Linking urban population exposure to heatwaves with land cover change across the UK

Land cover change and carbon sequestration dynamics in a tropical karst landscape under secondary forest regeneration

Timely and accurate land-cover information is critical for environmental monitoring, sustainable development, and spatial planning. However, existing datasets are often outdated, lack sufficient spatial resolution, or remain inaccessible to non-expert users, limiting their practical value. This study presents the land observation and classification interface (LOCI), a prototype web-based platform developed as a proof of concept for near-real-time land-cover classification and vegetation monitoring. LOCI integrates Sentinel-2 imagery, Google Earth Engine, and a random forest classifier to deliver scalable and interactive land-cover and normalized difference vegetation index products directly through a browser interface. Rather than replicating full spatial digital twin (SDT) systems, LOCI functions as a modular component that enhances SDT ecosystems by providing near-real-time environmental intelligence. The platform's usability and performance are demonstrated through three use cases: (1) identifying cropland preparation and forest clearing as indicators of potential hydrological risk, (2) monitoring land-cover changes, and (3) tracking wetland vegetation dynamics. LOCI achieves high classification accuracy (overall accuracy 92%–93%, Kappa 0.88–0.89) and effectively quantifies relevant environmental changes. These findings demonstrate LOCI's potential to democratise access to remote sensing data and support evidence-based environmental planning. Furthermore, it strengthens integration with SDT frameworks that align with the UN SDGs 6, 11, 13, and 15.

Accurate land cover mapping is essential for environmental monitoring, sustainable land management and georisk assessment. However, the limited spatial representativeness of in situ training data can constrain the performance of machine learning in remote sensing applications. This study improves the positional and spatial accuracy of the Land Use and Coverage Area Frame Survey (LUCAS) dataset, a key European source of land cover mapping data—by replacing individual observation points with automatically generated representative areas that reflect local land cover homogeneity more accurately. When applied to the LUCAS 2018 dataset, the region-growing approach generated spatially representative areas for 86.2% of the points, compared to the 19% coverage provided by existing LUCAS Copernicus polygons. Multitemporal Sentinel-2 classification experiments conducted across five European countries demonstrated consistent accuracy enhancements, with F1 scores increasing from 53.1% to 76.5% when using original LUCAS points to 92.7%–97.3% when using representative areas. The method also outperformed the Sen4Map benchmark dataset. These results emphasize the crucial role of spatially representative training data in enhancing the reliability of machine learning-based land cover classification and change detection. It also provides a robust framework for developing and fine-tuning next-generation Earth observation foundation models.

Heterogeneous change detection (HeCD) enables the identification of land-cover changes using remote sensing imagery obtained from different sensors. Most existing methods overly emphasize modality transformation and shared feature extraction to bridge the gap between heterogeneous images. While these strategies facilitate comparable representations, they tend to neglect the intrinsic characteristics of the changes themselves, which limits their effectiveness in complex scenarios. To overcome this limitation, we propose a change prior-guided image transformation model (CPIT) for unsupervised HeCD. Specifically, starting from the definition of change detection, we analyze the connections among pairwise object relationships, change labels, and change semantics, and then derive change semantic consistency and inconsistency rules solely from the inherent nature of the change detection problem, without relying on data-specific assumptions. These rules are subsequently encoded as change semantic consistency and inconsistency constraints, which, from the perspective of graph signal processing, correspond to low-pass and high-pass spectral properties of the change signals. Finally, by integrating these semantic constraints with sparsity priors and image transformation constraints, we formulate a more precise transformation model for HeCD. Solving this model produces change detection results that conform to the change priors, thereby improving the detection performance. The derivation, formulation, and utilization of change priors in this work offer valuable insights for broader change detection research. Extensive experiments on five datasets validate the effectiveness of CPIT. The code will be released at https://github.com/yulisun/CPIT.

