Research on dynamic simulation of land use change based on geographical weighted CLUE-S model

Abstract

In order to overcome the problems of poor denoising effect, large quantitative accuracy error and large spatial accuracy error of current land use change simulation methods, a dynamic simulation method of land use change based on geographically weighted CLUE-S model was proposed. Using CLUE-S model to simulate the expansion of urban space, combined with geographic weighted logistic stepwise regression method, the influencing factors of land use change were analysed. The spatial distribution of future land use area is realised by iteration, and the spatial visualisation simulation of land use prediction is realised. The experimental results show that the signal-to-noise ratio of the proposed method is more than 85 dB, the quantitative and spatial accuracy errors are less than 4%, and the ROC value is close to 1, which proves that the spatial simulation effect is relatively good.