Land use/land cover (LULC) change is one of the most important indicators of environmental transformation and regional landscape dynamics. Monitoring these changes is essential for understanding the impacts of urbanization, agricultural activities, and land conversion processes on semi-arid environments. This study aims to investigate the spatio-temporal LULC dynamics of Yozgat Province, Türkiye, between 2000 and 2024 using multi-temporal Landsat satellite imagery and Geographic Information Systems (GIS)-based spatial analysis techniques. Multi-temporal Landsat-5 TM, Landsat-7 ETM+, and Landsat-8/9 OLI images with 30 m spatial resolution were obtained from the USGS Earth Explorer platform. Image preprocessing, clipping, classification and temporal change detection analyses were performed in ArcGIS/ArcMap 10.8. Four major land use classes were identified: agriculture, settlement, bare land and vegetation/water. Multi-temporal classification results were compared to quantify long-term land transformation patterns. The classification accuracy was evaluated using confusion matrix analysis, Overall accuracy and Kappa metrics. The results revealed significant changes in the spatial structure of Yozgat Province over the 24-year period. Settlement areas exhibited the most substantial increase, rising by 114.38%, indicating strong urban growth and infrastructure expansion. In contrast, bare land decreased by 54.13%, suggesting progressive conversion into agricultural and built-up surfaces. Agricultural land remained relatively stable with a moderate increase of 9.08%, while vegetation/water areas increased by 67.72%. The most pronounced transformation periods were identified between 2006–2012 and 2012–2018, during which major land conversion processes occurred. The findings demonstrate that urban expansion and the reduction of bare land are the dominant drivers of landscape transformation in Yozgat Province. This study provides valuable scientific evidence for sustainable land use planning, regional environmental management, and future GIS-based monitoring studies in semi-arid regions of Central Anatolia. The results demonstrate that remote sensing and GIS techniques provide reliable tools for long-term monitoring of LULC dynamics in semi-arid environments.

Large-scale disasters fundamentally alter urban spatial structures, often triggering rapid and unsustainable land-use changes during the reconstruction phase. This study quantifies the spatial extent and nature of urban transformation in Antakya, Türkiye, following the devastating February 6, 2023, earthquakes, by analyzing Land Use/Land Cover (LULC) change between the pre-disaster (2022) and post-reconstruction (2025) periods. To achieve high-accuracy mapping in a spectrally complex post-disaster landscape, we implement an Object-Based Image Analysis (OBIA) framework coupled with a Support Vector Machine (SVM) classifier using multi-temporal Sentinel-2 imagery. By processing a 36-band dataset including seasonal spectral indices (Normalized Difference Vegetation Index (NDVI) and Normalized Difference Built-up Index (NDBI)), the model successfully navigated the spectral noise of earthquake debris, achieving high Overall Accuracies (89%-90%) and a consistent 94% Producer's Accuracy for the Settlement class. The analysis confirms that the urgent need for reconstruction significantly accelerated urban sprawl, with the Settlement class expanding by 55% (34.7km2). Cross-tabulation matrices reveal that 45.1km2 of prime agricultural land were converted to built-up areas, signalling a shift toward a fragmented urban macro-form at the expense of productive peri-urban zones. Furthermore, the 97% increase in Bare Land highlights the intensive spatial disturbance caused by temporary housing and debris removal. Methodologically, this study demonstrates the efficacy of SVM in capturing complex urban textures where spectral confusion is high. The results suggest that centralized rebuilding strategies, despite their emphasis on speed and seismic security, risk creating environmentally compromised urban forms. This study provides a scalable computational framework to assess such ecological trade-offs in disaster recovery zones.

