Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library

Yan Y. Liu, Mengyu Guo, Shaowen Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Optimization algorithms are often employed in spatial analysis and modeling to provide adaptive mechanisms at both individual and collective levels to enable decision-makers for the search of optimal solutions with respect to single/multiple objectives and constraints imposed by spatial configurations. This research aims to solve large-scale agricultural land use optimization problems by exploiting massive parallel computing resources provided by supercomputers such as those in XSEDE. The optimization of agricultural land use patterns finds an optimal assignment of crops (e.g., food and biofuel crops) on land parcels of a specified study area that maximizes the total yield and satisfies various competing constraints. These constraints often consider spatial factors such as contiguity and ownership, climate and land management factors (e.g., soil, precipitation, light, temperature, and ozone) and their effects on the productivity, suitability, and cost of assigning a crop on a land parcel. We have formulated the land use optimization problem as a classic combinatorial optimization problem - Generalized Assignment Problem (GAP) [2]. GAP is a well-known NP-hard problem [3]. When a landscape includes tens of thousands of land parcels (e.g., Figure 1), finding an exact optimal solution is computationally intractable.

Original languageEnglish (US)
Title of host publicationProceedings of the XSEDE 2013 Conference
Subtitle of host publicationGateway to Discovery
DOIs
StatePublished - Aug 26 2013
EventConference on Extreme Science and Engineering Discovery Environment, XSEDE 2013 - San Diego, CA, United States
Duration: Jul 22 2013Jul 25 2013

Publication series

NameACM International Conference Proceeding Series

Other

OtherConference on Extreme Science and Engineering Discovery Environment, XSEDE 2013
CountryUnited States
CitySan Diego, CA
Period7/22/137/25/13

Fingerprint

Parallel algorithms
Land use
Genetic algorithms
Crops
Supercomputers
Combinatorial optimization
Biofuels
Parallel processing systems
Ozone
Computational complexity
Productivity
Soils
Costs
Temperature

Keywords

  • Genetic algorithm
  • Heuristics
  • Land use optimization
  • Parallel computing
  • Scalability

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Liu, Y. Y., Guo, M., & Wang, S. (2013). Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library. In Proceedings of the XSEDE 2013 Conference: Gateway to Discovery [3] (ACM International Conference Proceeding Series). https://doi.org/10.1145/2484762.2484824

Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library. / Liu, Yan Y.; Guo, Mengyu; Wang, Shaowen.

Proceedings of the XSEDE 2013 Conference: Gateway to Discovery. 2013. 3 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, YY, Guo, M & Wang, S 2013, Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library. in Proceedings of the XSEDE 2013 Conference: Gateway to Discovery., 3, ACM International Conference Proceeding Series, Conference on Extreme Science and Engineering Discovery Environment, XSEDE 2013, San Diego, CA, United States, 7/22/13. https://doi.org/10.1145/2484762.2484824
Liu YY, Guo M, Wang S. Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library. In Proceedings of the XSEDE 2013 Conference: Gateway to Discovery. 2013. 3. (ACM International Conference Proceeding Series). https://doi.org/10.1145/2484762.2484824
Liu, Yan Y. ; Guo, Mengyu ; Wang, Shaowen. / Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library. Proceedings of the XSEDE 2013 Conference: Gateway to Discovery. 2013. (ACM International Conference Proceeding Series).
@inproceedings{cb8a70324bc24d638f1db4b195ef62d7,
title = "Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library",
abstract = "Optimization algorithms are often employed in spatial analysis and modeling to provide adaptive mechanisms at both individual and collective levels to enable decision-makers for the search of optimal solutions with respect to single/multiple objectives and constraints imposed by spatial configurations. This research aims to solve large-scale agricultural land use optimization problems by exploiting massive parallel computing resources provided by supercomputers such as those in XSEDE. The optimization of agricultural land use patterns finds an optimal assignment of crops (e.g., food and biofuel crops) on land parcels of a specified study area that maximizes the total yield and satisfies various competing constraints. These constraints often consider spatial factors such as contiguity and ownership, climate and land management factors (e.g., soil, precipitation, light, temperature, and ozone) and their effects on the productivity, suitability, and cost of assigning a crop on a land parcel. We have formulated the land use optimization problem as a classic combinatorial optimization problem - Generalized Assignment Problem (GAP) [2]. GAP is a well-known NP-hard problem [3]. When a landscape includes tens of thousands of land parcels (e.g., Figure 1), finding an exact optimal solution is computationally intractable.",
keywords = "Genetic algorithm, Heuristics, Land use optimization, Parallel computing, Scalability",
author = "Liu, {Yan Y.} and Mengyu Guo and Shaowen Wang",
year = "2013",
month = "8",
day = "26",
doi = "10.1145/2484762.2484824",
language = "English (US)",
isbn = "9781450321709",
series = "ACM International Conference Proceeding Series",
booktitle = "Proceedings of the XSEDE 2013 Conference",

