Comprehensive Evaluation Model for Resettlement Site Selection in Karst Areas Using Multiobjective Particle Swarm Optimization

Abstract

Resettlement site selection is a systematic project constrained by multiple geographic, social, and economic factors, and site selection in karst mountainous areas is even more complicated. The key step in resettlement site selection is to reduce the uncertainty and inaccuracy of evaluation models. This study constructed an evaluation index system of a model for resettlement site selection in karst mountainous areas from multiple aspects, including karst rocky desertification environment, degree of geological hazard development, resource and environmental carrying capacity, transportation and economic development potential, as well as relocation cost. A hierarchical model was applied to classify the indices, determine the weighted optimal solution of the eigenvectors in matrices, and evaluate the suitability. A new algorithm for model parameter inference was developed based on four objectives, including achieving suitable ecoenvironment capacity, ensuring production and development, controlling relocation cost, and meeting the comprehensive requirements. The objective functions and constraints of the model with four objectives were also established. To address this problem, the multiobjective particle swarm algorithm was applied, and a novel concept of "noninferior solution set" was proposed. The objective functions and constraint conditions of the algorithm were optimized and improved from four aspects: parameter setting, representativeness of particles, noninferior solution set storage, and selection of global noninferior solution set. Guanling County, an area in Guizhou Province with a typical development of karst rocky desertification, was selected as the study site. The latest data for land use mapping were adopted as the smallest evaluation unit, and the improved multiobjective particle swarm algorithm was employed in evaluating the resettlement site selection within this area. The improved algorithm was applicable to a wide range of multiobjective optimization problems.

Location Selection of Digital Cultural Tourism Town Based on Improved Genetic Algorithm and BP Neural Network

“…Cultural and tourism featured towns account for the largest proportion in the whole investment process, which is significantly higher than the cultural and tourism complex, and much higher than the investment in scenic spots, theme parks, and other cultural and tourism projects. However, it should be noted that in the first half of 2019, compared with the same period in 2018, the number of cultural tourism featured town projects increased by 188%, but the total investment decreased by 20.61% [12,13].…”