Accurate prediction of urban land use changes at fine spatial scales is essential for developing healthy and sustainable cities, yet traditional simulation models struggle to capture local dynamics due to limited availability of fine-grained data and insufficient complexity in modeling urban systems. To address these limitations, we propose a novel approach that leverages advances in pre-trained vision-language foundation models combined with spatial dynamic modeling to forecast detailed urban land use patterns. Specifically, we collected a spatially dense collection of street view images (SVIs) throughout Shenzhen, China, and applied UrbanCLIP, a specialized vision-language prompting framework, to perform zero-shot inference of urban land use directly from images without labeled datasets and model retraining. The resulting fine-grained classifications delineate eight distinct urban land use types, producing a detailed urban functional map. These high-resolution patterns were then integrated into a spatial dynamic model enhanced by polynomial regression to simulate urban evolution toward 2035. This approach effectively captures neighborhood influences, socioeconomic drivers, and urban planning policies. Our simulation provides actionable insights for sustainable development in Shenzhen by identifying areas for balanced growth, targeted infrastructure investments, and ecological preservation. Compared to conventional methods, our methodology significantly improves predictive accuracy and spatial granularity. By incorporating foundation models, our approach addresses traditional data constraints, offering scalable and robust tools for informed urban governance and decision-making. • Proposed a VLM-enhanced framework to predict fine-grained urban land use changes. • Achieved zero-shot land use inference based on street view images. • Produced high-resolution simulations of Shenzhen's urban dynamics toward 2035.

Different land use types around megacities contribute contrasting heavy metal pollution and health risks in soil-leaf vegetable systems.

Agricultural and urban land use intensifies riverine GHG emissions across continents.

Decoding Climate-Zone-Specific Nonlinear Interactions Between Urban Morphology, Vegetated Coverage, and Land Surface Temperature for the United States

Systemic inflammation during pregnancy is associated with adverse health outcomes for both mother and child. C-reactive protein (CRP) is a widely used biomarker of inflammation, and its levels may be influenced by environmental factors. This study examined the association between 26 components of the external urban exposome-including air pollutants, land use, and access to green and blue spaces-and CRP concentrations in 1547 pregnant women from the INMA birth cohort in Spain (Gipuzkoa, Sabadell, and Valencia). Environmental exposures during the first trimester were assessed using GIS-based indicators and land-use regression models, and were grouped into low, moderate, and high exposome clusters using hierarchical clustering on principal components. Associations between exposome clusters and CRP were evaluated using multivariable linear regression models and meta-analyses, adjusting for maternal and lifestyle covariates. No significant associations were found between exposome clusters and CRP levels. However, specific air pollutants-fine particulate matter (PM2.5: 1.08% increase per unit; 95% CI: 1.02-1.15) and nitrogen oxides (NOx: 1.03%; 95% CI: 1.00-1.06)-were positively associated with CRP. No associations were observed for green space indicators or other built environment variables. CRP concentrations also varied by region, with the highest levels observed in Valencia (3.2±4.6mg/dL). These findings suggest that while overall urban exposome profiles may not predict systemic inflammation, individual air pollutants such as PM2.5 and NOx are key contributors. Targeting these exposures in maternal health strategies may help mitigate inflammation-related risks during pregnancy, supporting the need for more detailed and component-specific exposome assessments.

Spatial correlation network of urban construction land allocation and carbon emission reduction coupled with high-quality economic development

Analyzing urban sprawl in response to land use land cover change dynamics in Areka town and surrounding area: Wolaita Zone, Ethiopia

