You are here:
Handling Practicalities in Agricultural Policy Optimization for Water Quality Improvements
Citation:
Barnhart, B., Z. Wu, M. Bostian, A. Sinha, K. Deb, L. Kurkalova, M. Jha, AND G. Whittaker. Handling Practicalities in Agricultural Policy Optimization for Water Quality Improvements. In Proceedings, The Genetic and Evolutionary Computation Conference (GECCO), Berlin, N/A, GERMANY, July 15 - 19, 2017. Association for Computing Machinery (ACM), New York, NY, 1065-1072, (2017).
Impact/Purpose:
This conference paper is for the 2017 Genetic and Evolutionary Computation Conference in Berlin, Germany, July 15-19, 2017, where we will participate in a meeting consisting of computer optimization specialists, academics, and practitioners who are interested in multiobjective optimization, genetic algorithms and computer programming. Our paper and presentation, which is submitted within the “Real-World Applications” track, will compare different genetic algorithms used for optimizing a simple agricultural policy problem to improve water quality using targeted agricultural incentives. This serves as preliminary work to determine the best optimization algorithms to use when targeting agricultural incentives amidst multiple conflicting objectives. Our discussion on robust policies may also be relevant to a wider audience (e.g., policy makers), since we show that robust policy results can be achieved at the expense of individual objectives. This work relates to RAP task SSWR5.01A: Green Infrastructure Model Research.
Description:
Bilevel and multi-objective optimization methods are often useful to spatially target agri-environmental policy throughout a watershed. This type of problem is complex and is comprised of a number of practicalities: (i) a large number of decision variables, (ii) at least two inter-dependent levels of optimization between policy makers and policy followers, and (iii) uncertainty in decision variables and problem parameters. Given agricultural and economic data from the Raccoon watershed in central Iowa, we formulate a bilevel multi-objective optimization problem that accommodates objectives of both policy makers and farmers. The solution procedure then explicitly accounts for the nested nature of farm-level management decisions in response to agri-environmental policy incentives constructed by policy makers. We specifically examine the spatial targeting of a fertilizer-reduction incentive policy while seeking to maximize farm-level productivity while generating mandated water quality improvements using this framework. We test three different evolutionary optimization algorithms – m-BLEAQ, NSGA-II, and SPEA2 – and show that m-BLEAQ is well suited for handling the bilevel optimization problems and the considered practicalities.
