This study investigates the global status of sustainable energy use in urban built-up areas (UBAs), addressing a critical data gap for achieving Sustainable Development Goals. By integrating multi-source remote sensing and gridded data from 2001 to 2019 regarding GDP, population, electricity, and carbon emissions, the researchers constructed a Sustainable Utilization Energy in Urban Built-up Areas (SUEUBA) index for 41 countries. The analysis reveals a steady global improvement, characterized by consistent progress in developed nations and a polarized performance among developing countries, where some show rapid growth while others stagnate. Major economies face distinct challenges due to complex socioeconomic conditions. These findings underscore the urgent need for differentiated policy strategies—ranging from infrastructure upgrades in high-income regions to expanded renewable access in rapidly urbanizing areas—and provide a scalable framework for monitoring and guiding sustainable urban energy transitions.

Extreme heatwaves intensify urban heat islands and pose increasing risks to urban sustainability and human health. However, how urban morphology is associated with daytime and nighttime land surface temperature (LST) across urban functional zones (UFZs), particularly under heatwave conditions, remains insufficiently understood. To address this gap, this study integrates daytime and nighttime LST data derived from SDGSAT-1, multi-dimensional urban morphology indicators, and two interpretable ensemble models (XGBoost and GWRF) to investigate overall sample-level nonlinear model-based associations between urban morphology and LST and to explore spatial variation in local predictor importance within Beijing and Nanjing, China. Because the daytime and nighttime scenes were not always paired within the same heatwave episode, the analysis focuses on selected heatwave-condition observations. The results show marked contrasts between the selected daytime and nighttime observations in UFZ-level thermal patterns. Industrial zones generally exhibited the highest daytime LST, whereas residential zones showed the highest nighttime LST. Building density was identified as the primary model-based predictor of daytime LST in both cities, although its association with LST was nonlinear and varied across density ranges. In contrast, nighttime LST was characterized by more heterogeneous predictor associations, involving vegetation structure, sky openness, building form, anthropogenic indicators, and material-related variables, with their relative importance differing across cities and UFZ types. Local predictor-importance patterns also varied across neighborhoods, cities, and observation times, indicating that model-identified locally important predictors were not spatially uniform within each city. These findings highlight the potential of SDGSAT-1 daytime and nighttime thermal observations and interpretable machine learning for screening candidate local thermal priority areas and key morphology-related factors under heatwave conditions.

The mapping and monitoring of urban green space (UGS) are of great significance for ecological assessment and sustainable development in urban settlements. However, for fine-grained classification tasks in high-resolution remote sensing imagery, existing methods suffer from significant challenges due to the high spectral similarity between low-growing and dense vegetation, as well as the complexity of spatial structures. To overcome these challenges, this paper proposes a Dual-Encoder Multi-Source Feature Fusion Network (DMSF-Net) for fine-grained urban green space segmentation. The proposed method constructs a parallel encoding structure for RGB and auxiliary features (NDVI and LBP), introduces an Adaptive Feature Fusion Module (AFFM) during the encoding phase to achieve dynamic weighted fusion of cross-source features, and designs a Boundary-Aware Up-Sampling Module (BAM) during the decoding phase to strengthen the representation of complex boundary regions through joint modeling of regional semantics and boundary information. Experimental results on a self-constructed UrbanGreen dataset and the publicly available Vaihingen dataset demonstrate the superior performance of DMSF-Net over existing mainstream methods across several evaluation metrics, achieving mIoU values of 82.27% and 74.73%, with improvements of 1.07% and 0.57% over the best baselines, respectively. The model demonstrates particularly strong discrimination capability for the fine-grained category of low vegetation. Ablation experiments further validate the usefulness of each structural module, with AFFM playing a key role in overall performance improvement, while the BAM improves boundary delineation as observed in visual comparisons. Through the synergistic integration of multi-source feature information and structural optimization, DMSF-Net effectively enhances fine-grained UGS segmentation in complex urban scenes, thereby providing an effective approach for high-resolution remote sensing-based urban ecological monitoring.

