Xuan Liu

Urban–rural public facility disparity is a systemic challenge that reflects dysfunctional feedback loops within and across social and technical subsystems. Traditional administrative-unit-based analyses cannot capture such systemic alignments. This study applies the marker-controlled watershed segmentation (MWS) algorithm, the Two-Step Floating Catchment Area (2SFCA) method, and spatial clustering methods sequentially to dynamically separate urban from rural areas and assess the urban–rural disparity in public facility provisions within the Chengdu–Chongqing economic circle (CCEC). The results indicate: (1) The distribution of public facilities in the CCEC is characterized by significant spatial inequity, predominantly manifested as a substantial disparity between urban and rural areas. (2) A significant misalignment exists between the supply of public facilities and the demands of vulnerable groups. Rural residents, low-income groups, and elderly people are at a disadvantage in accessing public facilities. (3) Rural residents are concentrated in low-income areas and have the most limited ability to obtain public facility services and resources, especially in terms of healthcare facilities. By replacing predefined administrative boundaries with image-derived functional urban–rural patches, the proposed framework enables a more spatially realistic assessment of urban–rural public facility disparities. This approach provides a transferable tool for system-level decision-making in regional planning, particularly for targeting resource allocation in underserved areas.

Geographic artificial intelligence (GeoAI) is reshaping how we observe, understand, and govern land systems

In certain newly established or niche e-commerce platforms, user–item interactions are often exceedingly sparse due to limited user bases or specialized product lines, posing significant obstacles to accurate personalized recommendations. To address these challenges, this paper proposes an enhanced recommendation approach based on a latent factor model. By leveraging factorization to uncover the hidden features of users and items and incorporating both user behavioral data and item attribute information, a multi-dimensional latent semantic space is constructed to more effectively capture the underlying relationships between user preferences and item properties. The method involves data preprocessing, model construction, user and item vectorization, and semantic-similarity-based recommendation generation. For empirical validation, we employ a real-world dataset gathered from an e-commerce platform, comprising 4645 ratings from 3445 users across 277 items in nine distinct categories. Experimental results demonstrate that, compared with conventional collaborative filtering methods, this approach achieves superior precision and recall even in highly sparse settings, showing stronger resilience under low-density conditions. These findings offer objective and feasible insights for advancing personalized recommendation techniques in newly established or niche e-commerce platforms.

Understanding the status and progress of tourism is a critical step for formulating sustainable tourism strategies. A traditional statistical data-based evaluation of tourism development is costly and time-consuming. Recently, remote sensing data and geospatial big data allow the rapid and convenient observation of socioeconomic development and provide opportunities for the cheap and updated analysis of tourism development. This study develops a tourism development index to quickly catch the development status of tourism in one city with open-access night-time lighting (NTL) data and point-of-interest (POI) data. The index is applied to evaluate the tourism development in Yunnan Province, a less-developed region in China, and compared with the traditional statistical data-based evaluation. The results show the following: (1) The index constructed with open-access data offers a cheap and fast way to evaluate the status of tourism development and could obtain a result similar to the traditional statistical data-based method. (2) Tourism development in Yunnan Province is uneven, with two tourism centers significantly surpassing the others: Kunming and Lijiang–Dali. (3) An increasing polarization has characterized the progress of tourism among cities in Yunnan Province over the years. This study is an attempt to rapidly evaluate tourism development using only open-access data, which could play a positive role in saving public management costs in less-developed areas.

The graduate approach applied in China for the economic transition poses the risk of continued government influence on the market. The land reform and the following adjustment in China have introduced a seemingly complete market for residential land. However, a widely practiced coalition between the local developmental states and developers might impact residential land leasing in a more hidden way. Taking central Chengdu as the study area, this study takes the enterprise ownership and affiliations as two explanatory factors that impact the land leasing prices and builds an MGWR model to evaluate the premium of political connections for the developers to obtain the land. The result gives a clue to the local protectionism and preference for state-owned enterprises that might exist in land leasing in Chengdu. It is proved in this study that the average purchase price by state-owned enterprises is 8.9% lower than the prices that private enterprises could enjoy, and the average land leasing price by local enterprises is 14.2% lower than that enjoyed by non-local enterprises. The preceding conceptual and empirical discussion in this study advocates for a review and rethinking of the public sector’s intervention in China’s land market. In-depth analyses of the factors that define the land leasing behaviors of the local government are needed.

The rapid development of artificial intelligence technology has had a huge impact on the fields of computer vision, natural language processing, and geographic information applications

Geospatial artificial intelligence (Geo-AI) methods have revolutionarily impacted earth observation and remote sensing

In recent years, with economic development, urbanization has been accelerating. In the past 100 years, the global average temperature has increased by 0.5°C, and according to the predictions of most global climate models, the temperature will continue to increase by 1.5°C to 3.0°C in the next 100 years. Under the influence of global warming, the urban heat island effect problem is becoming more and more serious, bringing much harm. Studying the thermal effect and its influencing factors is of great significance for sustainable urban development. In this study, the seasonal and interannual surface temperature changes of the study area are inverted based on the SW-TES algorithm, and the LST inversion of the algorithm is simply verified. At the same time, a cell dichotomous model was established to explore the influencing factors of the urban heat island effect and the influence of different land use types and normalized vegetation indices in the Hangzhou metropolitan area was analyzed. The results showed that the overall heating trend of the study area showed a heating trend, the expansion rate of regional construction land was relatively fast, and the scale of urban land was increasing. Based on the results of surface temperature changes of areas with different land types, we obtained the temperature trends of each land type [from 2005 to 2018] and found that there was a negative correlation between surface temperature and normalized vegetation index. This study provides a theoretical basis to evaluate the urban heat island effect and analyze factors that impact it and would promote sustainable urban development.