Multi-Source Data-Driven Identification and Spatial Optimization of Rural Settlements: Evidence from Sangxu, China

Based on the goal of achieving a classified promotion of rural revitalization in China’s Comprehensive Rural Revitalization Plan (2024–2027), this study presents a framework for a comprehensive sustainable development assessment system using multi-source data. This framework mainly adheres to the principles of settlement-type identification and spatial optimization strategies. The proposed framework is applied to Sangxu Town in eastern China to divide the settlements into five types and then optimize the spatial layout of rural settlements by employing spatial point pattern analysis, weighted Voronoi diagrams, and an extended breakpoint combination model. This study shows that, firstly, the overall development level of settlements in Sangxu Town is relatively high, but the distribution is uneven, with higher levels in the central and eastern regions and lower levels in the west. Secondly, based on the sustainable comprehensive development levels, 14 removal-type settlements (accounting for 27.45%), 21 control and retention-type settlements (41.18%), 7 agglomeration and upgrading-type settlements (13.73%), and 5 suburban integration-type settlements (9.80%) were identified. Thirdly, the activity intensity of residents is generally low in areas with low nighttime light intensity. The number of rural settlements was reduced to 37 after relocation, freeing up 94.91 hectares of homestead land—a reduction of 9.51%. This research improves the application of big data technology in identifying types of rural settlements and optimizing layout, providing experience for achieving sustainable development in rural areas in China.