Search Results (389)

Historical landslide inventory serves as a critical tool for analyzing landslide activity patterns and evaluating the long-term geological impacts of triggering events, including earthquakes, extreme weather events, and large-scale infrastructure projects. Although various methods—including visual interpretation, heuristic approaches, machine learning, and deep learning models—have been employed for landslide detection, efficient techniques for historical landslide mapping remain understudied. As a result, comprehensive historical landslide inventories continue to be scarce worldwide. In this study, we developed an advanced landslide detection model using a Swin Transformer architecture integrated with a Pyramid Segmentation Attention mechanism. Subsequently, we applied a network fine-tuning method to achieve cross-domain adaptation, enabling the reconstruction of a decadal-scale landslide inventory across the Wenchuan earthquake-affected region efficiently. Experimental results from the Wenchuan earthquake area demonstrate the proposed approach’s superior temporal transfer mapping performance compared to state-of-the-art models. The proposed historical map also exhibits high accuracy and completeness, offering significant value for analyzing landslide spatiotemporal activity and long-term regional stability. Findings reveal that landslides stabilized overall between 2008 and 2021, with key influences including altitude, slope, and aspect. The results lay the groundwork for regional stability analysis and eco-environment recovery, enabling informed decisions in urban planning and infrastructure investments. Full article

The M_JMA 7.6 (Mw 7.5) Noto Peninsula Earthquake of 1 January 2024 in Japan triggered widespread slope failures across northern Noto region, but their spatial controls and susceptibility patterns remain poorly quantified. Most previous studies have focused mainly on fault rupture, ground deformation, and tsunami impacts, leaving a clear gap in machine learning based assessment of earthquake-induced slope failures. This study integrates 2323 mapped landslides with eleven conditioning factors to develop the first data-driven susceptibility framework for the 2024 event. Spatial analysis shows that 75% of the landslides are smaller than 3220 m² and nearly half occurred within about 23 km of the epicenter, reflecting concentrated ground shaking beyond the rupture zone. Terrain variables such as slope (mean 31.8°), southwest-facing aspects, and elevations of 100–300 m influenced the failure patterns, along with peak ground acceleration values of 0.8–1.1 g and proximity to roads and rivers. Six supervised machine learning models were trained, with Random Forest and Gradient Boosting achieving the highest accuracies (AUC = 0.95 and 0.94, respectively). Explainable AI using SHapley Additive exPlanations (SHAP) identified slope, epicentral distance, and peak ground acceleration as the dominant predictors. The resulting susceptibility maps align well with observed failures and provide an interpretable foundation for post-earthquake hazard assessment and regional risk reduction. Further work should integrate post-seismic rainfall, multi-temporal inventories, and InSAR deformation to support dynamic hazard assessment and improved early warning. Full article

Mapping Plant Ecological Units (PEUs) support sustainable rangeland management. Yet, distinguishing them from multispectral imagery remains challenging due to high intra-class variability and spectral overlap. This study evaluates the contribution of auxiliary data layers to improve PEU classification from Landsat-8 OLI imagery in semi-arid rangelands of northeastern Iran. A random forest (RF) classifier was trained using field samples and multiple feature combinations, including spectral indices, topographic variables (DEM, slope, aspect), and principal component analysis (PCA) components. Classification performance was assessed using overall accuracy (OA), kappa coefficient, and non-parametric Friedman and post hoc tests to determine significant differences among scenarios. The results show that auxiliary features consistently enhanced classification performance as opposed to spectral bands alone. Integrating DEM and PCA layers yielded the highest accuracy (OA = 79.3%, κ = 0.71), with statistically significant improvement (p < 0.05). The findings demonstrate that incorporating topographic and transformed spectral information can effectively reduce class confusion and improve the separability of PEUs in complex rangeland environments. The proposed workflow provides a transferable approach for ecological unit mapping in other semi-arid regions facing similar environmental and management challenges. Full article

