A Multi-scale Object-based Framework for Hierarchical Urban Land Use and Land Cover Classification Using Ensemble Machine Learning and Multi-source Geospatial Data

Microplastics (MPs) are widely distributed throughout freshwater ecosystems and are easily ingested by aquatic organisms. However, the uptake of MPs by freshwater birds and their potentially detrimental impacts on fitness and health remain poorly understood. We collected faecal samples from White-throated dipper (Cincluscinclus) nestlings across Scotland and the Basque Country (Spain), encompassing territories with varying degrees of anthropogenic land use. We analysed MP concentrations in the faeces alongside body condition, a proxy for growth conditions and health during early development. MPs, mostly fibres, were detected in 62.5% of broods, with concentrations positively correlated with urban and agricultural land cover. Despite this, MP load exhibited only a weak association with nestling body condition, likely reflecting underlying variation in diet quantity or quality. Overall, our findings highlight the widespread presence of MPs in freshwater birds inhabiting anthropogenic landscapes but indicate no short-term effects on nestling growth. Further research is needed to understand the long-term health implications of MPs and to determine optimal proxies for assessing their effects on freshwater bird health.

Many countries are concerned by and wish to arrest or reverse what is termed a biodiversity crisis in invertebrates. To understand the issues facing riverine invertebrates in England, a fully integrated dataset where macroinvertebrate monitoring sites were aligned in space and time with physical, geographic, habitat, and chemical factors from 2003 to 2018 (quantitative abundance data being universally available from 2003) was brought together for statistical analysis. Over this period the median abundance either did not change or for some groups actually increased. The aim was to identify what the principal factors were that influenced Ephemeroptera (Mayflies), Plecoptera (Stoneflies), Trichoptera (Caddisflies), Odonata (Dragonflies and Damselflies), Diptera (True Flies), Coleoptera (Beetles), Hemiptera (True Bugs), and Gastropoda (Snails) abundance over this 16-year period. The dataset was examined using an ensemble framework within two modelling approaches: generalised linear mixed-effects models with permutation-based variable importance, as well as non-linear generalised additive mixed models to assess the percentage of deviance explained by each variable. The range of approaches aimed to offer different perspectives on variable importance, providing a more comprehensive understanding of the data and highlighting how model selection can influence ecological data interpretation. For most groups, physical factors, such as altitude, distance from source, slope, bed substrate and flow discharge, were strong predictors of abundance, likely reflecting natural habitat preferences shaped by evolutionary history. Land cover was also influential, with seminatural areas generally supporting higher abundances and urban land cover associated with lower abundances. Some chemical and ecological factors - such as wastewater and nutrient content, were particularly important for Ephemeroptera, Plecoptera, and Trichoptera abundance. For Coleoptera, Hemiptera, Trichoptera, Diptera and Gastropoda, metal levels played a role in their abundance, whilst for Odonata, mean temperature appeared to be important. Diptera appeared to be relatively insensitive to the factors examined. This statistical examination of large monitoring datasets, with no a priori assumptions, is vital in resolving a key challenge in bioassessment: identifying what influences invertebrate abundance when data are sparse. The results can provide policy options to improve ecological conditions, and the approach is transferable to other regions.

Compared with visible-light remote sensing, multispectral remote sensing provides multi-band land surface information and enhances spectral separability through data fusion, thereby enabling more accurate surface representation. However, spectral redundancy, resolution discrepancies, and highly complex urban environments impose greater challenges on existing methods. Deep learning approaches based on convolutional neural network (CNN) offer superior capabilities in extracting and integrating multispectral features, enabling more accurate urban land cover segmentation. This review focuses on pixel-level urban land cover segmentation and systematically summarizes recent advances in deep learning for multispectral remote sensing. First, we emphasize that the rich spectral information and spatial complementarity of multispectral data effectively enhance segmentation performance and alleviate ambiguities caused by the ‘same spectrum-different objects’ and ‘same object-different spectra’. Second, we review 19 publicly available multispectral datasets, highlighting differences in spectral bands, spatial resolution, and application scenarios, and summarize a standardized preprocessing pipeline including radiometric calibration, geometric correction, band normalization, and spectral dimensionality reduction to support reproducibility. Third, we discuss representative spectral-spatial feature extraction and cross-scale context modeling strategies, covering dilated convolution, 3D-2D hybrid structures, dual-branch architectures, and multi-scale enhancement modules. Extensive comparative experiments on ISPRS Potsdam and GID datasets further demonstrate the applicability and performance differences of representative models. Finally, future research trends and directions are discussed, encompassing multi-temporal and multi-scale temporal learning, cross-modal fusion, and the lightweight design of complex models.