To unlock the potential of high-resolution nighttime light (NTL) data, robust compositing methods are required. We present an automatic and scalable method for high-resolution NTL data compositing, demonstrated using SDGSAT-1 data. It operates at the pixel level by ranking structural image features across a temporal stack and selecting the observation acquired under the most favourable conditions. Unlike workflows that rely on external cloud masks and physical atmospheric correction models, it uses only internal image characteristics and stationarity metrics to mitigate contamination from clouds, haze, moonlight reflection, and sensor artefacts. The resulting composites show strong agreement with established, annual VIIRS products used as independent external benchmarks (correlation up to 0.95, R-2 consistently >0.80), while retaining a spatially crisper signal than VIIRS at a common aggregated scale (e.g. 800 m). The method also improves SDGSAT-1 usability by suppressing acquisition-dependent artefacts, including scene anomalies and inter-band RGB misregistration, and by improving spatial alignment: mean positional error is reduced from >340 m in the input data to 19.2 m in the composite. Internal geometric consistency improves markedly, with mean inter-band RGB misregistration decreasing from 47.6 m to 3.6 m. The workflow also introduces a taxonomy combining NTL brightness, temporal stationarity, and built-up area presence. For the Po Plain (Italy), the stationary NTL domain covers similar to 10% of the area yet contains similar to 60% of total light emissions; within it, 73.6% originate from built-up areas and 26.4% from non-built-up infrastructure (e.g. lit roads). Overall, the method supports integration of SDGSAT-1 data into global monitoring frameworks.

Building height stands as a vital vertical representation of urban morphology and is closely linked to the development of sustainable cities. However, accurately mapping building heights over a wide area at a fine scale remains challenging due to the high costs of field data acquisition, the loss of spatial details in large-scale mapping, and the underestimation of high-rise buildings. To tackle these challenges, this study develops a novel Tri-Modal Height Estimation Network (TMHEN) and a Cross-modal Adaptive Enhancer (CAE) module. Leveraging SDGSAT-1 Glimmer imagery, Sentinel-2 MultiSpectral Imager (MSI) and Sentinel-1 Synthetic Aperture Radar (SAR) data, building height maps with 10-m resolution were derived. The nighttime light (NTL) imagery of SDGSAT-1 is introduced for the first time in building height estimation. Trained on building height data collected from 61 cities nationwide, our model achieves a satisfactory accuracy, with the root mean square error ranging from 2.05 m to 7.87 m and a mean absolute error from 0.67 m to 2.71 m. Our results exhibit notable consistency with the reference data and outperform existing state of the art products in capturing rich spatial details. The incorporation of high-resolution NTL data effectively mitigates the underestimation primarily caused by SAR backscatter, reducing residuals by 13.01% and 17.98% compared to models utilizing lower-resolution NTL data or no NTL data, respectively. The proposed TMHEN is applied to five major Chinese urban agglomerations, revealing the diversity of urban vertical forms and distinct development patterns. The high-resolution building height maps provide scientific insights to the evaluation of SDG 11 indicators towards a more comprehensive understanding of urbanization processes. The code of TMHEN is provided at https://github. com/lzlhome/Tri-Modal-Height-Estimation-Network.