Alpine treeline ecotones (ATEs) are critical ecological boundaries that are highly sensitive to climate change, yet their long-term spatial dynamics remain understudied in mountainous regions. This study investigates four decades (1984–2023) of ATE elevational shift along the Eastern Slopes of the Canadian Rocky Mountains (ESCR) using the Alpine Treeline Ecotone Index (ATEI), developed by integrating NDVI gradients, elevation data, and logistic regression. Multi-temporal Landsat composites and Shuttle Radar Topography Mission (SRTM) data were processed in Google Earth Engine (GEE) to map ATE boundaries over nine composite intervals. Results show a 13.32% increase in ATE area (from 1494.17 km² to 1693.19 km²), indicating a general upslope expansion consistent with a warming climate and extended growing seasons. Although the Mann–Kendall test did not reveal a significant monotonic trend in area change (neither upward nor downward) (p-value > 0.05), notable spatial variability was observed (approximately 8 km²/year). North-facing aspects exhibited the greatest mean elevation gain (+40.21 m), and significant ecotonal changes occurred within the Bow and Athabasca watersheds (p < 0.05), which are equal to around 416 and 452 km², respectively. These findings highlight the complex, aspect- and watershed-dependent nature of alpine vegetation responses to climate forcing and demonstrate the utility of ATEI for monitoring vegetation biodiversity shifts in high-elevation ecosystems. Full article

Persistent forest fire refugia are areas within fire-prone landscapes that remain fire-free over long periods of time and are crucial for ecosystem resilience. Modelling to develop maps of these refugia is key to informing fire and land use management. We predict persistent forest fire refugia using variables linked to the fire triangle (aspect, slope, elevation, topographic wetness, convergence and roughness, solar irradiation, temperature, surface wind direction, and speed) in machine learning algorithms (Random Forest, XGBoost; two ensemble models) and K-Nearest Neighbour. All models were run with and without ADASYN over-sampling and grid search hyperparameterisation. Six iterations were run per algorithm to assess the impact of omitting variables. Aspect is twice as influential as any other variable across all models. Solar radiation and surface wind direction are also highlighted, although the order of importance differs between algorithms. The predominant importance of aspect relates to solar radiation received by sun-facing slopes and resultant heat and moisture balances and, in this study area, the predominant fire wind direction. Ensemble models consistently produced the most accurate results. The findings highlight the importance of topographic and microclimatic variables in persistent forest fire refugia prediction, with ensemble machine learning providing reliable forecasting frameworks. Full article

Yongshan County in northeastern Yunnan Province is a frequent geological hazard zone. Based on previous detailed geological hazard surveys, the county contains 455 landslide hazard sites, primarily distributed in the western and northern regions. Influenced by multiple factors including rainfall, earthquakes, human activities, and reservoir water storage, it is challenging to evaluate their development using a single indicator. Therefore, there is an urgent need to conduct landslide susceptibility assessments that integrate deformation rate characteristics. However, existing studies in this region have only considered static spatial factors such as slope aspect, elevation, and lithology. Traditional landslide susceptibility assessments often struggle to balance zoning accuracy with timeliness, leading to biased results and limited update efficiency. This study employs SBAS-InSAR technology to capture surface deformation rates and utilizes machine learning models to partition landslide susceptibility distribution maps. It innovatively introduces an RFE-RF-XGBoost model to reduce partitioning errors and enhance the accuracy of landslide susceptibility mapping. Experiments utilized 147 Sentinel-1A and 14 LT-1 scenes. Through five-fold cross-validation, 13 influencing factors were selected. The RFE-RF-XGBoost model was trained via hyperparameter optimization and compared against four conventional models (CatBoost, LightGBM, XGBoost, RF). After validating the predictive performance of different models via ROC curves, the prediction results at each level were analyzed using Accuracy, Precision, Recall, and F1 metrics. Results indicate that all five machine learning models demonstrate effective zoning capabilities. Among them, the RFE-RF-XGBoost model achieves optimal mapping performance. Compared to the other four models, it reduces the proportion of low-risk zones by 2–4% while increasing the proportion of extremely high-risk zones by approximately 2–12%, with an AUC value reaching around 0.95. Field investigations further validated that this approach enhances landslide interpretation accuracy by integrating SBAS-InSAR technology with remote sensing techniques. Full article