The study provides a novel three decades (1993-2022) geospatial investigation on urban heat island (UHI) and land use land cover (LULC) dynamics in the Haldia industrial region, eastern India, revealing the compounded impact of industrialization, urban growth, and vegetation loss on rising surfaces. Using multi-temporal Landsat imagery, the maximum likelihood classifier (MLC) was applied to classify the LULC classes, while indices such as the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), and LST were employed to quantify environmental changes. The results show a 22.59 sq. km expansion in built-up area (1993-2022), accompanied by decreases in agricultural land (29.12 sq. km), fallow land (6.89 sq. km), and vegetation cover (10.72 sq. km since 2011). Directional analysis highlighted north-eastern, eastern, southern, and south-western sectors as hotspots of urban expansion and heat accumulation, driven by population growth, industrialization, and vegetation loss. The gradient distance and direction analysis suggested that the north-eastern, eastern, southern, and south-western parts have experienced urban expansion and were also affected by the heat island due to urbanization, population pressure, industrialization, and vegetation insufficiency. Maximum LST rose from 27.51°C (1993) to 37.13°C (2022), while UHI intensity increased from 9.31 to 12.49 °C over the same period. Correlation analysis revealed positive associations between LST with NDBI/NDWI and a negative correlation with NDVI. The study's novelty lies in its integrated geospatial assessment of three decades of UHI-LULC dynamics in an industrialized region of eastern India, offering critical insights for sustainable urban planning and climate-resilient land-use policies.

Abstract Understanding the contributions of diffuse and point sources to nitrate pollution is crucial for managing river water quality. We conducted a long-term modeling study for the Rhine and Elbe basins and their 146 subbasins from 1950 to 2021 to quantify the roles of diffuse and, in particular, point sources in driving stream NO ₃ –N concentrations. In both basins, simulated results show a decline in point source contributions from 1950 to 2000, followed by a relatively stable level at around 25% in the Rhine and fluctuations around 30% levels in the Elbe. The decline in the simulated stream NO ₃ –N concentrations in both basins after 1990 was largely driven by a decrease in point sources, and stream NO ₃ –N concentrations remained high (∼2 mg l −1 ) during 2010–2021, even when point sources were excluded. At the subbasin level, changes in point source contributions and stream NO ₃ –N concentrations reflected the overall trends of their respective basins, although individual subbasins exhibited diverse patterns. In subbasins with high stream NO ₃ –N concentrations during 2010–2021, point source contribution accounted for around 30% (median values across subbasins), and the fractions of agricultural, urban, and industrial land cover were relatively high. These results highlight that point source management alone is not sufficient to reduce stream nitrate to a good ecological status (< 2 mg l −1 ), and spatial targeted management is required to achieve good ecological status at both the regional and local levels.

Against the backdrop of accelerating global climate change and urbanization, urban land cover change has emerged as a critical indicator for understanding the dynamic evolution of cities and the transformation of urban ecosystems. This study proposes a data-driven framework for fine-scale urban land cover change assessment based on the UASFNet model, enabling high-precision evaluation of urban land cover dynamics. The approach first performs preprocessing and co-registration of bi-temporal remote sensing images from the study area, and applies the trained UASFNet model to identify urban land cover types and extract land cover information for each temporal phase. The Analytic Hierarchy Process (AHP) is then employed to determine the weights of various indicator factors. By integrating building disturbance, greenbelt disturbance, and road disturbance indices, the framework quantitatively evaluates the intensity of land cover change at both pixel and regional scales. Experimental results across three benchmark datasets, consisting of high-resolution sub-meter RGB urban remote sensing imagery, demonstrate that UASFNet achieves superior segmentation accuracy, with mean Intersection over Union (mIoU) values of 91.52%, 93.31%, and 88.90%, substantially outperforming several state-of-the-art baseline models. Spatial analysis of the Langfang urban area (2017-2023) reveals a marked increase in impervious surface coverage (+16.86%) and a sharp decline in greenbelt (-40%), with the urban landscape exhibiting a multi-core, belt-like expansion pattern oriented toward newly developed districts. The proposed framework not only enhances the interpretability and generalization of remote sensing models in complex urban environments but also provides a scalable analytical tool to support urban spatial planning, ecological conservation, and sustainable city governance.

