Investigating the intensive redevelopment of urban central blocks using data envelopment analysis and deep learning: A case study of nanjing, china

Abstract

Intensification of morphology of blocks, which are the basic units of urban form and land management, is the key to sustainable urban development. Taking 206 blocks of Nanjing's central city area as an example, an evaluation system featuring six output-oriented indicators and five input-oriented indicators was constructed for data envelopment analysis to measure the blocks' intensity level. Relatively intensive blocks were selected as training data, and the output-oriented indicators of non-intensive blocks were predicted by a deep learning model, completing the procedure from evaluation of intensity to optimisation of morphological indicators. Finally, using the difference calculation and Arctool of weighted overlay in ArcGIS, a reference for the optimisation design of urban block morphology was created.