A hybrid genetic algorithm for multiobjective problems with activity analysis-based local search

Whittaker, Gerald; Confesor, Remegio; Griffith, Stephen M.; Färe, Rolf; Grosskopf, Shawna; Steiner, J. J.; Mueller‐Warrant, George W.; Banowetz, Gary M.

doi:10.1016/j.ejor.2007.10.050

Cited by 67 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Watershed simulation, including simulating the water quality impacts of agricultural conservation practices are handled by the hydrologic model, SWAT2005, coupled with a Windows-based database control system, i_SWAT 6,8 . The optimization component operates on the hydrologic response units (HRUs) of SWAT and employs the logic of an evolutionary algorithm 26 to find the allocation of conservation practices which simultaneously minimizes nutrient loadings (N, P, or both) and the cost of conservation practices. After the algorithm iterations are terminated, a set of surviving individuals represents the approximate tradeoff frontier.…”

Section: Discussionmentioning

confidence: 99%

“…A recent and expanding set of research is attempting to use similar methods and integrates water quality models with broadly defined evolutionary optimization methods 3,4,9,10,[13][14][15][17][18][19]22,23,25 . In this application, we demonstrate a program which follows Rabotyagov et al's approach and integrates a modern and commonly used SWAT water quality model 7 with a multiobjective evolutionary algorithm SPEA2 26 , and user-specified set of conservation practices and their costs to search for the complete tradeoff frontiers between costs of conservation practices and userspecified water quality objectives. The frontiers quantify the tradeoffs faced by the watershed managers by presenting the full range of costs associated with various water quality improvement goals.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Rabotyagov

Campbell

Vâlcu

et al. 2012

JoVE

View full text Add to dashboard Cite

Finding the cost-efficient (i.e., lowest-cost) ways of targeting conservation practice investments for the achievement of specific water quality goals across the landscape is of primary importance in watershed management. Traditional economics methods of finding the lowest-cost solution in the watershed context (e.g., 5,12,20 ) assume that off-site impacts can be accurately described as a proportion of on-site pollution generated. Such approaches are unlikely to be representative of the actual pollution process in a watershed, where the impacts of polluting sources are often determined by complex biophysical processes. The use of modern physically-based, spatially distributed hydrologic simulation models allows for a greater degree of realism in terms of process representation but requires a development of a simulation-optimization framework where the model becomes an integral part of optimization.Evolutionary algorithms appear to be a particularly useful optimization tool, able to deal with the combinatorial nature of a watershed simulationoptimization problem and allowing the use of the full water quality model. Evolutionary algorithms treat a particular spatial allocation of conservation practices in a watershed as a candidate solution and utilize sets (populations) of candidate solutions iteratively applying stochastic operators of selection, recombination, and mutation to find improvements with respect to the optimization objectives. The optimization objectives in this case are to minimize nonpoint-source pollution in the watershed, simultaneously minimizing the cost of conservation practices. A recent and expanding set of research is attempting to use similar methods and integrates water quality models with broadly defined evolutionary optimization methods 3,4,9,10,[13][14][15][17][18][19]22,23,25 . In this application, we demonstrate a program which follows Rabotyagov et al.'s approach and integrates a modern and commonly used SWAT water quality model 7 with a multiobjective evolutionary algorithm SPEA2 26, and user-specified set of conservation practices and their costs to search for the complete tradeoff frontiers between costs of conservation practices and userspecified water quality objectives. The frontiers quantify the tradeoffs faced by the watershed managers by presenting the full range of costs associated with various water quality improvement goals. The program allows for a selection of watershed configurations achieving specified water quality improvement goals and a production of maps of optimized placement of conservation practices. Video LinkThe video component of this article can be found at

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Rabotyagov

Campbell

Vâlcu

et al. 2012

JoVE

View full text Add to dashboard Cite

show abstract

“…In general, EAs belong to a class of stochastic optimization methods and are well suited for approximating solutions to complex combinatorial problems (see, e.g., Deb 2001;Forrest 1993). Optimization methods falling under the broader EA classification have been successfully applied to integrated watershed modeling systems (Srivastava et al 2002;Veith et al 2003;Bekele and Nicklow 2005;Lant et al 2005;Muleta and Nicklow 2005;Arabi et al 2006;Whittaker et al 2007;Jha et al forthcoming;Rabotyagov et al 2010). To our knowledge, this is the first study to investigate the impact of land-use changes exogenous to optimization on the efficient frontier of tradeoffs between multiple water quality objectives (N and P) and the cost of conservation investments.…”

