As one of the most important methods for limiting urban sprawl, the accurate delineation of the urban–rural boundary not only promotes the intensive use of urban resources, but also helps to alleviate the urban issues caused by urban sprawl, realizing the intensive and healthy development of urban cities. Previous studies on delineating urban–rural boundaries were only based on the level of urban and rural development reflected by night-time light (NTL) data, ignoring the differences in the spatial development between urban and rural areas; so, the comprehensive consideration of NTL and point of interest (POI) data can help improve the accuracy of urban–rural boundary delineation. In this study, the NTL and POI data were fused using wavelet transform, and then the urban–rural boundary before and after data fusion was delineated by multiresolution segmentation. Finally, the delineation results were verified. The verification result shows that the accuracy of delineating the urban–rural boundary using only NTL data is 84.20%, and the Kappa value is 0.6549; the accuracy using the fusion of NTL and POI data on the basis of wavelet transform is 93.2%, and the Kappa value is 0.8132. Therefore, we concluded that the proposed method of using wavelet transform to fuse NTL and POI data considers the differences between urban and rural development, which significantly improves the accuracy of the delineation of urban–rural boundaries. Accurate delineation of urban–rural boundaries is helpful for optimizing internal spatial structure in both urban and rural areas, alleviating environmental problems resulting from urban development, assisting the formulation of development policies for urban and rural fringes, and promoting the intensive and healthy development of urban areas.

With the rapid expansion of urban built-up areas in recent years, it has become particularly urgent to develop a fast, accurate and popularized urban built-up area extraction method system. As the direct carrier of urban regional relationship, urban built-up area is an important reference to judge the level of urban development. The accurate extraction of urban built-up area plays an important role in formulating scientific planning thus to promote the healthy development of both urban area and rural area. Although nighttime light (NTL) data are used to extract urban built-up areas in previous studies, there are certain shortcomings in using NTL data to extract urban built-up areas. On the other hand, point of interest (POI) data and population migration data represent different attributes in urban space, which can both assist in modifying the deficiencies of NTL data from both static and dynamic spatial elements, respectively, so as to improve the extraction accuracy of urban built-up areas. Therefore, this study attempts to propose a feasible method to modify NTL data by fusing Baidu migration (BM) data and POI data thus accurately extracting urban built-up areas in Guangzhou. More accurate urban built-up areas are extracted using the method of U-net deep learning network. The maximum built-up area extracted from the study is 1103.45 km2, accounting for 95.21% of the total built-up area, and the recall rate is 0.8905, the precision rate is 0.8121, and the F1 score is 0.8321. The results of using POI data and BM data to modify NTL data to extract built-up areas have not been significantly improved due to the fact that the more data get fused, the more noise there would be, which would ultimately affect the results. This study analyzes the feasibility and insufficiency of using big data to modify NTL data through data fusion and feature extraction system, which has important theoretical and practical significance for future studies on urban built-up areas and urban development.

With the rapid expansion of urban built-up areas in recent years, accurate and long time series monitoring of urban built-up areas is of great significance for healthy urban development and efficient governance. As the basic carrier of urban activities, the accurate monitoring of urban built-up areas can also assist in the formulation of urban planning. Previous studies on urban built-up areas mainly focus on the analysis of a single time section, which makes the extraction results exist with a certain degree of contingency. In this study, a U-net is used to extract and monitor urban built-up areas in the Kunming and Yuxi area from 2012 to 2021 based on nighttime light data and POI_NTL (Point of Interest_Nighttime light) data. The results show that the highest accuracy of single nighttime light (NTL) data extraction was 89.31%, and that of POI_NTL data extraction was 95.31%, which indicates that data fusion effectively improves the accuracy of built-up area extraction. Additionally, the comparative analysis of the results of built-up areas and the actual development of the city shows that NTL data is more susceptible to urban emergencies in the extraction of urban built-up areas, and POI (Point of interest) data is subject to the level of technology and service available in the region, while the combination of the two can avoid the occasional impact of single data as much as possible. This study deeply analyzes the results of extracting urban built-up areas from different data in different periods and obtains the feasible method for the long time sequence monitoring of urban built-up areas, which has important theoretical and practical significance for the formulation of long-term urban planning and the current high-quality urban development.

No abstract