Using a genetic algorithm to improve oil spill prediction.

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.

[1]  M. Spaulding.  State of the art review and future directions in oil spill modeling. , 2017, Marine pollution bulletin.

[2]  I. Fujita,et al.  In situ estimates of horizontal turbulent diffusivity at the sea surface for oil transport simulation. , 2017, Marine pollution bulletin.

[3]  K Schroeder,et al.  A high-resolution real-time forecasting system for predicting the fate of oil spills in the Strait of Bonifacio (western Mediterranean Sea). , 2012, Marine pollution bulletin.

[4]  Avi Ostfeld,et al.  State of the Art for Genetic Algorithms and Beyond in Water Resources Planning and Management , 2010 .

[5]  Paul D. Bates,et al.  Assessing the uncertainty in distributed model predictions using observed binary pattern information within GLUE , 2002 .

[6]  Stephen P. Murray,et al.  TURBULENT DIFFUSION OF OIL IN THE OCEAN1 , 1972 .

[7]  Randy L. Haupt,et al.  Practical Genetic Algorithms , 1998 .

[8]  G. Georgiou,et al.  Hindcast of oil-spill pollution during the Lebanon crisis in the Eastern Mediterranean, July-August 2006. , 2011, Marine pollution bulletin.

[9]  M. Reed,et al.  Oil Spill Modeling towards the Close of the 20th Century: Overview of the State of the Art , 1999 .

[10]  W. J. Guo,et al.  A numerical oil spill model based on a hybrid method. , 2009, Marine pollution bulletin.

[11]  Ming-xiao Xie,et al.  The influence of surface wave on water exchange in the Bohai Sea , 2016 .

[12]  Martin Volk,et al.  Input variable selection with a simple genetic algorithm for conceptual species distribution models: A case study of river pollution in Ecuador , 2017, Environ. Model. Softw..

[13]  N. Jothi Shankar,et al.  Two- and three-dimensional oil spill model for coastal waters , 2001 .

[14]  Roger Proctor,et al.  Modelling tides and surface drift in the Arabian Gulf—application to the Gulf oil spill , 1994 .

[15]  Judith Helgers,et al.  Surface evolution of the deepwater horizon oil spill patch: combined effects of circulation and wind-induced drift. , 2012, Environmental science & technology.

[16]  Akira Okubo,et al.  Oceanic diffusion diagrams , 1971 .

[17]  E. Owens,et al.  DEVELOPMENT OF A STRANDED OIL IN COARSE SEDIMENT (SOCS) MODEL , 1993 .

[18]  Helga S. Huntley,et al.  Surface Drift Predictions of the Deepwater Horizon Spill: The Lagrangian Perspective , 2013 .

[19]  Serguei A. Lonin,et al.  Lagrangian Model for Oil Spill Diffusion at Sea , 1999 .

[20]  Poojitha D. Yapa,et al.  OIL SLICK TRANSPORT IN RIVERS , 1988 .

[21]  Norden E. Huang,et al.  An oilspill trajectory analysis model with a variable wind deflection angle , 1982 .

[22]  N. Booij,et al.  A third-generation wave model for coastal regions-1 , 1999 .

[23]  B. Hodges,et al.  Operational Oil Spill Modelling: From Science to Engineering Applications in the Presence of Uncertainty , 2015 .

[24]  Xiao-zhong Ren,et al.  Development and application of an oil spill model with wave-current interactions in coastal areas. , 2014, Marine pollution bulletin.

[25]  António M. Baptista,et al.  SELFE: A semi-implicit Eulerian–Lagrangian finite-element model for cross-scale ocean circulation , 2008 .

[26]  C. E. Sweeney,et al.  Natural dispersion of oil , 1988 .

[27]  R. M. Mamedov,et al.  Particle tracking method in the approach for prediction of oil slick transport in the sea: modelling oil pollution resulting from river input , 2004 .

[28]  Jining Chen,et al.  Oil spill forecast model based on uncertainty analysis: A case study of Dalian Oil Spill , 2012 .

[29]  O. Phillips.  The dynamics of the upper ocean , 1966 .

[30]  Holger R. Maier,et al.  A genetic algorithm calibration method based on convergence due to genetic drift , 2008, Inf. Sci..

[31]  null null,et al.  State-of-the-Art Review of Modeling Transport and Fate of Oil Spills , 1996 .

[32]  H. Ducklow.  Chesapeake Bay nutrient and plankton dynamics. 1. Bacterial biomass and production during spring tidal destratification in the York River, Virginia, estuary1,2 , 1982 .

[33]  Pavlo Tkalich,et al.  Vertical mixing of oil droplets by breaking waves. , 2002, Marine pollution bulletin.

[34]  Mark Reed,et al.  The physical fates component of the natural resource damage assessment model system , 1989 .

[35]  W. J. Guo,et al.  Modeling oil spill trajectory in coastal waters based on fractional Brownian motion. , 2009, Marine pollution bulletin.

[36]  N. Jothi Shankar,et al.  Development and Application of Oil Spill Model for Singapore Coastal Waters , 2003 .