Evaluation of Intensive Urban Land Use Based on an Artificial Neural Network Model： A Case Study of Nanjing City, China

• Published in: Chinese geographical science 2017-10, Vol.27 (5), p.735-746
• Main Authors: Qiao, Weifeng, Gao, Junbo, Liu, Yansui, Qin, Yueheng, Lu, Cheng, Ji, Qingqing
• Format: Article
• Language: English
• Subjects: Case studies; Cities; Earth and Environmental Science; Evaluation; Geography; Land use; Neural networks; Protected areas; Urban areas; 中国; 人工神经网络模型; 利用评价; 南京市; 土地利用强度; 土地集约利用; 城市土地利用; 多因素综合评价
• ISSN: 1002-0063; 1993-064X
• DOI: 10.1007/s11769-017-0905-7

In this paper, the artificial neural network （ANN） model was used to evaluate the degree of intensive urban land use in Nanjing City, China. The construction and application of the ANN model took into account the comprehensive, spatial and complex nature of urban land use. Through a preliminary calculation of the degree of intensive land use of the sample area, representative sample area selection and using the back propagation neural network model to train, the intensive land use level of each evaluation unit is finally determined in the study area. Results show that the method can effectively correct the errors caused by the limitations of the model itself and the determination of the ideal value and weights when the multifactor comprehensive evaluation is used alone. The ANN model can make the evaluation results more objective and practical. The evaluation results show a tendency of decreasing land use intensity from the core urban area to the periphery and the industrial functional area has relatively low land use intensity compared with other functional areas. Based on the evaluation results, some suggestions are put forward, such as transforming the mode of urban spatial expansion, strengthening the integration and potential exploitation of the land in the urban built-up area, and strengthening the control of the construction intensity of protected areas.