Section: Methodsmentioning

confidence: 99%

Impact of crop rotations on optimal selection of conservation practices for water quality protection

Rabotyagov¹,

Jha²,

Campbell³

2010

Journal of Soil and Water Conservation

View full text Add to dashboard Cite

This research integrates modern multiobjective optimization tools, water quality modeling capability, and data on costs of implementing conservation practices to develop a tradeoff frontier of cost-efficient nonpoint source pollution reduction solutions, which can be used to derive the watershed-level pollution abatement cost curve. Farmers' decisions, both on the intensive and the extensive margin, are likely to affect the shape of the tradeoff frontier as well as the mix of conservation practices selected for achievement of given nutrient reduction goals. In this paper, we wish to explore the consequences of changes in the cropping practices on the intensive margin and changes in the amount of cropland on the extensive margin on the baseline water quality as well as the shape of the tradeoff frontier and the mix of conservation practices. An empirical application focuses on a typical Midwestern agricultural watershed, Squaw Creek watershed in central Iowa. Using detailed crop production budgets, we follow Secchi and Babcock (2007) to demonstrate an alternative land-use scenario, which could arise from recently observed changes in crop prices and production costs. We find that the change in cropping practices effects direct changes in the shape of the tradeoff frontier and the mix and location of conservation practices selected to achieve particular nutrient loading reductions. In particular, we find that a potential shift to more corn (Zea mays L.)-intensive crop rotations and an increase in the amount of cropland in the watershed may lead to increased loadings of both nitrate and phosphorus and that additional conservation investments are required to maintain water quality gains achieved under the baseline (historic) cropping practices. In terms of conservation practices selected, the optimal placement of terraces appears robust to the changes in crop rotations and amount of cropland in the alternative land-use scenario.

show abstract

“…Zhang et al (2009) found GA to perform well compared to other optimization algorithms in the calibration of the SWAT model. Multi-objective GA have been used in the calibration of this model (Bekele and Nicklow, 2007;Whittaker et al, 2007) as well. GA have also been used to calibrate runoff models such as HBV (Seibert, 2000) and TOPSIS (Cheng et al, 2006) as well as crop (Dai et al, 2009) and crop-related models such as SWAP (He et al, 2007).…”

Section: Optimization Methodologymentioning

confidence: 99%

Calibration of a crop model to irrigated water use using a genetic algorithm

Bulatewicz

Jin

Staggenborg

et al. 2009

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Near-term consumption of groundwater for irrigated agriculture in the High Plains Aquifer supports a dynamic bio-socio-economic system, all parts of which will be impacted by a future transition to sustainable usage that matches natural recharge rates. Plants are the foundation of this system and so generic plant models suitable for coupling to representations of other component processes (hydrologic, economic, etc.) are key elements of needed stakeholder decision support systems. This study explores utilization of the Environmental Policy Integrated Climate (EPIC) model to serve in this role. Calibration required many facilities of a fully deployed decision support system: geo-referenced databases of crop (corn, sorghum, alfalfa, and soybean), soil, weather, and water-use data (4931 well-years), interfacing heterogeneous software components, and massively parallel processing (3.8×10 9 model runs). Bootstrap probability distributions for ten model parameters were obtained for each crop by entropy maximization via the genetic algorithm. The relative errors in yield and water estimates based on the parameters are analyzed by crop, the level of aggregation (county-or well-level), and the degree of independence between the data set used for estimation and the data being predicted.

show abstract

A hybrid genetic algorithm for multiobjective problems with activity analysis-based local search

Cited by 67 publications

References 20 publications

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Impact of crop rotations on optimal selection of conservation practices for water quality protection

Calibration of a crop model to irrigated water use using a genetic algorithm

Contact Info

Product

Resources

About