Agricultural land transition in rapidly urbanizing coastal regions poses significant challenges for sustainable land use planning and long-term food security. This study examines the driving forces behind agricultural land conversion in Cilegon City, Banten Province, Indonesia as one of Southeast Asia's most industrialized coastal cities by integrating Remote Sensing (RS), Geographic Information Systems (GIS), and the Analytical Hierarchy Process (AHP) with structured local knowledge elicitation. Land cover classification was performed using Random Forest machine learning applied to multi-temporal Landsat imagery (2011 and 2023), revealing substantial encroachment of non-agricultural land uses. Through pairwise comparison interviews with six domain experts, AHP weighting assigned the highest influence to rainfall (18%), soil quality (15%), and road accessibility (14%) as transition drivers. The resulting transitional suitability map, validated against observed land cover change, achieved an overall accuracy of 88.70% and a Kappa coefficient of 0.86, demonstrating the model's strong predictive capacity. The findings underscore that environmental, infrastructural, and socio-economic factors collectively govern land conversion dynamics. This study contributes a replicable, participatory spatial framework that bridges objective geospatial data with community-embedded knowledge, supporting more inclusive, evidence-based urban planning and agricultural land management in fast-growing coastal cities. Keywords: analytical hierarchy process, coastal city, land use change, local knowledge, remote sensing.

Spatio-Temporal Fusion (STF) has been widely used across various remote sensing applications, including environmental monitoring, land cover change detection, and water resource management by integrating multi-sensor data with different spatial and temporal resolutions. The objective of this study was to generate spatially and temporally fine-resolution imagery and to evaluate the performance of multiple STF algorithms and Consistent Adjustment of the Climatology to Actual Observations (CACAO) post-processing for parcel-level crop monitoring. The study was conducted in a soybean field located in Anseong, South Korea, covering the entire soybean growing season from late June to early November. Near-daily Planet SuperDove imagery with 3m resolution was used to temporally enhance UAV images, which were acquired at 0.05m resolution but only at weekly to monthly intervals. Through the downscaling process, the UAV data were converted into a daily dataset with a target spatial resolution of 0.5m. Relative radiometric normalization was applied, followed by the implementation and comparison of four STF algorithms- Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM), Fitting, spatial Filtering and residual Compensation (Fit-FC), Flexible Spatiotemporal Data Fusion (FSDAF), and Variation-based Spatiotemporal Data Fusion (VSDF)-within a 4-fold cross-validation framework. CACAO post-processing was then employed to reconstruct temporally continuous Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) trajectories, from which the NDVI-based Vegetation Growth Metrics (VGM)85 and the EVI-based VGMmax were derived. The validation results indicated that ESTARFM achieved the highest NDVI performance among the evaluated algorithms, with a Root Mean Square Error (RMSE) of 0.113 and the Universal Image Quality Index (UIQI) of 0.697. CACAO post-processing further improved these results, with CA-ESTARFM achieving an RMSE of 0.108 and a UIQI of 0.740, corresponding to a 4.4% reduction in RMSE and a 6.2% improvement in UIQI relative to the baseline ESTARFM. NDVI histogram and spatial analyses demonstrated that CA-ESTARFM achieved the most consistent agreement with UAV observations while preserving fine-scale spatial heterogeneity. In addition, intra-field vegetation assessment using NDVI-based VGM85 and EVI-based VGMmax showed that CA-ESTARFM remained consistent with simple linear interpolation of UAV observations while retaining finer spatial structure and reducing localized noise in the derived growth metrics. The proposed framework demonstrates strong potential for applications in comprehensive crop monitoring, precision agriculture management, and yield forecasting.

Land use and land cover (LULC) change significantly affects environmental processes and sustainable land management in river basins. The Upper Blue Nile River Basin, Ethiopia, has experienced significant LULC changes due to population growth, agricultural expansion, and deforestation. This study examines past and future LULC dynamic patterns using an integrated cloud-based framework implemented in Google Earth Engine. Classification and regression tree, random forest (RF), and support vector machine classifiers were used to process multi-temporal Landsat imagery. RF achieved the highest overall accuracy (94.4%) and kappa (0.879) in 2024. The results reveal pronounced agricultural expansion and substantial forest loss over the past two decades. Using the RF-derived LULC maps, a Cellular Automata-Markov model was calibrated and validated with strong agreement (Kappa = 0.886) to project future changes. Projections to 2034 and then 2044 indicate continued expansion of agricultural and built-up areas at the expense of forests and shrub/grasslands. The results support improved land use planning and environmental sustainability in the basin.