}

TY - GEN

T1 - Large-scale land use optimization by enhancing a scalable parallel genetic algorithm library

AU - Liu, Yan Y.

AU - Guo, Mengyu

AU - Wang, Shaowen

PY - 2013/8/26

Y1 - 2013/8/26

N2 - Optimization algorithms are often employed in spatial analysis and modeling to provide adaptive mechanisms at both individual and collective levels to enable decision-makers for the search of optimal solutions with respect to single/multiple objectives and constraints imposed by spatial configurations. This research aims to solve large-scale agricultural land use optimization problems by exploiting massive parallel computing resources provided by supercomputers such as those in XSEDE. The optimization of agricultural land use patterns finds an optimal assignment of crops (e.g., food and biofuel crops) on land parcels of a specified study area that maximizes the total yield and satisfies various competing constraints. These constraints often consider spatial factors such as contiguity and ownership, climate and land management factors (e.g., soil, precipitation, light, temperature, and ozone) and their effects on the productivity, suitability, and cost of assigning a crop on a land parcel. We have formulated the land use optimization problem as a classic combinatorial optimization problem - Generalized Assignment Problem (GAP) [2]. GAP is a well-known NP-hard problem [3]. When a landscape includes tens of thousands of land parcels (e.g., Figure 1), finding an exact optimal solution is computationally intractable.

AB - Optimization algorithms are often employed in spatial analysis and modeling to provide adaptive mechanisms at both individual and collective levels to enable decision-makers for the search of optimal solutions with respect to single/multiple objectives and constraints imposed by spatial configurations. This research aims to solve large-scale agricultural land use optimization problems by exploiting massive parallel computing resources provided by supercomputers such as those in XSEDE. The optimization of agricultural land use patterns finds an optimal assignment of crops (e.g., food and biofuel crops) on land parcels of a specified study area that maximizes the total yield and satisfies various competing constraints. These constraints often consider spatial factors such as contiguity and ownership, climate and land management factors (e.g., soil, precipitation, light, temperature, and ozone) and their effects on the productivity, suitability, and cost of assigning a crop on a land parcel. We have formulated the land use optimization problem as a classic combinatorial optimization problem - Generalized Assignment Problem (GAP) [2]. GAP is a well-known NP-hard problem [3]. When a landscape includes tens of thousands of land parcels (e.g., Figure 1), finding an exact optimal solution is computationally intractable.

KW - Genetic algorithm

KW - Heuristics

KW - Land use optimization

KW - Parallel computing

KW - Scalability

UR - http://www.scopus.com/inward/record.url?scp=84882339928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882339928&partnerID=8YFLogxK

U2 - 10.1145/2484762.2484824

DO - 10.1145/2484762.2484824

M3 - Conference contribution

AN - SCOPUS:84882339928

SN - 9781450321709

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the XSEDE 2013 Conference

ER -