In densely populated megacities of the global south, rapid urbanization and limited land availability pose significant challenges to socially just and environmentally resilient redevelopment. Transit-Oriented Development (TOD) is often promoted as a compact, mixed-use alternative to car-oriented sprawl, yet its implementation unfolds through contested stakeholder politics that shape who bears costs and who captures benefits over time. This study examines how key stakeholders—including authorities, landowners, developers, and academicians—perceive and negotiate TOD-based redevelopment in Dhaka, Bangladesh, focusing on conflicts around land consolidation, distrust, governance fragmentation, and risks of exclusion and gentrification. Drawing on qualitative methods such as key informant interviews, participatory appraisal, matrix‐based prioritization of obstacles, and SWOT analysis across three TOD typologies, the research identifies how power asymmetries and institutional fragmentation constrain inclusive sustainability, just transition, and long-term socioecological transformation. The findings reveal that governance fragmentation, institutional distrust, and exclusion of vulnerable groups constitute more severe obstacles than technical or financial constraints. Given severe data limitations—notably a very small landowner sample and reliance on perceived rather than observed outcomes—the findings are interpreted as exploratory insights into how TOD shapes future urban inequalities and environmental performance, rather than as statistically generalizable evidence. Policy implications are framed as three conditional pathways: (1) Equity-contingent pathway suggest strategical involvement of vulnerable groups when power asymmetries are high; (2) Conflict-responsive pathway promotes transparent decision-documentation systems to address diverge interests; (3) Scale-dependent pathway requires nested governance structures linking neighborhood, municipal, and regional decision-making of TOD implementation.

Cooling varies with green space characteristics: Unraveling nonlinear spatial heterogeneity in cooling effects of urban green spaces with geographic explainable AI

The phenomenon of political interest acquisition by urban officials profoundly affects the development of cities around the world, but there is a lack of sufficient research on how political interest acquisition affects the utilization of urban resources. This study aims to extend the understanding of this issue by viewing city officials’ promotion competition as a manifestation of political interest acquisition and investigating the impact of city officials’ promotion competition on the utilization of urban land resources. We theoretically deduce the impact of city officials’ promotion competition on city fiscal pressure, which ultimately affects how cities can obtain income from land and dispose land income. To measure the promotion competition incentives, fiscal pressure, and utility of urban land revenue for empirical analysis, a series of quantified indicators are constructed correspondingly. By employing an integrated empirical approach, including generalized method of moment (GMM) regression, mediation effect, and threshold models, and samples of 251 prefecture-level cities taken between the Years 2009 and 2017, the proposed mechanism is examined. The findings indicate that the risk intensity of city officials’ promotion competition generally reduces the efficiency of cities in obtaining land transfer income and leads to an unreasonable use of land income. Additionally, moderated by a dynamic fiscal pressure, officials’ promotion competition exhibits a negative–positive–negative and negative–positive nonlinear characteristic in the impact on rationality of land revenue and expenditure, respectively. The core conclusion is that increasing incentives for political interest can systematically undermine the utility of scarce resource allocation in urban development, whereas explicit constraints on official authority help mitigate this negative effect. The empirical pieces of evidence from China enlighten two fundamental approaches for other countries to alleviate the threats of political interest competition on urban development: sustainability-oriented political incentives and explicit constraints of power or political instruments. This study also inspires urban planning professionals to identify political uncertainty and craft land-use strategies that remain sustainable and adaptive amid leadership changes.

The impact of land use change awareness on the psychological adaptation of migrant communities in Khulna city

Can nature-based solutions improve urban land green use efficiency? Evidence from China's National Forest City certification

Does industrial digital transition improve urban land use efficiency? Evidence from Chinese cities

Quantifying zonal interdependencies in Urban Land Valuation: A novel geospatial model of infrastructure density and road network synergies

STHG-MSGNN: A Spatiotemporal Heterogeneity-Guided Multi-Scale Graph Neural Network for large-scale urban land subsidence prediction

Holistic assessment of India's water security using coupled climate-human intervention models.

Unveiling the coupling relationship between city size and economic efficiency of urban land use in China: A spatiotemporal evolutionary perspective