Continuous forest monitoring using machine learning algorithms is more reliable for land use planning and management. In this study, we assess forest cover change, associated carbon stocks, and future predictions in southwestern Ethiopia using Landsat 8 Operational Land Imager and thermal infrared sensor satellite data of three epochs (2018, 2022, 2025). Multi-temporal land use land cover (LULC) classifications were performed using three machine learning models: classification and regression trees (CART), random forest (RF), and support vector machine (SVM). Classification accuracies were evaluated using overall accuracy. The results show that the RF algorithm offers the most consistent and reliable performance, with greater than 92% overall accuracy. LULC analyses reveal a significant and stable increase in forest areas during the period, while agricultural and grassland areas show varying levels of variability depending on the classifier. Forest cover assessment shows that the net forest gains are much higher than losses. Forest cover increased markedly between 2018 and 2025, by 15.4%, 23.3%, and 23.4% according to the CART, RF, and SVM models, respectively. The result also reveals that the carbon sequestration potential increases as a result of the Green Legacy Initiative (GLI), which increases forest cover. Projections for 2035 indicate that forest areas and carbon sinks are expected to continue increasing; however, the results vary depending on the algorithm used (CART, RF, and SVM). Therefore, this study quantitatively demonstrates the spatial and climatic impacts of afforestation and restoration activities under the Ethiopian GLI; it provides a scientific basis for sustainable forest management and for combating climate change.

Assessing ecosystem services capacity and landscape sensitivity under rapid urbanization in a flood-prone lowland.

This study investigates the spatiotemporal dynamics of Land Use/Land Cover (LULC) in Saharsa District, Bihar, India, over 21 years (2002-2023), using multi-temporal Landsat satellite imagery (Landsat TM and Landsat OLI/TIRS) and geospatial analysis. The novel scientific contribution of this work lies in the integrated application of a Potential Ecological Vulnerability Index (PEVI) framework alongside LULC change detection to identify ecological stress hotspots and assess the cumulative environmental consequences of land transformation in a flood-prone Megafan environment, a combination not previously applied to the ecologically sensitive Kosi Basin. Satellite images from four time points (2002, 2009, 2016, and 2023) were subjected to radiometric, atmospheric, and geometric pre-processing, including cross-sensor radiometric calibration to ensure spectral consistency between Landsat 5 TM and Landsat 8 OLI/TIRS sensors, and classified using the supervised Maximum Likelihood Classifier (MLC) in ERDAS IMAGINE. Key quantitative findings reveal a 100.60km² (6.04%) increase in built-up area and a 77.42km² (4.66%) decline in forest cover over the study period. PEVI mapping identified a progressive shift from moderate to poor and very poor ecological quality, particularly in the central and southeastern zones of the district, corresponding to areas of accelerated deforestation and urban expansion. These results underscore the ecological vulnerability of the district and highlight the urgent need for sustainable land management policies, reforestation programmes, and flood-resilient urban planning. Future research should incorporate higher-resolution imagery (e.g., Sentinel-2), machine learning classifiers (Random Forest, SVM), socio-economic variables, and hydrological modelling for more comprehensive land-use policy formulation.

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.

Accurate monitoring of agricultural land is a cornerstone of sustainable land management, particularly in arid regions like Saudi Arabia, where water resources are scarce. Traditional Land Use Land Cover (LULC) classification methods, dependent on manually engineered features, often lack robustness across diverse environmental conditions. While deep learning models like Convolutional Neural Networks (CNNs) automate feature extraction and enhance generalization, their computational complexity can be prohibitive. This research investigates a hybrid methodology to optimize this balance, integrating the powerful feature learning of DenseNet121 with the computational efficiency of advanced machine learning classifiers, specifically Decision Trees (DT) and XGBoost. The objective was to develop a precise and efficient tool for mapping key land covers-especially agricultural areas-in Najran City using 2020 Landsat 8 imagery. The proposed framework extracts complementary spatial and spectral features, which are then classified. Experimental results demonstrated that the DenseNet121-XGBoost hybrid model achieved superior performance, with an overall accuracy of 98.82% and a Kappa coefficient of 0.9638, significantly outperforming the standalone CNN. This study confirms the efficacy of hybrid deep learning for reliable agricultural land monitoring, providing a valuable decision-support tool for promoting sustainable practices in arid environments.

Geospatial and machine learning approaches for malaria risk mapping in flood-prone districts: Implications for public health decision-making.

Agriculture-conservation nexus in East Asian GIAHS: Paddy reclamation reshapes migratory avian communities.

