Under the background of urban–rural integration, balanced development between urban and rural areas has been increasingly advocated. Rural population loss (RPL) is not only due to the laws of social and economic development but also the comprehensive action of natural, social, and economic factors. Taking 774 administrative villages in Laiyang County, which is in a hilly region, as our research area, we comprehensively used spatial analysis and geographic detectors to explore the spatial characteristics and driving factors of RPL, which was significantly correlated with rural planning. The research demonstrated that: (1) The rural population in Laiyang County generally had a low level of RPL (1.9%), but each village varied greatly. The village with the greatest RPL had a rate of 56%. The RPL between urban and rural areas, towns and streets, and villages and villages were unbalanced, and rural population flow mainly occurred between urban and rural areas. (2) RPL in Laiyang County was generally low in the central urban area and high in the northern and southern areas. Population loss presents agglomeration globally and high–low agglomeration locally. (3) The distance from village to county, elevation, cultivated land quantity, collective economic income, village area, and ecological service value were the key factors influencing RPL in Laiyang County. When comparing the dominant factors, the interaction between collective income and elevation was the strongest. Exploring the spatial characteristics and influencing factors of RPL provided us with ideas for the classified promotion of rural revitalization, preparation of rural development planning, and promotion of the integrated development of urban and rural areas.

Accurate recognition and extraction of rural residential land (RRL) is significant for scientific planning, utilization, and management of rural land. Very-High Resolution (VHR) Unmanned Aerial Vehicle (UAV) images and deep learning techniques can provide data and methodological support for the target. However, RRL, as a complex land use assemblage, exhibits features of different scales under VHR images, as well as the presence of complex impervious layers and backgrounds such as natural surfaces and tree shadows in rural areas. It still needs further research to determine how to deal with multi-scale features and accurate edge features in such scenarios. In response to the above problems, a novel framework named cascaded dense dilated network (CDD-Net), which combines DenseNet, ASPP, and PointRend, is proposed for RRL extraction from VHR images. The advantages of the proposed framework are as follows: Firstly, DenseNet is used as a feature extraction network, allowing feature reuse and better network design with fewer parameters. Secondly, the ASPP module can better handle multi-scale features. Thirdly, PointRend is added to the model to improve the segmentation accuracy of the edges. The research takes a plain village in China as the research area. Experimental results show that the Precision, Recall, F1 score, and Dice coefficients of our approach are 91.41%, 93.86%, 92.62%, and 0.8359, respectively, higher than other advanced models used for comparison. It is feasible in the task of high-precision extraction of RRL using VHR UAV images. This research could provide technical support for rural land planning, analysis, and formulation of land management policies.

Under the background of urban-rural integration, the frequent flow of urban and rural elements has promoted the close connection between rural transformation (RT) and construction land transition (CLT). How is CLT related to RT? By taking the plain area Linqing County in China as the study area, basing the study on the RT and CLT coupling framework of relevance theory, building an RT and CLT evaluation index system, using the multi-factor evaluation method for the evaluation of RT and CLT from 2010 to 2018, and using the grey correlation model to measure the RT and CLT coupling relationship, the results showed that the level of RT was from 0.04 to 97.42, and the level of CLT was from 14.89 to 82.47, showing the trends of gradual increase and fluctuating increase, respectively. Taking 2013 and 2016 as the time point, RT could be divided into the initial stage, growth stage I, and growth stage II, corresponding to the initial stage, high growth stage, and stable development stage of CLT. The coupling degree between the two was in the range of 0.6–0.8 and was in the stage of a medium to high coupling degree. The correlation degree between the subsystem of RT and CLT was over 0.65. In the subsystem of CLT, the correlation degrees between quantitative structure transition and RT and efficiency transition and RT were both lower than 0.65, which were relatively low. Controlling the scale of construction land and taking efficiency transition are the effective methods to guide the deep exploration of potential and are the inevitable way to strengthen the relationship between CLT and RT and promote urban-rural integration development.