Soil erosion poses a significant threat to the sustainability of land systems in karst mountainous regions, where steep slopes, shallow soils, and intensive human activities exacerbate land degradation, undermining both the productive functions and ecological services of land resources. This study evaluated soil erosion susceptibility in the karst-dominated Qingshui River watershed, Southwest China, and identified key drivers of land degradation to support targeted land management strategies. Four machine learning models, BPANN, BRTs, RF, and SVR were trained using twelve geo-environmental variables representing lithological, topographic, pedological, hydrological, and anthropogenic factors. Variable importance analysis revealed that annual precipitation, land use type, distance to roads, slope, and aspect consistently had the greatest influence on soil erosion patterns. Model performance assessment indicated that BRTs achieved the highest predictive accuracy (RMSE = 0.161, MAE = 0.056), followed by RF, BPANN, and SVR. Spatial susceptibility maps showed that high and very high erosion risk zones were mainly concentrated in the central and southeastern areas with steep slopes and exposed carbonate rocks, while low-risk zones were located in flatter, vegetated southwestern regions. These results confirm that hydrological conditions, topography, and anthropogenic activities are the primary drivers of soil erosion in karst landscapes. Importantly, the findings provide actionable insights for land and landscape management—such as optimizing land use, restoring vegetation on steep slopes, and regulating human activities in sensitive areas—to mitigate erosion, preserve land quality, and enhance the sustainability of karst land systems. Full article

With an area of 13,000 km² and more than 60 outlet glaciers (tidewater or lake-terminating), the Southern Patagonian Icefield (SPI) stores a substantial volume of freshwater, and its accelerating melt contributes to global sea level rise. In addition to monitoring frontal retreat and ice thinning, tracking near-terminus glacier surface velocity can provide key insight into glacier dynamics. Here, we aimed to understand the current state of the SPI and to explore the dynamic restructuring of the glaciers in comparison with previous results. Considering that ice velocity acceleration near termini can be indicative of a drastic ice thinning and calving, during 2019–2020, we investigated the surface velocity of glaciers in the SPI using feature and speckle tracking. We calculated velocity maps (450 in total) from Sentinel-1 SAR images. Velocity ranged from 0 to 6571 myr⁻¹ for the whole study period, taking into account the 846 one square kilometer subsamples. Mean values of the topographic parameters (elevation, slope, aspect) have variable correlation with the mean velocity values, while mean ice thickness does not have a strong correlation with velocity. Nevertheless, mean velocities show association between near-frontal motion acceleration and calving, as observed in tidewater glaciers and four lake-terminating glaciers. Considering along-length changes in the glaciers, it is found that there are glaciers with upward increasing velocities, downward increasing velocities, and with a single velocity peak and multiple velocity peaks. Comparing our measurements with previous studies, we found major dynamic changes in several glaciers. A massive calving event at Pío XI Glacier significantly affected its velocity for months. The slowdown observed at 13–14 km from the terminus of the Jorge Montt Glacier contrasts with all previous studies that showed an acceleration of the glacier in this area. Our observations indicate rapid changes in some of the SPI glaciers, which suggests their unstable state. Full article

This research presents a comprehensive analysis of the spatial extent and temporal change in benthic habitats within the Puck Lagoon in the southern Baltic Sea, utilizing integrated machine learning classification and multi-sourced remote sensing. Object-based image analysis was integrated with Random Forest, Support Vector Machine, and K-Nearest Neighbors algorithms for benthic habitat classification based on airborne bathymetric LiDAR (ALB), multibeam echosounder (MBES), satellite bathymetry, and high-resolution aerial photography. Ground-truth data collected by 2023 field surveys were supplemented with long temporal datasets (2010–2023) for seagrass meadow analysis. Boruta feature selection showed that geomorphometric variables (aspect, slope, and terrain ruggedness index) and optical features (ALB intensity and spectral bands) were the most significant discriminators in each classification case. Binary classification models were more effective (93.3% accuracy in the presence/absence of Zostera marina) compared to advanced multi-class models (43.3% for EUNIS Level 4/5), which identified the inherent equilibrium between ecological complexity and map validity. Change detection between contemporary and 1957 habitat data revealed extensive Zostera marina loss, with 84.1–99.0% cover reduction across modeling frameworks. Seagrass coverage declined from 61.15% of the study area to just 9.70% or 0.63%, depending on the model. Seasonal mismatch may inflate loss estimates by 5–15%, but even adjusted values (70–94%) indicate severe ecosystem degradation. Spatial exchange components exhibited patterns of habitat change, whereas net losses in total were many orders of magnitude larger than any redistribution in space. These findings recorded the most severe seagrass habitat destruction ever described within Baltic Sea ecosystems and emphasize the imperative for conservation action at the landscape level. The methodology framework provides a reproducible model for analogous change detection analysis in shallow nearshore habitats, creating critical baselines to inform restoration planning and biodiversity conservation activities. It also demonstrated both the capabilities and limitations of automatic techniques for habitat monitoring. Full article