The Eastern Desert of Egypt is a hyper-arid region where groundwater serves as the primary alternative to surface water for sustainable development. However, comprehensive assessments of groundwater potential across this vast and geologically complex region remain limited. This study addresses this gap by developing a spatial model for delineating groundwater potential zones (GWPZ) using an integrated approach that combines remote sensing, Geographic Information Systems (GIS), and the Analytical Hierarchy Process (AHP). Seven key thematic layers, precipitation, lithology, slope, drainage density, soil type, land use/land cover (LULC), and lineament density, are selected, standardized, and weighted based on hydrogeological relevance. These layers are integrated through a weighted overlay analysis in a GIS environment. The resulting GWPZ map is initially classified into five categories: very high, high, moderate, low, and very low potential. The very high and very low potential zones have very small areas in the final output due to the region’s arid conditions and hydrogeological limitations. The remaining zones covered the study area as follows: high potential (7.7%), moderate (54.5%), and low potential (37.7%). Model reliability is assessed through two complementary validation approaches. First, 370 groundwater wells with available location data are spatially overlaid on the GWPZ map, showing limited overlap with high recharge zones, as most wells target deep fossil aquifers not influenced by present-day surface conditions. Second, a supplementary validation using three independent surface-derived indicators: Topographic Wetness Index, curvature, and lineament–stream intersection density, demonstrated strong agreement with the GWPZ output. The integration of these two validation methods confirms the robustness of the model for mapping shallow groundwater recharge potential in arid environments. This framework offers a scalable, data-driven approach to support groundwater exploration and strategic water resource planning in similar regions worldwide.

The western Greater Khingan Mountains-Songnen Plain transition zone in Northeast China is a typical agro-pastoral ecotone, characterized by various agro-pastoral composite ecosystems such as rice-reed-fish and forest-grass-field mosaics. Driven by regional economic development and increasing food demand, large areas of marsh grasslands and saline-alkali lands have been reclaimed for agriculture, altering the structure and ecosystem service functions of the composite ecosystems. Here, we employed the InVEST model and the revised grain yield model to evaluate water yield, food provision, and biodiversity maintenance from 1990 to 2020. Pixel-based spatiotemporal statistical method and the Root Mean Square Error (RMSE) method are employed to quantify trade-offs among these functions and identify highly imbalanced areas. The results show that: (1) Over the past 30years, the regional average annual water yield was 31.09 × 10⁸m3, decreasing spatially from southeast to northwest; water yield of built-up land, saline-alkali wasteland, and cropland was higher than that of forests, grasslands, and wetlands. (2) Food provision followed a "U"-shaped pattern (lowest in 2000 at 2631kg/hm2), with high-value areas in the southeast and north, and low-value areas in the central pastoral zones. (3) Biodiversity maintenance declined overall, with an average index value of 0.395; the poor-function areas occurred in built-up land and saline-alkali wasteland. In contrast, the good-function areas occurred in forests, grasslands, and wetlands. (4) Across different scales, trade-offs among ecosystem services were more pronounced than synergies, especially in Zhenlai and Da'an counties. For the identified highly imbalanced multi-ecosystem service function areas (Zones I and II), we recommend implementing appropriate conservation measures or adjusting Land Use Land Cover (LULC) patterns to promote the synergistic development of ecosystem services.