Highlights What are the main findings? What are the implications of the main findings?Highlights What are the main findings? What are the implications of the main findings?Abstract Climate change is amplifying heat-related health risks, making heat health risk assessment increasingly important for sustainable urban development. However, current studies still face three challenges: (1) macro-scale and fine-scale assessments remain weakly linked; (2) nighttime heat health risk has received limited attention; and (3) dominant factor identification remains insufficient, especially within the Local Climate Zone (LCZ) framework. To address these gaps, this study developed a hazard-exposure-vulnerability-based, multi-scale framework for assessing nighttime heat health risk in Shandong Province, China. At the macro scale, MODIS nighttime land surface temperature (1 km) was used to characterize heat hazard, and district-level risk was assessed by integrating socio-statistical data. Hotspot analysis was then applied to identify high-risk clusters and select cities for fine-scale assessment. At the fine scale, SDGSAT-1 thermal infrared data (30 m) were used to characterize intra-urban nighttime heat hazard, and block-level risk was assessed by integrating socioeconomic and urban infrastructure data. Dominant risk factors were further identified for each spatial unit. Results show that (1) at the macro scale, high nighttime heat health risk districts are concentrated mainly in southern Shandong and major urban cores; (2) at the fine scale, overall risk is higher in inland cities than in the coastal city, and the inland cities show similar spatial patterns; (3) at both district and block units, higher risk levels are associated with more complex dominant factor configurations; and (4) compact high- and mid-rise zones (LCZ 1-2) are mainly characterized by multiple dominant factors, whereas open low-rise/sparsely built zones (LCZ 6/9) are mainly characterized by no dominant factor. This study provides a multi-level perspective for heat-risk governance, offers a scientific basis for both macro-scale policy formulation and fine-scale intervention, and contributes to more sustainable and resilient cities.

Urban expansion has exacerbated the urban heat island (UHI) effect, endangering public health and urban ecosystems. While urban spatial morphology (USM) has a substantial influence on land surface temperature (LST), the varying effects across Global South cities remain poorly understood. This study investigates 2D/3D USM-LST relationships in the urban core areas of four South Asian cities using SDGSAT-1 high-resolution LST data and eleven USM metrics. Stepwise multiple linear regression is applied alongside XGBoost-SHAP interpretation to provide linear baseline comparisons and enhance interpretability. The building density (BD; Pearson's r = 0.60-0.71) and building volume (BV; r = 0.22-0.68) are significantly related to elevated LST, while vegetation volume (VV; r = -0.38 to -0.15) provides substantial cooling in all urban cores. Building volume has emerged as the dominant driver of increased LST in Karachi, Faisalabad, and Gujranwala, whereas building height is the primary factor in Lahore. For cooling effects, the pervious surface fraction is the key factor in all cities except Gujranwala, where the vegetation structure (volume and height) prevails. Furthermore, the relationship between the average building height and LST showed an inflection-like pattern in Karachi. These findings provide actionable insights for promoting heat-resilient urban planning through targeted morphological interventions.

Significant progress has been achieved in the applications of multisource datasets, comprising satellite observations, geophysical measurements, geochemical analysis, and geological information, for mineral prospectivity research. However, conventional mineral exploration techniques are increasingly challenged in complex geological settings, especially for deep-seated or concealed deposits, due to their limited capability to integrate and interpret highly heterogeneous multi-source datasets. Deep learning, as a state of the art methodology, can learn joint representations from such heterogeneous Earth observation and geoscientific data, integrate subtle spectral, spatial and structural patterns, and thereby support more efficient and targeted field campaigns by prioritising prospective areas and reducing unnecessary ground surveys. In this systematic review, 349 studies on deep learning for mineral exploration published between 2018 and 2025 are examined. A stage-dependent data framework is proposed to detail how data requirements evolve from regional reconnaissance to deposit-scale targeting. Subsequently, we critically evaluate major deep learning architectures and relate their specific strengths to distinct data characteristics, such as spatial grids, sequences, and graph topologies. Special attention is given to multisource fusion strategies, emphasizing the necessity of rigorous spatial consistency and physical complementarity. Furthermore, persistent challenges limiting operational uptake are identified, including discovery bias in label representativeness, class imbalance, interpretability, and cross-region generalization. Finally, emerging frontiers are discussed, including the role of geospatial foundation models and Large Language Models in automating knowledge extraction.