Long-term land use projections are essential for food security planning, conservation policy, and sustainable development, yet forecasting frameworks applied to the complete historical record of United States land use remain absent from the literature. Here we present the first comprehensive forecasting analysis of the USDA Economic Research Service (ERS) Major Land Uses (MLU) dataset, which spans 1945 to 2017 across 16 temporal observations for the 48 contiguous states. We develop and compare three forecasting approaches: (1) a Markov chain transition probability model estimated from 15 consecutive period-pairs via constrained least squares; (2) Akaike Information Criterion (AIC)-selected parametric curve fitting among linear, quadratic, logistic, and exponential models; and (3) scenario-modified Markov projections representing business-as-usual (BAU), accelerated urbanization, and conservation pathways. Projections extend 50 years to 2067 with bootstrap-derived uncertainty bounds from 500 iterations. Under BAU, cropland is projected to decline from 20.6% to 17.1% of total land area, forest-use land from 28.0% to 19.3%, while grassland pasture and range increases from 34.8% to 39.8% and special uses from 9.0% to 12.6%. AIC model selection independently identifies logistic saturation curves as the best-fitting model for cropland, forest, and urban land, providing convergent evidence that these major transitions are approaching asymptotic equilibria rather than continuing linearly. Under accelerated urbanization, urban land reaches 6.5% by 2067 with correspondingly greater losses in cropland and forest. State-level Markov models reveal convergence half-lives ranging from 5 to 15 years, demonstrating that the U.S. land use transformation is geographically asynchronous. The proposed framework leverages publicly available census-based tabular data and is designed to complement, rather than replace, remote sensing approaches; it can be readily adapted to any country that maintains periodic census-based or survey-based land use inventories, particularly in contexts where high-frequency national accounting over multi-decadal periods is required.

Precise extraction of buildings from high-resolution remote sensing images is essential for urban analysis and land management. However, accurately extracting buildings as a region of interest (ROI) from remote sensing (RS) images remains challenging. This difficulty arises from the spectral similarity of other objects, such as roads, cars, or trees, along with limited information on building boundaries and small buildings. Traditional image segmentation methods often rely on a fixed threshold value, making optimisation difficult in cases of over-segmented regions. As a result, region merging is subsequently performed on the region adjacency graph (RAG). Consequently, building segmentation in RS images becomes problematic and can lead to inaccurate boundary delineation or region classification. To overcome these limitations, we propose a novel segmentation approach that incorporates an adaptive thresholding optimisation technique and a merging criterion (MC) based on deep features extracted via a convolutional neural network (CNN)-based AttentionU-Net architecture. This ensures that merging decisions are guided by intrinsic region-level characteristics and refined through deep feature representations. Beginning with initial segmentation generated by the simple linear iterative clustering (SLIC) algorithm, the AttentionU-Net architecture is applied to high-resolution RS images to extract deep features, respectively. As a result, our approach combines both low and high-level feature information, reducing misalignment during merging and enhancing traditional region merging strategies. To validate this approach, the WHU buildings’ RS images dataset was utilised. Experimental results demonstrate that our approach achieves superior segmentation accuracy in building delineation while eliminating the need for rigid thresholds. Finally, the results were compared with those obtained using the multiresolution segmentation (MRS) algorithm implemented in eCognition software on the same WHU buildings RS images, where our approach performs better. Specifically, the proposed approach attained a higher segmentation accuracy, with an F-measure of 0. 91 and a goodness of segmentation score Gs of 0.92, compared to 0.52 and 0.83, respectively, achieved by the MRS algorithm.

Assessments on the cooling potential of natural environments in urban areas has largely focussed on green spaces at very specific spatial and temporal dimensions. Less has been studied so far about the surface thermal heat mitigation effect of urban blue spaces across an entire city and for different seasons and years. This study investigates the impact of urban blue spaces, such as lakes and ponds, on surface temperature for the city of Hannover, Germany. Using remote sensing data, we assess how different lake sizes and surrounding urban land use structures influence water surface temperature, surface temperature cooling intensity and distance across seasons and for three consecutive years. Our results indicate that larger lakes consistently exhibit the coolest water surface temperatures and provide the highest surface cooling intensities. The study identifies a case-specific Threshold Value of Efficiency (TVoE) of 0.70ha for surface cooling intensity in the hottest months. We found that high proportions of impervious areas and buildings are associated with increased water surface temperatures and reduced surface temperature cooling effects, while high vegetation close to urban blue spaces show significantly lower surface temperature values. Given our limitations in data availability for particular environmental condition indicators (e.g. wind regime, air humidity) and water body characteristics (shape and depth) probably also influencing the thermal effect of blue spaces, we suggest a multi-method approach combining remote sensing and in-situ based environmental measurements to assess the thermal regulation of urban environments.