Improving Oil Slick Trajectory Simulations with Bayesian Optimization

2025-03-04

AI Summary

Oil spill trajectory modeling suffers from low accuracy and poor adaptability due to reliance on expert knowledge and manual parameter tuning. Method: This study proposes a Bayesian optimization–based automatic parameter inversion framework, systematically integrated with the MEDSLIK-II numerical model for the first time. Horizontal diffusion coefficient and drift factor are optimized against satellite remote sensing observations, using the Fraction Skill Score (FSS) as the objective function to enable dynamic, adaptive calibration. Contribution/Results: The method eliminates manual intervention and significantly enhances model robustness and generalizability under complex marine conditions. Validated against the 2021 Baniyas oil spill incident in Syria, it increased the mean FSS from 5.82% to 11.07%, markedly improving temporal consistency—particularly during phases of rapid drift variation.

Technology Category

• Search and Optimization: Algorithm Configuration
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Bayesian Learning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate simulations of oil spill trajectories are essential for supporting practitioners' response and mitigating environmental and socioeconomic impacts. Numerical models, such as MEDSLIK-II, simulate advection, dispersion, and transformation processes of oil particles. However, simulations heavily rely on accurate parameter tuning, still based on expert knowledge and manual calibration. To overcome these limitations, we integrate the MEDSLIK-II numerical oil spill model with a Bayesian optimization framework to iteratively estimate the best physical parameter configuration that yields simulation closer to satellite observations of the slick. We focus on key parameters, such as horizontal diffusivity and drift factor, maximizing the Fraction Skill Score (FSS) as a measure of spatio-temporal overlap between simulated and observed oil distributions. We validate the framework for the Baniyas oil incident that occurred in Syria between August 23 and September 4, 2021, which released over 12,000 $m^3$ of oil. We show that, on average, the proposed approach systematically improves the FSS from 5.82% to 11.07% compared to control simulations initialized with default parameters. The optimization results in consistent improvement across multiple time steps, particularly during periods of increased drift variability, demonstrating the robustness of our method in dynamic environmental conditions.

Problem

• Improving oil spill trajectory simulations using Bayesian optimization.
• Automating parameter tuning for accurate oil spill modeling.
• Enhancing simulation accuracy with satellite observation integration.

Innovation

• Integrates MEDSLIK-II with Bayesian optimization
• Estimates optimal physical parameters iteratively
• Improves simulation accuracy using satellite data