A maps-to-maps approach for simulating urban land expansion based on convolutional long short-term memory neural networks

Abstract

Cellular automata (CA) have been prevalently used for the simulation of urban land change. However, how to effectively learn the spatial-temporal dynamics of urban development from time-series data remain an important challenge for CA-based models. To address this issue, we propose a new model for the simulation of urban development based on convolutional long short-term memory (ConvLSTM) neural networks. The core of the proposed model is a sequence of vanilla ConvLSTM cells integrated with the modules of channel attention and contextual embedding. Compared with conventional CA-based models, the proposed ConvLSTM model is more advanced in that it can better leverage the open access annual urban land maps to capture simultaneously the spatial structure and the temporal dependency of historical urban development, and further predict multiple maps of annual development for subsequent years (i.e., Maps-to-Maps). The performance of the ConvLSTM model is evaluated through the case studies in China’s three mega-urban regions, and ConvLSTM outperforms other state-of-the-art deep learning architectures at both the pixel level and the coarser grid level. The results also suggest the satisfactory transferability of ConvLSTM in that the model trained in one mega-urban region can be successfully re-used in others without fine tuning.

Keywords:

• Urban land expansion
• cellular automata
• convolutional long short-term memory

Acknowledgments

The authors are grateful to the associate editor, Song Gao, and the anonymous reviewers for their valuable comments and suggestions.

Authors contributions

Zihao Zhou: Methodology, formal analysis, validation, writing—original draft preparation; Yimin Chen: Conceptualization, supervision, project administration, funding acquisition, writing—review and editing; Xiaoping Liu: Conceptualization, writing—review and editing; Xinchang Zhang: Investigation, writing—original draft preparation; Honghui Zhang: Investigation, writing—original draft preparation. All authors have read and agreed to the published version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

The materials that support the findings of this study are available via https://doi.org/10.6084/m9.figshare.23918658. The code can also be accessed via https://github.com/kwtk86/UrbanM2M.

Additional information

Funding

This study was funded by National Natural Science Foundation of China (Grant No. 42271415 and 42322110) and Guangdong Natural Science Funds for Distinguished Young Scholar (Grant No. 2021B1515020104).

Notes on contributors

Zihao Zhou

Zihao Zhou is a master’s student of GIScience at Sun Yat-sen University, Guangzhou, China. His research interests include urban simulation and urban big data analysis.

Yimin Chen

Yimin Chen is an Associate Professor of GIScience at Sun Yat-sen University, Guangzhou, China. His research interests include machine learning and urban applications.

Xiaoping Liu

Xiaoping Liu is a Professor of GIScience at Sun Yat-sen University, Guangzhou, China. His research interests include land use change models and applications.

Xinchang Zhang

Xinchang Zhang is a Professor of GIScience at Guangzhou University, Guangzhou, China. His research interests include spatial data analysis and GISystem development.

Honghui Zhang

Honghui Zhang is the Co-President of Guangdong Guodi Planning Science Technology Co., Ltd, China. His research interests include urban big data analysis and urban planning.