Understanding the spatiotemporal variation characteristics of habitat quality and its driving mechanisms is crucial for enhancing biodiversity and promoting regional ecological restoration. This study assessed the habitat quality across terrestrial ecosystems in China from 2000 to 2020 with the Integrated Valuation of Ecosystem Services and Tradeoffs （InVEST） model. By integrating ecological quality transitions and spatial autocorrelation models， this study explored the spatiotemporal evolution patterns of the habitat quality. This study also analyzed the influence of land use/land cover （LULC）， enhanced vegetation index （EVI）， topographic factors， climatic factors， and socioeconomic factors on the spatial heterogeneity of habitat quality with the Geodetector method， using both single-factor and interaction detection. The results revealed that： ① The spatial distribution pattern of habitat quality across terrestrial ecosystems of China aligned closely with the land use/land cover types. Habitat quality was higher in forest and grassland areas compared to that in cropland and unused land， which was primarily due to higher vegetation coverage， more stable ecosystem structure and function， and richer biodiversity in the forest and grassland areas. ② The habitat quality in terrestrial ecosystems of China was overall relatively high， with areas classified as Level III or above accounting for approximately 55% of the total terrestrial area. Strong spatial clustering patterns of the habitat quality were observed， with high-value areas concentrated in the Qinghai-Tibet Plateau， Yangtze River Economic Belt， Hainan， and the Greater and Lesser Khingan Mountains. Low-value areas were primarily located around the Tarim Basin， western Inner Mongolia， the Shandong Peninsula， and the Yangtze River Delta. The habitat quality remained stable in most regions （90.84%） during the study period. Declines in habitat quality （4.63%） were mainly observed in eastern coastal regions， especially in urban agglomerations such as the Beijing-Tianjin-Hebei region， the Shandong Peninsula， and the Yangtze River Delta. Improvements in habitat quality （4.53%） were concentrated in areas such as the Loess Plateau and the Sanjiangyuan Region. ③ LULC had the highest explanatory power （q-value） and showed the strongest interaction effects with other factors. Habitat quality in terrestrial ecosystems， biodiversity priority areas， and non-priority areas was primarily influenced by LULC， EVI， and precipitation， indicating a consistent mechanism across different biodiversity zones， namely， the dominant role of natural factors. Socioeconomic factors showed relatively low explanatory power when considered individually but demonstrated increasing interaction effects when combined with LULC and EVI， with q-values exceeding 0.32. Notably， the nighttime light index and the proportion of construction land had q-values in non-priority areas that were 9-30 times and 1-3 times higher than those in priority areas， respectively. The findings of this study can provide essential scientific support for regional ecological conservation and high-quality development.

Land-use change and surface warming in Uganda’s oil-rich Albertine region (1995–2025): A geodetector analysis

Use of Surface Water and Ocean Topography (SWOT) observations to support Land Use/Land Cover (LULC) change products: the case of the pacific coast of Ecuador

Riparian zone transformation in South Africa: Evaluating changes, causes, and the role of legal frameworks

Impact of land cover land use changes on the ecosystem services in northern Pakistan

Agriculture is fundamental to rural livelihoods but faces increasing threats from irregular rainfall, water scarcity, and unsustainable land use. Therefore, this study analyzes the temporal dynamics of land use/land cover (LULC) change and rainfall variability in Dewgain Village, India, and assesses future rainfall scenarios to evaluate potential rainfall and drought risks and their implications for agricultural resilience. Multi-temporal Sentinel-2 imagery (2017-2024) was processed and classified using Google Earth Engine, and the derived LULC maps were analyzed in a GIS environment to quantify area changes and identify LULC transitions. Rainfall trend analysis from 1981 to 2024 was conducted to assess long-term rainfall variability and trends in the study area using the Rainfall Anomaly Index (RAI), the Mann-Kendall test, and Sen's slope estimator. The Mann-Kendall test indicates a statistically significant upward trend in annual rainfall (P = 0.0184, τ = 0.248). RAI analysis further reveals considerable interannual variability (R2 = 0.185, p = 0.00359), with seven dry years recorded during the study period. Despite this overall increase, winter rainfall shows a declining tendency, suggesting increasing drought stress and potentially higher irrigation requirements. Moreover, this study found that, according to LULC change analysis, cropland is expanding, while forest land, rangeland, and water bodies in the area are declining; this may alter local hydrological conditions and reduce the landscape's capacity to retain water. Combining LULC change with strong monsoon rainfall variability and weak rainfall during other seasons, these changes may increase rainfall above the recommended conditions during the monsoon and water stress in other seasons, ultimately affecting farming activities and agricultural productivity. Future projections indicate an increase in extreme rainfall events, heightening the likelihood of flood risks in low-lying agricultural zones. The integration of LULC and rainfall dynamics provides actionable insights for local climate adaptation strategies, emphasizing agroforestry, water-efficient irrigation, and participatory farm planning to boost the resilience of agriculture to extreme climate and improve food systems.

