TY - GEN
T1 - Spatially constrained geodesign optimization (GOP) for improving agricultural watershed sustainability
AU - Xie, Yiqun
AU - Yang, Kwang Soo
AU - Shekhar, Shashi
AU - Dalzell, Brent J
AU - Mulla, D J
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Given an agricultural watershed containing a set of spatial units, and a set of land management practices, the Geodesign Optimization (GOP) aims to find a land management practice for each spatial unit that optimizes overall water quality improvements in the watershed under both budget constraint and spatial constraints (e.g., minimum contiguous area, shape) arising from farm equipment operation practicalities. GOP is important for redesign of agricultural watersheds in Midwestern US to mitigate soil and water quality degradation and loss of habitat. The problem is computationally challenging as a large-scale combinatorial problem (NP-hard) under spatial constraints. Existing optimization techniques do not address spatial constraints, and lead to impractical solutions requiring frequent farm equipment reconfiguration. In this paper, we formalize the spatially-constrained GOP and propose a novel spatial optimizer which explores optimal solution without constraint violations. Our approach is further validated through a Geodesign case study at Seven Mile Creek watershed in Midwestern US.
AB - Given an agricultural watershed containing a set of spatial units, and a set of land management practices, the Geodesign Optimization (GOP) aims to find a land management practice for each spatial unit that optimizes overall water quality improvements in the watershed under both budget constraint and spatial constraints (e.g., minimum contiguous area, shape) arising from farm equipment operation practicalities. GOP is important for redesign of agricultural watersheds in Midwestern US to mitigate soil and water quality degradation and loss of habitat. The problem is computationally challenging as a large-scale combinatorial problem (NP-hard) under spatial constraints. Existing optimization techniques do not address spatial constraints, and lead to impractical solutions requiring frequent farm equipment reconfiguration. In this paper, we formalize the spatially-constrained GOP and propose a novel spatial optimizer which explores optimal solution without constraint violations. Our approach is further validated through a Geodesign case study at Seven Mile Creek watershed in Midwestern US.
UR - http://www.scopus.com/inward/record.url?scp=85044594861&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044594861&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85044594861
T3 - AAAI Workshop - Technical Report
SP - 57
EP - 63
BT - WS-17-01
PB - AI Access Foundation
T2 - 31st AAAI Conference on Artificial Intelligence, AAAI 2017
Y2 - 4 February 2017 through 10 February 2017
ER -