Rapid urbanization is reshaping thermal environments worldwide, with the strongest impacts occurring at the interface between urban and non-urban areas. Impervious surfaces, as key indicators of urban expansion, are critical for monitoring urban growth and assessing surface urban heat island (SUHI) effects. Land use and land cover change (LULCC) provides an essential link between urban dynamics and their environmental and societal consequences. Here, we integrated the U.S. Geological Survey (USGS) Climate Global Issues (CGI) Land Cover Product with Landsat thermal time-series to investigate SUHI evolution in two contrasting metropolitan regions: Wuhan, China, and Brasília, Brazil. Using data spanning 1986–2023, we analyzed the relationships between land cover, Landsat-based land surface temperature (LST), and SUHI intensity, and identified persistent thermal hotspots. Results demonstrate that the land cover data utilized increases the accuracy of impervious surface mapping along urban–rural gradients. Average SUHI intensities were 3.4 °C in Wuhan and 3.3 °C in Brasília, with statistically significant warming trends of 0.04 °C/year and 0.01 °C/year, respectively. Maximum temperature proved to be a robust indicator of SUHI intensification, capturing long-term upward trends. Our findings highlight the important role of urban land cover dynamics in shaping temporal SUHI variability and hotspot emergence. This prototype framework demonstrates the scientific and policy value of combining long-term land cover monitoring information with satellite thermal monitoring to quantify and track SUHI at city scale, supporting sustainable urban planning and climate adaptation strategies.

In recent years, semantic segmentation of remote sensing images using deep convolutional neural networks (CNNs) has seen rapid development in fields like urban planning and land cover analysis. However, reliance on a single imaging modality is often hampered by spectral ambiguity, the absence of elevation cues, and geometric confusion, limiting the discrimination of spectrally similar yet distinct categories like roads versus roofs. While multisource data fusion has emerged as a promising solution, effectively leveraging complementary information from multimodal features remains challenging. To address these challenges, we propose a multimodal fusion and multilayer interaction network (MFMINet), a two-way encoder-decoder network. Our model employs a multimodal cross-layer fusion module (MCFM) to integrate high-level semantic information with low-level spatial details, exploring the complementarities between different information modalities. Additionally, we introduce a self-attention module (SAM) to capture long-range spatial dependencies and refine fused features. Additionally, we develop a feature enhancement module (FEM) that intelligently selects between Transformer blocks for narrow channels and CNN blocks for wide channels, followed by point-wise convolution for optimal feature integration. Furthermore, we propose a dual spatial awareness module (DSAM) to mitigate downsampling effects and process global multiscale contextual information. Extensive experiments on ISPRS Vaihingen and Potsdam datasets demonstrate superior performance, with mIoU reaching 89.96% and 88.24%, respectively, validating the effectiveness of our method.

Intensifying urbanisation in the Arctic, particularly in spatially constrained coastal and island cities, requires reliable information on long-term land-use/land-cover (LULC) change to assess environmental impacts and support urban planning. However, multi-decadal, high-resolution LULC datasets for Arctic cities remain limited. In this study, we quantify LULC change on Tromsøya (Tromsø, Norway) from 1984 to 2024 using a Random Forest classifier applied to multispectral satellite imagery from Landsat and PlanetScope, complemented by LiDAR-derived canopy height models (CHM) and building footprints. We mapped LULC change trajectories and examined how these shifts relate to district-level population redistribution using gridded population data. The integration of a LiDAR-derived CHM was found to substantially improve the accuracy of Landsat-based LULC mapping and to represent the dominant source of classification gains, particularly for spectrally similar urban classes such as residential areas, roads, and other paved surfaces. Landsat augmented with CHM was shown to achieve practical equivalence to PlanetScope when the latter was modelled using spectral features only, supporting the feasibility of scalable and cost-effective long-term monitoring of urbanisation in Arctic cities. Based on the best-performing Landsat configuration, the proportions of artificial and green surfaces were estimated, indicating that approximately 20% of green areas were transformed into artificial classes. Spatially, population growth was concentrated in a small number of districts and broadly coincided with hotspots of green-to-artificial conversion The workflow provides a reproducible basis for long-term, district-scale LULC monitoring in small Arctic cities where data constraints limit the consistent use of high-resolution image.