ABSTRACT Protected areas (PAs) provide critical ecosystem services, including global climate regulation through the retention of carbon in biomass and soil. Evaluating the impact of terrestrial PAs on carbon storage is essential for strengthening their role in mitigating climate change, especially in the face of significant Land Use and Land Cover (LULC) changes, which can influence carbon dynamics. This study focuses on Ifrane National Park (INP) in Morocco, where the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model was used to simulate carbon stock changes between 2018 and 2033, with a particular emphasis on Strict PAs. The results reveal a total carbon stock decline of 14.28% within INP over the study period. Forested areas, especially Holm oak forests, showed notable resilience, with their carbon stocks increasing by 20.79% inside Strict PAs and by 46.63% outside these zones. In contrast, cedar forests experienced a decline of 5.24% within Strict PAs and 17.56% outside. This highlights the significant role of Strict PAs in mitigating carbon losses, especially in vulnerable ecosystems like cedar forests. Our study underscores the need to expand Strict PAs and adopt sustainable forest management to enhance carbon sequestration and support climate change mitigation.

Land-use and land-cover change (LULCC) is a major source of anthropogenic CO₂ emissions, yet projections remain scarce. Here, we use the reduced-complexity Earth system model OSCAR to generate national LULCC carbon emission trajectories through 2100, across 150 socioeconomic and policy-relevant scenarios. Deforestation and forest regrowth dominate variability in LULCC carbon emission, with policy timing and ambition exerting strong control. Ending gross deforestation by 2030 yields large, persistent removals (about -30 Pg C by 2100), whereas net forest area balance still emits 4-9 Pg C. The strongest sinks are projected to emerge in China and Indonesia, while Brazil and the Democratic Republic of the Congo dominate global sources. The accompanying open dataset enables country-level scenario assembly and policy evaluation. Our findings underscore that early and ambitious land governance, particularly in tropical regions, is essential for transforming the land sector into a durable carbon sink aligned with global temperature goals.

Remote sensing has rapidly advanced with the integration of deep learning, enabling more accurate and scalable detection of land use and land cover (LULC) changes, particularly with the increasing availability of Sentinel-1 and Sentinel-2 multispectral imagery. This review traces the evolution of classical machine learning approaches toward modern deep learning architectures, including Convolutional Neural Networks (CNNs), encoder-decoder models, Siamese and dual-stream networks, attention-based frameworks, and, more recently, Transformer-based models. Recent developments in Earth observation foundation models, trained on large-scale, multimodal datasets, have introduced new capabilities, including zero-shot inference, cross-sensor transferability, and improved generalization across diverse geographic regions. Despite these advances, significant challenges remain. The fusion of multimodal data, including optical, SAR, and ancillary sources, is complicated by differences in spatial, spectral, and temporal characteristics. Furthermore, domain adaptation, label noise, and limited geographic transferability continue to constrain the robustness of change detection pipelines. The quantification of uncertainty and model interpretability has also become increasingly important for operational applications in urban planning, agriculture, ecosystem monitoring, and disaster response. In addition, the growing computational and environmental costs of large-scale model pretraining underscore the need for more sustainable AI practices. Future research should therefore focus on advancing the Earth observation foundation and generative models, developing temporal AI methods for long-term sequence analysis, and promoting responsible, energy-efficient geospatial artificial intelligence. Integrating advances in remote sensing, machine learning, and environmental science will be essential for building practical, scalable, and reliable planetary monitoring systems.

ABSTRACT Detention ponds are a key component of urban flood control as they mitigate the additional runoff generated by land-cover changes and the associated reduction in time of concentration. Estimating the required reduction in peak discharge involves hydrological reservoir routing. This study proposes a novel simulation-driven routing methodology based on a modified Rosenbrock numerical scheme to solve the mass continuity equation coupled with the storage–outflow relationship. A key advantage of the proposed approach is its automatic time-step adjustment. Monte Carlo simulations are employed to generate multiple routing scenarios, which are subsequently used to train machine learning surrogate models. Among the evaluated ML algorithms, a Rational Quadratic Gaussian Process Regression model exhibited the best predictive performance. The methodology is demonstrated through a case study of a 17,340 m2 urban catchment. The proposed framework constitutes a practical decision-support tool for engineers and environmental agencies involved in the design and assessment of detention ponds.

