International Journal of Computational Intelligence Research
  • Year: 2007
  • Volume: 3
  • Issue: 4

Multi-Objective Evolutionary Algorithm for Land-Use Management Problem

  • Author:
  • Dilip Datta1, Kalyanmoy Deb1, Carlos M. Fonseca2, Fernando G. Lobo2, Paulo A. Condado2, Júlia Seixas3
  • Total Page Count: 14
  • Page Number: 371 to 384

1Department of Mechanical Engineering, Indian Institute of Technology Kanpur, Kanpur - 208 016, India. E-mails: dattadilip@rediffmail.com, deb@iitk.ac.in

2DEEI, Faculdade de Ciências e Tecnologia, Universidade do Algarve, Campus de Gambelas, 8000-117 Faro, Portugal. E-mails: cmfonsec@ualg.pt, flobo@ualg.pt, pcondado@ualg.pt

3DCEA, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa, 2829-516 Caparica, Portugal. E-mail: mjs@fct.unl.pt

Abstract

Due to increasing human activities on land to meet various demands, land uses are being continuously changed without any attention to their long term environmental impacts. Thus affecting the natural balance of the environment, in the form of global warming, soil degradation, loss of biodiversity, air and water pollution, and so on. Hence, it has become urgent need to manage land uses scientifically to safeguard the environment from being further destroyed. Owing to the difficulty of deploying field experiments for direct assessment, mechanistic models are needed to be developed for improving the understanding of the overall impact from various land uses. However, very little work has been done so far in this area. NSGA-II-LUM, a spatial-GIS based multi-objective evolutionary algorithm, is developed in the present work for three incommensurable objective functions: maximizing economic return, maximizing carbon sequestration and minimizing soil erosion, where the latter two are burning issues to today's researchers as the remedies to global warming and soil degradation. NSGA-II-LUM is applied to a Mediterranean landscape from Southern Portugal, and a number of interesting solutions, maintaining good trade-off among them, are obtained.