Water-quality degradation from nutrient pollution remains a major challenge for resource managers. Developing effective strategies requires tools to characterize nutrient sources and transport. This study used the RSPARROW framework to develop and assess new, smaller-scale models for Total Nitrogen (TN) and Total Phosphorus (TP) transport across Mississippi (MS). These state-level models were built using 15 years (2005–2020) of observation data and considered variables including multiple nutrient sources, land characteristics, and attenuation processes. The MS models demonstrated comparable accuracy to larger regional SPARROW models, validating the use of smaller-scale models for local management. Results showed agricultural sources are the major contributors to TN, dominated by fertilizer in northern MS and livestock manure in the south. Urban land cover also significantly influenced TN and was the second most significant source of TP, following geologic material (background P). Fertilizer and manure were also important TP sources. This study provides valuable, spatially explicit data on nutrient distribution in MS streams, supporting the state’s nutrient reduction planning. It concludes by highlighting the need for future model improvements via updated source data and mean annual flow estimates.

Cloud-based Earth observation platforms, such as data cubes, enable reproducible analyses of long-term satellite time series for climate and urban studies. In parallel, Essential Climate Variables (ECVs) provide a standardised framework for monitoring climate dynamics, with urban land cover and temperature being particularly relevant in historic urban contexts. This study analyses long-term trends and statistical associations between satellite-based ECVs and urbanisation indicators within the Historic Urban Landscape (HUL) of Sfax (Tunisia) from 1985 to 2021. Using the Digital Earth Africa (DEA) data cube, we derived six urban spectral indices (USIs), land surface temperature, air temperature at 2 m, wind characteristics, and precipitation from Landsat and ERA5 reanalysis data. An automated and reproducible Python-based workflow was implemented to assess USI behaviour, evaluate their performance against the Global Human Settlement Layer (GHSL), and explore spatio-temporal co-variations between urbanisation and climate variables. Results reveal a consistent increase in air and surface temperatures alongside a decreasing precipitation trend over the study period. The USIs demonstrate comparable accuracy levels (≈88–90%) in delineating urban areas, with indices based on SWIR and NIR bands (NDBI, BUI, NBI) showing the strongest statistical associations with temperature variables. Correlation and multivariate regression analyses indicate that temporal variations in USIs are more strongly associated with air temperature than with land surface temperature; however, these relationships reflect statistical co-variation rather than causality. By integrating satellite-based ECVs within a data cube framework, this study provides an operational methodology for long-term monitoring of urban-climate interactions in historic Mediterranean cities, supporting both climate adaptation strategies and the objectives of the UNESCO HUL approach.

Grassland restoration and conservation is necessary to retain ecosystem services and biodiversity. Insects are ecologically important yet often not the focus of restoration. Beetles in the family Carabidae (carabids) are frequently studied after restoration, but the effects of grassland restoration on beetles in the family Scarabaeidae (scarabs) have not been extensively studied despite high scarab diversity in grasslands. Investigating the effects of restoration on carabids and scarabs can inform restoration plans and conservation of these diverse and ecologically influential taxa. Further, most research on beetle responses to grassland restoration have occurred in Europe or the Great Plains of the United States. We investigated how carabids and scarabs were associated with management practices, local landcover, habitat features, and Red Imported Fire Ant ( Solenopsis invicta ) density in an understudied grassland system in the southeastern United States, the Black Belt Prairie. We collected beetles from 24 sites and analyzed morphospecies‐level data with occupancy models and family‐level data with abundance models. Vegetation diversity, burn frequency, agricultural landcover, and disturbed landcover were positively associated with occupancy probability, while urban landcover was negatively associated with occupancy probability. We found positive relationships between the occupancy probability of some morphospecies and tree basal area, time since burning, and seeded restoration and negative relationships between occupancy probability and these covariates for other morphospecies. Our results indicate S. invicta had a direct negative relationship with carabids and scarabs. We identified potential relationships carabid and scarab morphospecies have with habitat and management that can direct future research and support management and restorations of grasslands.

