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.
Highlights
Rapid urbanization and socioeconomic development have increased the tension in human-environment interactions [1] since the industrial era
In terms of the model, since LUCC is the result of a complex spatiotemporal process, most models are currently based on cellular automata (CA), which estimate a future state pixel by pixel according to their initial state through a set of transition rules and the surrounding neighborhood effects
The values indicated that the results of our model had landscape pattern metrics that were more similar to the true land cover (LC)
Summary
Rapid urbanization and socioeconomic development have increased the tension in human-environment interactions [1] since the industrial era. In terms of the model, since LUCC is the result of a complex spatiotemporal process, most models are currently based on cellular automata (CA), which estimate a future state pixel by pixel according to their initial state through a set of transition rules and the surrounding neighborhood effects. In this way, it achieves the simulation of a complex scene though the simple transition of pixels. The proposed model combines the LC data of multiple time phases together with the city planning information to predict the future LC results Experiments in both short-term and long-term scenarios were conducted, and results evaluated in terms of accuracy, landscape form and diversity have demonstrated the effectiveness of the proposed framework.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have