Early-life exposure to environmental pollutants poses a critical risk to pediatric health, yet few studies have integrated chemical contaminants with urban land-use characteristics to assess their combined associations with the developing gut microbiome. In this study, we evaluated the associations between fecal heavy metal (HM) concentrations and residential land-use cover area (measured as area-based metrics within specific buffers), as well as gut microbial composition and predicted functional pathways, in 78 preschool children from the greater Taipei area. Using Bayesian kernel machine regression (BKMR), we characterized nonlinear and interactive exposure-response relationships. Elevated fecal cadmium (Cd) levels were significantly and positively associated with increased abundance of Bacteroides (q = 0.02), while nominal positive associations were observed with Klebsiella and Veillonella. Fecal lead (Pb) showed a suggestive positive association with Phocaeicola (q = 0.07). Crucially, residential land-use features modified these associations: increased gas station coverage was linked to lower Bacteroides and Veillonella levels but higher Klebsiella abundance, whereas green-space coverage was positively associated with Veillonella. The BKMR model highlighted synergistic negative associations between fecal Cd and gas station area coverage within a 1500-m residential buffer on Veillonella and Bacteroides, suggesting that the spatial distribution of physical urban infrastructure may be linked to the apparent effects of chemical contaminants on the gut microbiota. These environmental contaminants were further associated with alterations in predicted microbial functional pathways involved in energy metabolism, secondary metabolite biosynthesis, and genetic information processing. These findings suggest that children's gut health may be associated with a complex interplay of urban chemical and structural factors. Our results underscore the need for science-informed urban management and health-protective zoning, which may inform strategies such as optimizing land-use cover area of gas stations near residential areas and increasing urban greenery to mitigate environmental risks during critical developmental windows.

Quantifying land use land cover (LULC) dynamics in vulnerable ecosystems of the Ethiopian highlands is crucial for understanding the drivers of environmental degradation and informing sustainable land management to protect ecosystem integrity. The Jema River Sub-basin, a critical contributor to the Upper Blue Nile, is highly vulnerable to agricultural expansion, the loss of native vegetation, and landscape fragmentation. This study quantified the spatiotemporal dynamics of LULC change and identified potential drivers between 1994 and 2024, to support evidence-based climate-resilient land-use planning in this basin. A machine-learning framework was implemented on the Google Earth Engine (GEE) platform to classify LULC. We utilized Landsat 5 TM, Landsat 7 ETM+, Landsat 8 OLI, and Sentinel-2 MSI imageries, which were classified using the Random Forest (RF) algorithm. The classification was optimized by integrating spectral indices, including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), and Modified Normalized Difference Water Index (MNDWI), along with topographic variables (slope and elevation). Classification accuracy, assessed using 3100 ground-truth samples, exceeded 87% overall accuracy with Kappa coefficients above 83%. Temporal change detection, transition matrices, and trend analyses quantified alterations across seven LULC classes. The results show that farmland expanded by 37.4%, and built-up area by 23.5%, while natural vegetation and grazing land declined by 56% and 67.4%, respectively. Focus group discussions and key informant interviews identified population pressure, agricultural intensification, and weak governance as the dominant socio-economic drivers. The integration of multi-temporal geospatial analysis with local knowledge indicates substantial anthropogenic landscape modification and provides empirical evidence to inform sustainable land-use planning and ecosystem restoration initiatives in the Jema Sub-basin.

Ecosystems provide critical services essential for human well-being and environmental sustainability. This study examines the impacts of land use land cover (LULC) dynamics on ecosystem service values (ESVs) in Hoto area, South Ethiopia, from 1993 to 2023. Using multispectral Landsat imagery, analyzed with ERDAS IMAGINE 2014 and ArcGIS 10.8, six LULC classes were identified: barren land, forest, grazing land, farmland, shrubland, and settlement. The analysis reveals a significant decline in forest cover (from 24.9% to 11%, net loss of 55.69%) and grazing land (from 13.5% to 9.9%), alongside expansions in settlement (from 4.6% to 7.0%), barren land (from 2.1% to19.5%), and shrubland. Total ESVs decreased from US$ 4.35million in 1993 to US$ 3.33million in 2023, driven primarily by deforestation, overgrazing, and land degradation, which impaired key services like food production, water regulation, and erosion control. The decline was most pronounced in regulating services (-29.4%), which dominated the total ESV. Overall, these findings underscore the urgent need for targeted policy interventions, including reforestation of degraded lands, promotion of sustainable agroforestry, protection of remaining forest patches, and regulating grazing to restore critical ecosystem services and to improve local livelihoods in the study area.