A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Simulating Urban Sprawl in China Based on the Artificial Neural Network-Cellular Automata-Markov Model
In recent years, China’s urbanization rate has been increasing rapidly, reaching 59.58% in 2018. Urbanization drives rural-to-urban migration, and inevitably promotes urban sprawl. With the development of remote sensing and geographic information technologies, the monitoring technology for urban sprawl has been constantly innovated. In particular, the emergence of night light data has greatly promoted monitoring research of large-scale and long-time-series urban sprawl. In this paper, the urban sprawl in China in 1992, 1997, 2002, 2007, 2012, and 2017 was identified via night light data, and the Artificial Neural Network-Cellular Automata-Markov (ANN-CA-Markov) model was developed to simulate the future urban sprawl in China. The results show that the suitability of urban sprawl based on the ANN model is as high as 0.864, indicating that the ANN model is very suitable for the simulation of urban sprawl. The Kappa coefficient of simulation results was 0.78, indicating that the ANN-CA-Markov model has a high simulation accuracy on urban sprawl. In the future, the hotspot areas of urban sprawl in China will change over time. Although the urban sprawl in the Beijing-Tianjin-Hebei region, the Yangtze River delta, and the Pearl River delta will still be considerable, the urban sprawl in the Chengdu-Chongqing city cluster, the Guanzhong Plain city cluster, the central plains city cluster, and the middle reaches of the Yangtze River will be more prominent. Overall, China’s urban sprawl will be concentrated in the east of Hu’s line in the future.
Simulating Urban Sprawl in China Based on the Artificial Neural Network-Cellular Automata-Markov Model
In recent years, China’s urbanization rate has been increasing rapidly, reaching 59.58% in 2018. Urbanization drives rural-to-urban migration, and inevitably promotes urban sprawl. With the development of remote sensing and geographic information technologies, the monitoring technology for urban sprawl has been constantly innovated. In particular, the emergence of night light data has greatly promoted monitoring research of large-scale and long-time-series urban sprawl. In this paper, the urban sprawl in China in 1992, 1997, 2002, 2007, 2012, and 2017 was identified via night light data, and the Artificial Neural Network-Cellular Automata-Markov (ANN-CA-Markov) model was developed to simulate the future urban sprawl in China. The results show that the suitability of urban sprawl based on the ANN model is as high as 0.864, indicating that the ANN model is very suitable for the simulation of urban sprawl. The Kappa coefficient of simulation results was 0.78, indicating that the ANN-CA-Markov model has a high simulation accuracy on urban sprawl. In the future, the hotspot areas of urban sprawl in China will change over time. Although the urban sprawl in the Beijing-Tianjin-Hebei region, the Yangtze River delta, and the Pearl River delta will still be considerable, the urban sprawl in the Chengdu-Chongqing city cluster, the Guanzhong Plain city cluster, the central plains city cluster, and the middle reaches of the Yangtze River will be more prominent. Overall, China’s urban sprawl will be concentrated in the east of Hu’s line in the future.
Simulating Urban Sprawl in China Based on the Artificial Neural Network-Cellular Automata-Markov Model
Xueru Zhang (author) / Jie Zhou (author) / Wei Song (author)
2020
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Space – time patterns of urban sprawl, a 1D cellular automata and microeconomic approach
| Online Contents | 2009
Space-time patterns of urban sprawl, a 1D cellular automata and microeconomic approach
| BASE | 2008