ABSTRACT The Brahmaputra River (BR) is one of the world’s most dynamic rivers, and its channel migration significantly impacts the land use and land cover (LULC), and socio-economic stability of Assam, India. This study evaluates LULC changes within the river corridor and their impact on socio-economy of the region. Multi-temporal satellite imagery from 1976 to 2020 was analysed using hybrid classification techniques and manual recoding to map seven LULC classes. River dynamics was quantified through bankline shift and overlay analysis. Results indicate a pronounced south-westward shift of the river, with average bankline shifts of 1.71 km on the left bank and 1.74 km on the right bank. Over 44-years, 1552.2 km2 of land was lost to erosion, while 286.5 km2 was formed through deposition. Erosion severely affected agriculture (705.9 km2), threatening food security and livelihoods, and vegetation (446.3 km2), reducing ecological resources. Critically, Built-up losses (78.7 km2) exposed settlements to displacement and infrastructure damage, representing the most immediate socio-economic impact. Conversely, deposition resulted in constructive change supporting agriculture expansion (131.1 km2), vegetation growth (63.6 km2), and settlement development (17.1 km2). These findings underscore that agriculture, vegetation and settlements, the core socio-economic pillars of Assam’s floodplain communities are directly shaped by river dynamics.

Urban biodiversity has emerged as a major global concern due to rapid urban expansion. Accelerated urbanization in urban towns has caused loss of biodiversity, changes in land use land cover (LULC), and environmental imbalance. This study attempts to capture the ecological uniqueness of four Himalayan towns, i.e. Manali, Kullu, Mandi, and Bilaspur, through an integrated assessment of LULC and floristic diversity assessment. LULC classification was carried out using WorldView and GeoEye imagery (at 0.5m resolution) through image segmentation and random forest classification. It was accompanied by field surveys to assess the floristic diversity in selected towns. Accuracy assessment yielded values above 0.90 for overall accuracy and kappa coefficient, confirming reliability of the results. The results revealed that trees were the dominant land cover in Manali and Bilaspur, whereas grasses in Kullu and buildings prevailed in Mandi. Open lands and water bodies consistently accounted for the smallest proportions. The results highlight the transitional nature of Himalayan urban systems, where vegetation still occupies larger extents than built-up areas, unlike bigger cities. Vegetation surveys using line transects across seven urban habitats identified 731 plant species, with herbaceous species as the most prevalent life form. Chi-square tests illustrated a highly significant association between species presence and habitat type in all four towns (p < 0.01), confirming that species distributions were strongly habitat-dependent. The cluster analysis test demonstrated strong associations between species composition and habitat heterogeneity, reflecting the combined influence of ecological and anthropogenic factors. Floristic diversity analysis indicated wide variations in alpha diversity (28-223 species), high gamma diversity (731 species), and beta diversity (β = 7.13) across habitats. These findings emphasize the need to conserve semi-natural habitats and maintain habitat heterogeneity to balance urban development with biodiversity conservation, thereby sustaining the ecological integrity of Himalayan towns.

An explainable AI approach to deciphering groundwater depth responses to climate variability and human activities in Western U.S.

Contrasting 2001 and 2020 land cover states: Impacts on heterogeneous HONO chemistry and nitrate formation in China.

Land use and land cover change (LUCC) exerts substantial influence on ecosystem service values (ESV). But conventional ESV valuation approaches frequently neglect temporal shifts in crop economic returns. Integrating high-resolution land use data (2000-2020) with the Patch-generating Land Use Simulation (PLUS) model-and augmenting it with spatial econometric analysis-we project 2030 land use configurations under four policy-relevant scenarios: Business-as-Usual (BAU), Economic Development Priority (EDP), Ecological Protection Priority (EPP), and Ecological Economic Balance (EEB). Under EDP, construction land expands by 5.52%, critically low-ESV areas increase by 476.83 km2 (a 2.7-fold surge relative to the 2010-2020 period), and net ESV declines by 1.04%. By contrast, EPP achieves a 10.19% reduction in urban land through targeted ecological restoration, effectively arresting ESV degradation. High-value ESV zones are concentrated in water bodies and forests, which dominate regional regulating services. The three-province in the Middle Reaches of the Yangtze River epitomizes the inherent tension between rapid urbanization and ESV conservation. These findings provide a basis for assessing the social, economic and environmental factors. Furthermore, the results provide a new solution approach for formulating differentiated ecological environment protection policies in the study area and addressing key technical challenges in land use planning for large-scale ecological functional area.