The city emission function (CEF) characterizing the angular distribution patterns of urban nighttime light (NTL) emissions, plays a decisive role in modeling the night sky radiant intensity. However, seldom studies have improved the CEF incorporating the vegetation phenological characteristics. The multiangle, high-frequency NTL observations from the visible infrared imaging radiometer suite provide vital data support for estimating CEF coefficients. In this study, we developed a satellite-derived NTL model, which is a function of viewing zenith angle (VZA) and normalized difference vegetation index (NDVI). Based on this model, we performed angular normalization on Black Marble time series (2016-2018) for 11 deciduous vegetation-dominated study areas across North America. The proposed approach yields two main outcomes: 1) high-frequency pixel-level CEF coefficients, and 2) angular-normalized NTL time series, which were evaluated against near-nadir monthly composite products using two metrics, the coefficient of determination (R-2) and the root mean square error (RMSE). The results demonstrated that 1) the magnitude of the normalized CEF tends to decrease with increasing VZA and increase with rising NDVI, 2) angular normalization reduced the impact of VZA on NTL temporal dynamics, and 3) the addition of vegetation characteristics improved the accuracy of angular normalization algorithms, yielding an average increase in R-2 of 0.028 and a decrease in RMSE of 0.166 nW/sr. This study provides an effective approach to estimating urban emitted lights using NTL remote sensing data, and is expected to provide insights into urban environmental monitoring and sustainable lighting management.

The evolution of land use patterns and the emergence of urban heat islands (UHI) over time are critical issues in city development strategies. This study aims to establish a model that maps the correlation between changes in land use and land surface temperature (LST) in the Mashhad City, northeastern Iran. Employing the Google Earth Engine (GEE) platform, we calculated the LST and extracted land use maps from 1985 to 2020. The convolutional neural network (CNN) approach was utilized to deeply explore the relationship between the LST and land use. The obtained results were compared with the standard machine learning (ML) methods such as support vector machine (SVM), random forest (RF), and linear regression. The results revealed a 1.00°C–2.00°C increase in the LST across various land use categories. This variation in temperature increases across different land use types suggested that, in addition to global warming and climatic changes, temperature rise was strongly influenced by land use changes. The LST surge in built-up lands in the Mashhad City was estimated to be 1.75°C, while forest lands experienced the smallest increase of 1.19°C. The developed CNN demonstrated an overall prediction accuracy of 91.60

Due to the compounding impacts of urbanization and climate change-induced warming, urban inhabitants face increasing risks of thermal health issues. The use of high-resolution maps that categorize intra-urban thermal environment and Local Climate Zones (LCZ) could enhance the understanding of the correlation between heat-related health risks and microclimates. In this study, a fine-scale heat risk assessment framework was applied in an arid megacity, Karachi, Pakistan. Following Crichton’s Risk Triangle framework, heat health risks were mapped by considering hazard-exposure-vulnerability components at the census ward level. The heat hazard was mapped using SDGSAT-1 thermal infrared data at a 30 m spatial resolution during summer season. Factors contributing most to heat vulnerability were identified as the availability of electricity facilities, bathroom facilities, and housing density, with contribution rates of 47.51 %, 21.86 %, and 8.07 %, respectively. Heat risks were considerably higher for built types (0.16) compared to natural LCZ types (0.07), with 65 % of LCZ 2, 3, 6, and 7 (compact mid-rise, compact low-rise, open low-rise, and lightweight low-rise areas) identified as high-risk areas. To mitigate heat risks, green space should be planned in LCZ2 and LCZ3 characterized by dense population and compact buildings arrangement, and public cooling facilities and infrastructure should be improved in LCZ7 featured with squatter and slum settlements. Urban planners may consider restricting the growth of these areas in newly-developed regions, including encroachments and unplanned settlements, to prevent further exacerbation of heat stress. This study offers a valuable guide for assessing and alleviating heat risks at the community level, thereby promoting the development of heat resilient urban areas.

