Population aging is a global issue. China is facing the same challenge, especially in its megacities, with more than 10 million permanent urban residents. These densely populated cities urgently need the scientific planning and optimization of the layout of service facilities for older people. Taking Guangzhou, a megacity in China, as an example, this study uses point-of-interest (POI) data and the ID3 machine learning decision tree algorithm to train a site selection model for service facilities for older people. The model can help to select appropriate locations for new service facilities for older people more scientifically and accurately, and it can provide targeted suggestions to optimize the layout of the service facilities for older people in Guangzhou. First, Guangzhou city is divided into 29,793 grids of 500 m × 500 m based on the range of activities of older people, and 985 grids are found to contain service facilities for older people. Then, the POI data of the grid are fed into the ID3 algorithm for training to obtain a prediction model for the selection of sites for service facilities for older people. The effective prediction rate of the model reaches 87.54%. Then, we apply the site selection model to predict the whole city of Guangzhou, and 4534 grids are suitable for service facilities for older people. In addition, considering the degree of concentration of the elderly population in each street, we further filter out 1066 priority grids as the final site selection. Finally, taking into account the situation of the streets in different districts, we propose several strategies to optimize the layout of the construction of service facilities for older people.

Against the background of smart city construction and the increasing application of big data in the field of planning, a method is proposed to effectively improve the objectivity, scientificity, and global nature of urban park siting, taking Guangzhou and its current urban park layout as an example. The proposed approach entails integrating POI data and innovatively applying machine learning algorithms to construct a decision tree model to make predictions for urban park siting. The results show that (1) the current layout of urban parks in Guangzhou is significantly imbalanced and has blind zones, and with an expansion of the search radius, the distribution becomes more concentrated; high-density areas decrease from the center outward in a circle, which manifests as a pattern of high aggregation at the core and low dispersion at the edge. (2) Urban park areas with a service pressure of level 3 have the largest coverage and should be prioritized for construction as much as possible; there are fewer areas at levels 4 and 5, which are mainly concentrated in the central city, and unreasonable resource allocation is a problem that needs to be solved urgently. (3) There was a preliminary prediction of 6825 sites suitable for planning, and the fit with existing city parks was 93.7%. The prediction results were reasonable, and the method was feasible. After further screening through the coupling and superposition of the service pressure and the layout status quo, 1537 locations for priority planning were finally obtained. (4) Using the ID3 machine learning algorithm to predict urban park sites is conducive to the development of an overall optimal layout, and subjectivity in site selection can be avoided, providing a methodological reference for the planning and construction of other infrastructure or the optimization of layouts.

In order to alleviate the increased habitat fragmentation caused by the accelerating urbanization and ecological deterioration, constructing ecological networks is an effective way to improve ecological connectivity, facilitate regional energy flow, and promote biodiversity enhancement. In this study, Yongtai County was taken as the research object, and the morphological spatial pattern analysis (MSPA) method was used to analyze the landscape pattern, identify the ecological source sites, classify the ecological source sites according to the importance degree by possible connectivity index (PC) and the Delta values for probability index of connectivity (dPC), and then construct the potential ecological corridors with the help of the minimum cumulative resistance (MCR) model to generate the ecological network, and then put forward the optimization strategy according to the current situation. The results show that (1) the core area of Yongtai County is 1071.06 km², the largest among all landscape types, with a fragmented distribution, high degree of fragmentation, and poor connectivity, mainly in the east and southwest, and sparser in the middle. (2) The area of highest resistance value is mainly located in the built-up areas of towns and rural settlements in the central and northwestern parts of the country; the lowest value is distributed in the southwest and southeast, and the land use mode is mainly expressed as woodland. (3) The ecological network consists of 13 ecological sources and 78 potential ecological corridors. The ecological sources are mainly located in the east and southwest, with high connectivity; the potential ecological corridors are distributed in the form of a network, with fewer in the center, resulting in the phenomenon of ecological disconnection. (4) Lack of ecological sources and corridors, serious landscape fragmentation, and optimization of ecological network by adding and protecting ecological sources, repairing ecological breakpoints and building stepping stones. This study is of guiding significance for urban green space system planning, biodiversity protection, and ecosystem function enhancement in Yongtai County, and also provides reference for ecological protection and optimization in other mountainous cities.

This paper aims to propose an approach to automatically identify historic villages from remote sensing images based on deep learning algorithm and accurate