Jiao Limin

Rural land use spatial allocation in the semiarid loess hilly area in China: Using a Particle Swarm Optimization model equipped with multi-objective optimization techniques

Semiarid loess hilly areas in China are enduring a series of environmental conflicts between urban expansion, cultivated land conservation, soil erosion and water shortage, and require land use allocation to reconcile these environmental conflicts. We argue that the optimized spatial allocation of rural land use can be achieved by a Particle Swarm Optimization (PSO) model in conjunction with multi-objective optimization techniques. Our study focuses on Yuzhong County of Gangsu Province in China, a typical catchment on the Loess Plateau, and proposes a land use spatial optimization model. The model maximizes land use suitability and spatial compactness based on a variety of constraints, e.g. optimal land use structure and restrictive areas, and employs an improved PSO algorithm equipped with a determinant initialization method and a dynamic weighted aggregation (DWA) method to obtain the optimized land use spatial pattern. The results suggest that (1) approximately 4% of land use should be reallocated and these changes would alleviate the environmental conflicts in the study area; (2) the major reshuffling is slope farmland and newly added construction and cultivated land, whereas the unchanged areas are largely forests and basic farmland; and (3) the PSO is capable of optimizing rural land use allocation, and the determinant initialization method and DWA can improve the performance of the PSO.

Model of Land Suitability Evaluation Based on Computational Intelligence

A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The structure and process of this network is clear. Fuzzy rules (knowledge) are expressed in the model explicitly, and can be self-adjusted by learning from samples. Genetic algorithm (GA) is employed as the learning algorithm to train the network, and makes the training of the model efficient. This model is a self-learning and self-adaptive system with a rule set revised by training.

The application of BP networks to land suitability evaluation

The back propagation (BP) model of artificial neural networks (ANN) has many good qualities comparing with ordinary methods in land suitability evaluation. Through analyzing ordinary methods’ limit tions, some sticking points of BP model used in land evaluation, such as network structure, learning algorithm, etc., are discussed in detail, The land evaluation of Qionghai city is used as a case study. Fuzzy comprehensive assessment method was also employed in this evaluation for validating and comparing.