Extraction of Urban Built-Up Areas Using Nighttime Light (NTL) and Multi-Source Data: A Case Study in Dalian City, China

The rapid urban development associated with China’s reform and opening up has been the source of many problems. To understand these issues, it is necessary to have a deep understanding distribution spatial structure. Taking six districts Dalian as an example, in this study, we integrated enhanced vegetation index, points interest, surface temperature data into night light data. Furthermore, herein, analyze kernel density interest construct three indices using image geometric mean: human settlement index (HSI), HSI-POI (HP) HSI-POI-LST (HPL) index. Using support vector machine identify land type Dalian’s built-up area, 1000 sampling were created for verification. Then, threshold boundary corresponding highest overall accuracy each kappa coefficient was selected. relevant conclusions are follows: As compared other types data, HPL constructed study exhibited natural social attributes, area extracted method had accuracy, high resolution, able overcome omission issues observed when one or two sources. In addition, produces richer details actual provides more choices assessing small-scale areas future research.