TY - CONF
T1 - Multiobjective evolutionary optimization for quantifying corn yield and drainage nitrate load tradeoffs of fertilizer management decisions
AU - Peterson, Chelsea M.
AU - Rodríguez, Luis F.
AU - Chu, Maria L.
N1 - Funding Information:
The data for the LVR sites in this study were collected by the Illinois Agricultural Experiment Station, University of Illinois at Urbana-Champaign as a part of Project 10-309 and Southern Regional Research Project S-273 (formerly S-249) with funding from USDA-CSREES under special projects 91-EHUA-1-0040 and 95-EHUA-1-0123, NRI project 9501781, Special Project 95-34214-2266 (Purdue sub-contract 590-1145-2417-01). Additional funds came from the Council on Food and Agricultural Research. Moreover, I would like to thank Dr. Rabin Bhattarai for generously sharing the data with me and Dr. Jorge Guzman for help with coding.
PY - 2020
Y1 - 2020
N2 - Achieving 45% nutrient loss reduction goals in Illinois and the Mississippi River Basin will require farmers and land managers to adopt multiple best management practices. The current statewide estimates for nitrogen (N) load reductions of individual practices, however, cannot be added together because of nonlinear practice interactions. Our objective is to fully explore the synergies and tradeoffs of combined fertilizer management decisions by coupling the USDA's Root Zone Water Quality Model 2 (RZWQM2) with a multiobjective evolutionary algorithm. To initially develop and test the optimization framework, we use the calibrated model from Jeong and Bhattarai (2018) for two sites in east-central Illinois during the study period 1993 to 2000. The feasible ranges for decisions variables are based on historical fertilizer rates and application dates from the site management records. To calculate the profit and cost effectiveness of seasonal management decisions, we collected historical economic information for central Illinois, including market corn prices, fertilizer costs, and costs of shifting fertilizer timing from fall to spring, over the study period. With the vector-valued objective function to minimize N loads and cost effectiveness and maximize profit and corn yields, we implement the Strength Pareto Evolutionary Algorithm 2 with RZWQM2 under historical weather to generate nondominated sets of fertilizer rate, timing, and method decisions for eight growing seasons. We directly use these results to quantify the benefit of optimal management by comparing outcomes between optimized, rule-based, and historical management scenarios.
AB - Achieving 45% nutrient loss reduction goals in Illinois and the Mississippi River Basin will require farmers and land managers to adopt multiple best management practices. The current statewide estimates for nitrogen (N) load reductions of individual practices, however, cannot be added together because of nonlinear practice interactions. Our objective is to fully explore the synergies and tradeoffs of combined fertilizer management decisions by coupling the USDA's Root Zone Water Quality Model 2 (RZWQM2) with a multiobjective evolutionary algorithm. To initially develop and test the optimization framework, we use the calibrated model from Jeong and Bhattarai (2018) for two sites in east-central Illinois during the study period 1993 to 2000. The feasible ranges for decisions variables are based on historical fertilizer rates and application dates from the site management records. To calculate the profit and cost effectiveness of seasonal management decisions, we collected historical economic information for central Illinois, including market corn prices, fertilizer costs, and costs of shifting fertilizer timing from fall to spring, over the study period. With the vector-valued objective function to minimize N loads and cost effectiveness and maximize profit and corn yields, we implement the Strength Pareto Evolutionary Algorithm 2 with RZWQM2 under historical weather to generate nondominated sets of fertilizer rate, timing, and method decisions for eight growing seasons. We directly use these results to quantify the benefit of optimal management by comparing outcomes between optimized, rule-based, and historical management scenarios.
KW - Corn-soybean production
KW - Fertilizer management
KW - Multiobjective optimization
KW - Root Zone Water Quality Model
KW - Strength Pareto Evolutionary Algorithm 2
KW - Subsurface drainage
UR - http://www.scopus.com/inward/record.url?scp=85096567652&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096567652&partnerID=8YFLogxK
U2 - 10.13031/aim.202000163
DO - 10.13031/aim.202000163
M3 - Paper
AN - SCOPUS:85096567652
T2 - 2020 ASABE Annual International Meeting
Y2 - 13 July 2020 through 15 July 2020
ER -