GAN-Based LUCC Prediction via the Combination of Prior City Planning Information and Land-Use Probability

Abstract

Currently, the world is in a period of urbanization that will accelerate the processes of land-use cover and ecological change. Thus, establishing a land-use and land-cover change (LUCC) prediction and simulation model is of great significance for understanding the process of urban change and assessing its ecological impact. In previous studies, LUCC prediction models have been mainly based on cellular automata structures that calculate a future state pixel by pixel through transition rules. Because these transition rules are usually based on the global state and each pixel is calculated according to these fixed rules, the results of these methods have room for improvement in terms of generating details and heterogeneity. In this article, a generative adversarial network (GAN)-based LUCC prediction model using multiscale local spatial information is proposed. The model is based on a pix2pix GAN and an attention structure that predicts future land use through multiscale local spatial information. To validate our model, Shenzhen, a region that is experiencing rapid urbanization, was chosen as the source of the experimental data. The results indicate that the proposed method achieved the highest accuracy in both short-time interval and long-time interval scenarios. In addition, the results of the proposed method were also closest to the ground truth from the perspective of the landscape pattern.

Keywords

• Deep learning
• generative adversarial network (GAN)
• LUCC simulation
• remote sensing
• smart city