Land use and cover change (LUCC) in topographically complex subtropical regions remains poorly understood. This study analyzed spatiotemporal evolution and landscape patterns in Hunan Province (1990–2021) using GEE and Landsat imagery. Results show cultivated land decreased (1990–1996), then increased (1996–2021), while forest land followed an opposite trend. Significant transitions occurred: 31,748.83 km2 of cultivated land converted to forest, and 32,307.35 km2 of forest reverted to cultivation. Impervious surfaces exhibited the highest dynamic degree (5.59), reflecting rapid expansion driven primarily by GDP. Landscape metrics revealed high fragmentation in grasslands, while forest land maintained lower fragmentation but higher fractal dimension. Correlation analysis indicates socioeconomic factors, especially GDP and population density, surpassed climatic variables in impact intensity. Cultivated land area correlated positively with population and temperature but negatively with rainfall and GDP. These findings provide a scientific basis for refined natural resource management and cultivated land protection in subtropical hilly regions.

Unlocking the cooling effect of urban green spaces is an effective strategy to mitigate urban heat islands and extreme heat exposure. However, the cooling potential of optimized green configurations in riparian buffer zones remains largely unknown. In this study, we integrated land surface temperature (LST) data derived from remote sensing, machine learning models, and scenario analysis method to quantify the potential effects of green space configurations in different riparian buffer zones (30–200 m) on urban cooling. We selected three cities, Chongqing, Changsha, and Wuhan as study areas, and found that forests and cropland have cooling effects of −4.08 °C ± 0.71 °C and −2.09 °C ± 0.27 °C, respectively, compared with temperature on impervious surfaces. In addition, our simulated results show that different cities respond differently to the cooling effects of green space configurations. In Chongqing, the riparian afforestation scenario has the potential to reduce citywide temperature by −0.10 to −0.51 °C. In contrast, Changsha and Wuhan exhibit more pronounced cooling effects in rooftop greening scenarios, which have the potential to reduce temperatures by −0.25 °C–1.51 °C. Attribution analysis further indicates that land cover changes, such as afforestation, are the primary drivers of urban cooling, while the cooling mechanisms within riparian buffer zones across the three cities exhibit significant nonlinear interaction characteristics. Overall, our results demonstrate that optimizing green space configurations in riparian buffer zones is one of the key strategies to achieve urban cooling.

ABSTRACT Rapid urbanization, coupled with frequent land-use shifts, has emerged as a primary driver of ecological degradation in the Anthropocene. This study dissects the intricate interplay between land-use and land-cover change (LULC) and ecological environment quality within Hubei Province, a region undergoing rapid transformation, employing a multi-faceted approach that combines remote sensing with advanced statistical modelling. Our analysis reveals that: (1) From 1995 to 2025, Hubei’s land-use trajectory was marked by a dramatic surge in construction land, characterized by an early phase of rapid change transitioning to relative stabilization, while the comprehensive index of land-use intensity paradoxically decreased across prefecture-level cities amidst rapid urbanization; (2) despite a seemingly positive trend of overall ecological environment improvement across the province over three decades, a significant divergence exists between areas of ecological recovery and degradation, highlighting spatial heterogeneity in these responses; (3) Anthropogenic activities are unequivocally identified as the primary drivers of ecological change, exhibiting distinct spatial variability. This trend is projected to result in urban expansion, a marginal decrease in farmland, strengthened protection of forests and wetlands, and an increase in transportation infrastructure across Hubei by 2035. These findings suggest that judicious adjustments to the land-use mosaic offer a pathway to maintaining, or even enhancing, regional ecological integrity, underscoring the urgency for integrated planning and management strategies that balance rapid development with the long-term well-being of the socio-ecological system.