选址问题是GIS最基本的任务之一.一般性的选址是基于点的位置优化,可利用有关GIS功能完成.实际的选址问题是很复杂的.在给定设施的数量和面积前提下,需要在空间上确定设施的最佳位置,并对形状进行优化,以获取最大的效用.采用一般的方法无法求解这种最优化问题.而且,当选址问题涉及多个目标和不同的约束性条件时,就会变得异常复杂.提出了利用多目标粒子群优化算法和区域形状变异算法相结合来解决复杂的空间选址问题.具有智能的搜索方法,大大提高了空间搜索能力,并保持了搜索区域的连通性,取得了较好的效果.

Site selection, which is one basic task ofGIS functionalities, is to search for the best sites for a facility or a number of facilities. The objective is tomaxmi ize some utility functions subject to some goals. Traditional site selection methods using GIS only focus on the identifying the best locations (coordinates) of facilities. In many applications,contiguity constraintsmustbe considered in site selection. Site selection should considernotonly locations, butalso patch configuration for solvingmany optmi ization problems. The objective is tomaxmi ize utility functions subject to contiguity constraints and various planning goals. The combination of locations and contiguity for site selection is a difficultproblem for site selection because of involving huge solution space. The problem becomesmore complexwhenmulti-objectives are incorporated in the optmi ization.Many alternative generating techniques (such as theweightingmethod and the non-inferior set estmi ationmethod) have been developed tohelp decision-makers search solution spaces. Although thesemethodsare effective undersome circumstances,the approaches have severalweaknesses: (1) it can only be applied to problems thataremathematically formulated; (2) it is inefficientwhen applied to large problems; and (3) itmay fail to find mi portant solutions. As a consequence, builders of decision-support tools requiremethods that overcome these lmi itations and efficaciously generate alternative solutions tomulti-objectives decision problems. Particle-swarm optmi ization (PSO) can be used to achieue such goals.This paperpresents a newmethod to solve such problem by using particle-swarm optmi ization (PSO) method and shapemutate algorithms, which is a strictmutation operator to prevent the formation of“holes”in searching for optmi al contiguous sites. Particle-swarm optmi izationmethod is used tomake the solutions flying to the best locations. Shape contiguity constraint and patch configuration optmi ization are operated by shape-mutate algorithms. Here, a site is represented byusing an undirected graph and a setofoperations isdesigned to change the shape and location ofsitesduring the search forpossible solutions. These operations evolve randomly generated initial solutions into a setofoptmi al solutions to this type ofproblem; at the same tmi e,the contiguity ofa site ismaintained and the“holes”of the site are prevented to formation.This approach is applied to three different types of cost surfaces: uniform random, a conical and a deformed sombrero-like surface. The analyses are focused on a128×128 grid ofcells, where a facility is located atthe centerofthe area; The number of cells fora site is fixed and setat10. The resultsdemonstrate the robustness and effectiveness of this PSO-based approach to geographical analysis and multi-objective site selection problems. This approach has also been tested in the city ofGuangzhou, to search for the best locations for CBD.The results are also reasonable.The expermi ents have indicated that this approach is effective in solving this problem. It can successfully capture all the best solutions. The results can be used directly as the location selection by the decision-makers because these have been the best solutions.