Heatwave events significantly impact human health, with China facing severe heat-related threats. This systematic review analyzes the spatial-temporal patterns of heatwave risk in China, the driving factors, and mitigation measures. Limitations and future development of heat action plans are also discussed. We applied the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) approach and searched for Web of Science, Scopus, Google Scholar, and China National Knowledge Infrastructure from 2014 to 2024. A total of 107 peer-reviewed articles in both English and Chinese were selected. The measurement of heatwaves varies widely, with the risk triangle of "hazard-exposure-vulnerability" being the most common assessment method. Heatwave risks present significant spatial-temporal patterns at city, regional, and national scales, driven by socioeconomic, demographic, and environmental factors. Mitigation strategies typically involve climate-sensitive planning, public campaigns, and public health interventions. Despite notable progress in heatwave risk assessment in China, further efforts are needed, including compound-risk assessment, mechanism analysis, multiscale assessment, improved evaluation method, and the development of systematic heat health action plans. Findings of this review provide a scientific foundation for location-based policies and offer references for other developing countries to address extreme heat.

The increasing frequency of extreme heat events has resulted in severe and widespread global impacts. Comprehensive heat risk assessment is crucial for providing targeted climate information and services to enhance cities’ adaptation and mitigation capacities. However, the spatial resolution of administrative-level heat health risk assessments is inadequate for identifying intra-urban risk variations. This study developed a risk assessment framework for heat-related health risks integrating hazard, exposure, susceptibility, and adaptability factors. Utilizing geospatial data such as downscaled land surface temperature, gridded socioeconomic data and point of interest data, the heat health risks were evaluated comprehensively at a fine-grained 500-meter grid resolution in the Beijing-Tianjin-Hebei region, China. The results indicated that high-risk profiles were concentrated in the primary urban areas of Beijing and Tianjin. Analysis of Local Climate Zone (LCZ) classifications revealed distinct heat risk patterns across urban morphologies. Compact high-rise built zones (LCZ 1) showed the highest mean heat hazard index (0.82), while natural-type LCZ B areas exhibited the lowest (0.48). LCZ 1 (0.68) and LCZ 2 (0.67) represented the highest heat risk, followed by LCZ 4 (0.60) and LCZ 5 (0.57). To mitigate heat risks, priority measures for reducing ambient temperature and population density should be implemented in LCZs 1 and 2 regions, while LCZs 3, 4, and 5 should prioritize enhancements to healthcare and transportation infrastructure. These fine-scale risk assessment approaches effectively capture local-scale risk hotspots, providing actionable insights for improving heat governance practices and building more thermally resilient cities.

This study proposes a combined prediction model integrating variational mode decomposition (VMD), gated recurrent unit (GRU), and multi-layer perceptron (MLP) to address the low accuracy and poor fitting performance of existing short-term port wind speed prediction models. The model’s performance is evaluated using root mean square error (RMSE) and mean absolute percentage error (MAPE). Experiments were conducted with real-time wind speed data collected from wind speed sensors on large cranes to predict wind speed for the next 10 minutes. Comparative analysis results demonstrate that the VMD-GRU-MLP model achieves higher predictive accuracy for short-term forecasts.

Understanding the spatiotemporal dynamics of vegetation carbon stocks in ecologically functional areas and identifying their driving factors remain crucial for informing ecosystem protection and restoration efforts. The three eco-zones and four shelterbelts (TEFS) region encompasses critical ecological barriers and functional zones in China. Utilizing MODIS NDVI data, alongside climatic and topographic variables, we developed regionally optimized models to estimate net primary productivity (NPP) across the TEFS region from 2000 to 2023. Subsequently, the spatiotemporal variability of vegetation NPP and its associated drivers were explored using trend analysis, correlation, and residual analysis. The results revealed a significant NPP increase in approximately 90% of the TEFS region between 2000 and 2023, with an average annual increase rate of 3.46 gC m-2 yr-1. The most rapid increases occurred in ecological zones along the Yellow River basin. NPP changes were driven by the combined effects of climate change (CC) and human activities (HA) over the 24-year period. While CC contributed positively to NPP changes in 67.9% of the total area, HA had a positive impact in 75.4% of the region. Notably, HA dominated as the primary driver in western regions, whereas CC exerted a stronger influence in many eastern areas. Enhanced efforts in desertification control and protection of coastal wetland ecosystems are recommended to improve carbon sequestration potential.

