Using a genetic algorithm to improve oil spill prediction. (October 2018)

• Record Type: Journal Article
• Authors: Guo, Weijun; Jiang, Meirong; Li, Xueyan; Ren, Bing
• Is Part Of: Marine pollution bulletin. Volume 135(2018)
• Page Start: 386
• Page End: 396
• Publication Date: 2018-10
• Subjects: Oil spill -- Model evaluation -- Parameter optimisation -- Genetic algorithm; Marine pollution -- Periodicals; Marine Biology -- Periodicals; Water Pollution -- Periodicals; Mer -- Pollution -- Périodiques; Publications périodiques; Pollution des mers; Lutte antipollution; Electronic journals; 363.7394
• DOI: 10.1016/j.marpolbul.2018.07.026
• Languages: English
• ISSNs: 0025-326X

Abstract

Abstract: The performance of oil spill models is strongly influenced by multiple parameters. In this study, we explored the ability of a genetic algorithm (GA) to determine optimal parameters without the need for time-consuming manual attempts. An evaluation function integrating the percentage of coincidence between the predicted polluted area and the observed spill area was proposed for measuring the performance of a Lagrangian oil particle model. To maximise the objective function, the oil spill was run numerous times with continuously optimised parameters. After many generations, the GA effectively reduced discrepancies between model results and observations of a real oil spill. Subsequent validation indicated that the oil spill model predicted oil slick patterns with reasonable accuracy when equipped with optimal parameters. Furthermore, multiple objective optimisation for observations at different times contributed to better model performance. Graphical abstract: Genetic Algorithm is capable in seeking optimal parameters for oil spill simulation. Highlights: A formula is presented for evaluating the prediction performance of oil spill models. Genetic algorithm adoption improves the accuracy of oil spill model simulations. Optimal parameters and multi-objective optimisation improve prediction accuracy.