Abstract Insectivorous, Afro‐Palearctic migrant birds provide cross‐border ecosystem services, but many are declining rapidly. The complex life cycle of migrant birds makes their conservation difficult, but understanding where they spend time during the breeding season can help indicate where those actions will be most effective. We used the spotted flycatcher ( Muscicapa striata ), a declining, Afro‐Palearctic, migratory insectivore and habitat generalist, as a model to examine how river density and land‐cover change were associated with loss and colonization during the breeding season of 2 × 2‐km national atlas survey areas from 1990 to 2010. Greater river density was associated with a lower probability of loss (odds ratio [OR] 0.8) between survey periods and a higher probability of colonization (OR 1.25). Loss was associated with increases in urban land cover (OR 1.17), and, unexpectedly, colonization was negatively associated with increases in woodland (OR 0.91) and standing freshwater (OR 0.94). Our results suggest that habitat creation is unlikely to provide sufficient benefits for some insectivorous birds within the time needed for population recovery. Thus, efforts should focus on the protection and improvement of established habitats. River density was strongly associated with the persistence of the spotted flycatcher, and this finding highlights that understanding the benefits of freshwater habitat for terrestrial species should be a priority for conservation management.

The accurate land use and land cover (LULC) classification in the data-scarce urbanized region of Peshawar remains challenging due to computational limitations, accuracy assessment, and traditional techniques. This study, for the first time, addresses this research gap by introducing different robust machine learning (ML) algorithms in Google Earth Engine (GEE). The crux of this study is to analyze the comparative performances of four classifiers, namely, classification and regression tree (CART), minimum distance (MiD), random forest (RF), and support vector machine (SVM) within GEE using Sentinel data for reliable LULC classification from 2020 to 2024. The performance of each classifier was evaluated by validation and accuracy assessment. The composed points of each class were run in a scripted code and assigned 70% data for training and 30% for testing. The overall accuracy of RF and CART classifiers was 95% followed by the same values of Kappa coefficients. In contrast, MiD shows the weakest performance. The CART and RF classifiers maintain high producer accuracy (PA, > 90) and user accuracy (UA, > 90) for each class. The classification consistency was confirmed with mean Mathew correlation coefficient (MCC) values of 0.98 (for CART) and 0.99 (for RF), with an average F1 score of over 95%. The McNemar test showed no significant difference between CART, RF, and SVM classifiers; however, the confidence interval (CI 95%) confirmed the superior performance of CART and RF. This study confirms that the selected classifiers are transferable for a complex urban environment.

ABSTRACT Urban land cover doubled between 1985 and 2015, yet the spatial dynamics of urban form remain under-quantified, despite its importance for sustainability, infrastructure planning and climate risk. Urban expansion is a non-equilibrium process shaped by interactions between population growth, infrastructure, institutions and market failures – rendering static and equilibrium models inadequate. We review key challenges and modelling approaches, focusing on partial differential equation (PDE) frameworks. Borrowed from statistical physics, PDEs capture spatial heterogeneity, anisotropy, stochasticity and feedbacks between land use and transport networks. Integrating economic and institutional factors remains a major challenge for policy relevance. We propose a research agenda that bridges remote sensing, urban economics and complexity science to develop dynamic, empirically grounded models of urban expansion.

The invasive bridge vector mosquito Aedes albopictus has been increasingly detected across Europe, posing potential risks for arboviral disease transmission. Urban-scale assessments of its expansion remain scarce in Central Europe. The establishment and spread of Ae. albopictus in Budapest were analysed between 2018 and 2025 using spatio-temporal mapping, seasonal observations, and indicator-based ecological modelling, complemented by ensemble machine learning approaches. Occurrence patterns followed a logistic growth trajectory (R² = 0.995), with colonization rising from sparse foci in 2020 to over 85% of districts by 2025. Seasonal activity extended from late April to mid-October, peaking in early September. Ensemble machine learning models consistently achieved high predictive performance, with key predictors included urban fabric, temperature, topography, and precipitation-related indices (bio18; Köppen Aridity Index) while other factors contributed variably. Ecological associations were strongest with urbanized land cover (discontinuous and continuous urban fabric, industrial areas), specific soil types such as fluvent entisols, and humid temperate climates (Köppen Cfa). K-means clustering and decision tree analyses distinguished seven ecological clusters across Budapest, ranging from warm, densely built urban cores to cooler, shaded peri‑urban and forested zones. Conceptually linking ecological clusters to the Sustainable Development Goals highlighted spatially heterogeneous intersections with health (SDG 3), urban sustainability (SDG 11), water management (SDG 6), climate action (SDG 13), and biodiversity conservation (SDG 15). These findings provide a baseline for predicting urban vector expansion, informing early warning systems, and guiding public health interventions and vector control strategies in European metropolitan regions.

