IAAA Finalists

Authors: Jean Pauphilet & Baizhi Song (London Business School), Yannick Pham & Bruno Sainte–Rose (The Ocean Cleanup), Dick den Hertog (University of Amsterdam) 

Increasing ocean plastic pollution is irreversibly harming ecosystems and human economic activities. We developed advanced predictive and prescriptive analytics methods to help The Ocean Cleanup to remove the plastic from the oceans faster. Specifically, we optimize the route of their plastic collection system in the ocean to maximize the quantity of plastic collected over time. For the input for the optimization method, we developed a suite of models to estimate the dispersion and density of plastic in the Great Pacific Garbage Patch, by using hindcast and forecast models of ocean currents, waves, and wind. The dispersion model uses fluid dynamics to simulate the transport of floating plastics in a time-dependent manner and is calibrated using empirical data. We formulate the problem as a longest path problem in a well-structured graph. However, because collection directly impacts future plastic density, the corresponding edge lengths are nonlinear polynomials. After analyzing the structural properties of the edge lengths, we propose a search-and-bound method, which leverages a relaxation of the problem solvable via dynamic programming and clustering, to efficiently find high-quality solutions (within 6% optimal in practice) and develop a tailored branch-and-bound strategy to solve it to provable optimality. On one year of ocean data, our optimization-based routing approach increases the quantity of plastic collected by more than 60% compared with the current routing strategy, hence speeding up the progress toward plastic-free oceans. Recently, the CEO of The Ocean Cleanup estimated that this innovative analytics methodology halves the time needed to clean up the ocean to 5 years, and nearly halves the costs to 4 billion dollars.