEUS Institute, New Market, VA 22844, USA
Abstract

Introduction:
Marine environmental assessment increasingly requires predictive and policy relevant tools that can move beyond static index reporting. Although the Ocean Health Index has become an influential framework for measuring marine ecosystem condition and human ocean benefits, its longitudinal structure remains underused for forecasting, risk stratification, and management diagnostics. This study develops an interpretable artificial intelligence framework for modelling global ocean health trajectories and identifying vulnerable marine systems.

Methods:
The study analyses 341,124 Ocean Health Index score observations covering 220 coastal countries and territories, 19 goals or subgoals, six score dimensions, and 14 annual assessments from 2012 to 2025. The framework integrates data harmonisation, longitudinal trajectory modelling, K means country grouping, trajectory based risk stratification, Random Forest next year forecasting, feature importance analysis, and country specific policy diagnostics. Forecasting was conducted using goal and dimension level predictors, while the overall Index score was excluded from the predictor set to avoid circular prediction.

Results:
The global Ocean Health Index increased from 71.85 in 2012 to 74.94 in 2019, declined sharply to 69.50 in 2024, and partially recovered to 72.31 in 2025, remaining 2.63 points below its 2019 level. Goal level change was highly uneven, with Tourism and Recreation declining by 12.42 points, while Natural Products and Lasting Special Places increased by 7.67 and 7.38 points, respectively. Country trajectory clustering identified two regimes with mean 2025 Index scores of 65.07 and 74.47, separated by 9.40 points. Risk stratification classified 51 countries and territories as low risk, 98 as moderate risk, and 71 as high risk. The Random Forest model predicted next year OHI scores with R² = 0.723, MAE = 3.07, and RMSE = 4.03, identifying Habitat, Carbon Storage, and Fisheries as the strongest predictors of future ocean health.

Conclusions:
This study demonstrates that Ocean Health Index data can support interpretable AI based marine environmental intelligence. By linking trajectory dynamics, forecast accuracy, risk classes, and policy diagnostics, the framework offers a scalable decision support approach for ocean sustainability assessment, marine environmental management, and prioritisation of vulnerable coastal systems

Keywords
Ocean Health Forecasting
Marine Environmental Risk Stratification
Interpretable Artificial Intelligence
Ocean Health Index
Marine Sustainability Analytics
Coastal System Decision Support
Macroalgae as Bioindicators of Trace Element Contamination and Microplastic Entrapment in the Cape Peloro Lagoon Complex (Messina, Italy)
A Reliability-Oriented Perception, Decision-Making, and Control Architecture for Autonomous Surface Vehicles under Competition Constraints: An Experimental Validation Study