Development and economic growth in Indonesia have experienced rapid progress, followed by urbanization marked by the expansion of urban areas towards the outskirts, and have triggered urban expansion and land cover changes, especially on the outskirts of Surabaya City, and continue to expand to the Gerbangkertosusila area, which can indicate a decrease in Green Open Space (GOS). Given the important role of green open space in the sustainability of metropolitan areas, this study has three objectives. First, to analyze the impact of urban sprawl on GOS with spatial dynamics of land cover changes using Land Use Cover Changes (LUCC) analysis using ArcGIS software. Second, to identify spatial patterns of urban sprawl, and third, to calculate the index sprawl value to determine areas with urban sprawl impacts. The results of our study show that GOS has decreased in 25 years by 9.32%, and built-up area has increased by 8.27% of the total area of Gerbangkertosusila. The patterns of urban expansion that occur are Leap Frog Development, Ribbon Development, and Post- suburbia. The highest area expansion index value is in Sidoarjo at 4.74 and the lowest in Bangkalan at -7.62. The expansion of this area is marked by the development of settlements, industrial areas, and transportation routes, which result in the conversion of green open spaces into Built-up areas. Based on the analysis used in the Gerbangkertosusila area, the concept of Urban Growth Boundaries (UGB) is necessary; this concept effectively addresses urban expansion by establishing urban development permit policies.

Abstract. Urban expansion in India has accelerated significantly over the past two decades, leading to widespread changes in land use and land cover patterns. This study examines the spatiotemporal dynamics of urban expansion and land cover changes from 2001 to 2022 using a dual-resolution geospatial framework. MODIS MCD12Q1 (500 m) data were used for national-scale assessment across twenty Tier- I urban growth centres, while GLC_FCS30D (30 m) data supported high-resolution assessment in the Hyderabad metropolitan region. At the national level, the study revealed a steady increase in built-up areas, often exceeding 30–80% growth across key urban growth centres. Croplands were identified as the primary land category converted into urban use, followed by losses in grasslands and shrublands. The Hyderabad case study demonstrated the limitations of coarse-resolution datasets in detecting fragmented growth and peri-urban development. In contrast, the high-resolution GLC_FCS30D data enabled more detailed mapping of edge expansion, spatial fragmentation, and heterogeneous growth morphology. Unlike prior studies limited to either national or local focus, this work develops a unified, dual-resolution LULC analysis framework with pixel-level transition tracking enables cross-scale insights into urban expansion patterns in India. The integration of both datasets facilitated a comprehensive understanding of urban land changes, combining long-term trend detection with local-level spatial clarity. This approach underscores the importance of resolution–aware methods in urban monitoring and supports evidence–based decision–making in sustainable urban planning, infrastructure development, and land governance. The findings highlight the need for scalable geospatial strategies to address the challenge of rapid urbanization in India, particularly in developing countries undergoing intense land transformation.

This study develops a micro-level Ricardian model to assess how long-run climate patterns affect agricultural land values across the urban-rural gradient in the Chesapeake Bay Watershed. Using an 8-km gridded dataset that combines farmland prices, high-resolution climate data, and urban land cover, the analysis shows that seasonal temperature and precipitation affect land values nonlinearly, and urbanization significantly moderates the effects of precipitation. A climate simulation suggests heterogeneous impacts across urban grids. Our findings highlight the critical role of urban land cover in shaping climate adaptation strategies, offering new insights into how transitional urban-agricultural regions respond to climate stress. These results provide actionable guidance for policymakers seeking to enhance agricultural resilience in the face of continued urban expansion.