Tracking progress toward sustainable urban development requires detailed assessments of key indicators to support evidence-based policy and planning. However, data limitations often constrain evaluations of Sustainable Development Goal (SDG) indicators to national or sub-national levels. This study utilizes global urban spatial products derived from Earth observation data to evaluate the spatiotemporal dynamics of two urban SDG indicators - 11.3.1 (Land Use Efficiency, LUE) and 11.6.2 (annual average concentration of fine particulate matter in cities weighted by population or population-weighted PM2.(5) concentrations, PPM2.(5)) - for over 7000 cities in the Belt and Road region between 2000 and 2020. The results show that 30.6% of cities improved LUE from 2010 to 2020 compared to 2000-2010, while 24.3% experienced deterioration. For PM2.(5) exposure, 67.8% of cities experienced increased PPM2.(5) by 2020 compared to 2000 levels, with the largest increases occurring in South Asia. The integrated assessment of the two indicators demonstrate the necessity for coordinated strategies that concurrently enhance land use efficiency and strengthen air pollution control measures. These findings demonstrate the value of Earth observation data for revealing regional disparities and informing localized SDG implementation strategies.

A comprehensive understanding of fine particulate matter (PM2.5) distribution is vital for addressing health concerns related to deteriorating air quality. While remotely sensed nighttime light (NTL) observations have proven effective in monitoring PM2.5 concentrations, their coarse resolution limits their ability to capture the fine-scale spatial variations within urban environments. To address this limitation, an improved simple spatial random forest model was employed to estimate PM2.5 concentrations using SDGSAT-1 Glimmer NTL data. The resultant PM2.5 concentration maps, with a resolution of 300 m, were generated for the winter of 2021 (R-2 = 0.81) and cover four urban agglomerations (UAs) in China. Two population-weighted indicators were utilized to assess the nighttime population exposure to PM2.5. The findings suggest that population exposure to PM2.5 is highest in the Beijing-Tianjin-Hebei UA (66.84 mu g/m(3)), followed by Chengdu-Chongqing (CC) (62.66 mu g/m(3)), Yangtze River Delta (52.04 mu g/m(3)), and Guangdong-Hong Kong-Macao Greater Bay Area (33.74 mu g/m(3)). Notably, the CC UA exhibits the highest levels of exposure among children (<= 5 years) and the elderly (>= 65 years). These findings provide valuable insights for policymakers to prioritize pollution control strategies and measures.

Urbanization process significantly alters land use, thereby exacerbating the growth of carbon emissions and climate change-related risks. Understanding the changes in carbon emissions induced by urban land use changes can provide crucial information for developing effective policies for emission reductions. In this study, the change patterns of land use carbon emissions (LUCEs) were evaluated using land cover data and Energy Balance Tables (EBTs) in seven megacities in China in past two decades. Urban expansion projections under the Shared Socioeconomic Pathway (SSP) and Representative Concentration Pathway (RCP) scenarios were combined with the Constant Coefficient Riccati Grey model (CCRGM (1,1)) to predict forthcoming carbon emissions. LUCEs were projected from 2025 to 2040, and the average absolute percentage error of the CCRGM (1,1) was 0.19. The association between land urbanization and LUCEs was examined through the lens of the Environmental Kuznets Curve (EKC). Results indicate that future urban development policies should align with the SSP2-RCP4.5 scenario to effectively achieve carbon emission reduction targets. Beijing and Shenzhen reached their peak LUCEs in 2010, Shanghai and Tianjin in 2015, while Chongqing and Chengdu are expected to peak by 2030, and Guangzhou’s peak is projected to occur after 2030. The association between land urbanization and carbon emissions in Beijing, Chengdu, Shanghai, Shenzhen, and Tianjin follows an inverted U-shaped curve, while in Chongqing and Guangzhou, it forms an N-shaped curve. These findings provide valuable insights for cities facing similar challenges in promoting low-carbon development and formulating land use policies that integrate tenure security considerations.