Olive cultivation constitutes a fundamental Mediterranean rural activity in Greece, as it primarily accounts for the country’s substantial socio-economic development. Although the olive tree is one of the best acclimated species, its overall performance may be significantly impacted by changes in the climate. Thus, by considering the lack of scientific research on the climate suitability evaluation of olive groves over the entire Greek territory, a study between the geomorphological parameter mapping of Greece (altitude, aspect, slope, and terrain roughness) and the respective required atmospheric conditions for the olive crop’s growth (temperature, precipitation, and frost days) was performed. Every parameter is reclassified to translate its value into a score, and the final suitability map is the outcome of the aggregation of all score maps. Individually, the overall suitability for olive cultivation is high in Greece, given its extensive area, resulting in a high score (8–10); geomorphological and climatic conditions (34.44% and 59.40%, respectively); and overall suitability conditions (42.00%) for olive cultivation. Over the identified olive grove areas, the model gives a high score (8–10) for 91.59% of the cases. The model may be characterized by its simplicity, usability, flexibility, and efficiency. The current modelling procedure may serve as a means for identifying suitable areas for the sustainable and productive development of olive cultivation. Full article

The accuracy of historical landslide data is a key factor affecting the precision of landslide susceptibility mapping. The degree of conformity between mathematical models and disaster-prone environments cannot be predetermined, and the optimal model needs to be determined through comparative studies. In this paper, SBAS-InSAR and the object-oriented classification method were integrated to provide data for landslide susceptibility mapping: SBAS-InSAR was used to process Sentinel-1 images, while the object-oriented classification method was applied to interpret Landsat 8 images. Eleven hazard factors were selected for landslide susceptibility modeling, and the best-performing model was determined. The influences of single and multiple hazard factors on landslide susceptibility were analyzed using Geodetector. The results showed that 246 potential landslides were identified, with a total area of 0.427 km² and a total volume of 2.161 × 10⁶ m³. The Blending-XGBoost-CNN model achieved the highest AUC and Precision, outperforming the XGBoost model and CNN model. The extreme high susceptible areas, high susceptible areas, moderate susceptible areas, minor susceptible areas and extreme minor susceptible areas accounted for 6.24% (91.4 km²), 15.07% (220.6 km²), 29.15% (426.8 km²), 30.58% (447.7 km²), and 18.96% (277.8 km²) of the total area, respectively. NDVI and gradient were key factors determining landslide occurrence. Elevation, slope aspect, distance from river, and land use also played significant roles in landslide occurrence. The contributions of TWI and lithology to landslide occurrence were relatively small, while those of plane curvature and distance from road were minimal. The interaction of hazard factors exhibited NE or BE relationships, not only increasing landslide risk but also potentially leading to more complex disaster patterns. This study can provide a theoretical basis for landslide prevention-oriented land use planning. Full article

This study systematically investigates settlement sites that record living patterns of ancient humans, aiming to reveal the interactive mechanisms of human–environment relationships. The core issues of landscape archeology research are the surface spatial structure, human spatial cognition, and social practice activities. This article takes the Han Dynasty settlement site in Sanyangzhuang, Neihuang County, Anyang City, Henan Province, as a typical case. It comprehensively uses ArcGIS 10.8 spatial analysis and remote sensing image interpretation techniques to construct spatial distribution models of elevation, slope, and aspect in the study area, and analyzes the process of the Yellow River’s ancient course changes. A regional historical geographic information system was constructed by integrating multiple data sources, including archeological excavation reports, excavated artifacts, and historical documents. At the same time, the sequences of temperature and dry–wet index changes in the study area during the Qin and Han dynasties were quantitatively reconstructed, and a climate evolution map for this period was created based on ancient climate proxy indicators. Drawing on three dimensions of settlement morphology, architectural spatial organization, and agricultural technology systems, this paper provides a deep analysis of the site’s spatial cognitive logic and the ecological wisdom it embodies. The results show the following: (1) The Sanyangzhuang Han Dynasty settlement site reflects the efficient utilization strategy and environmental adaptation mechanism of ancient settlements for land resources, presenting typical scattered characteristics. Its formation mechanism is closely related to the evolution of social systems in the Western Han Dynasty. (2) In terms of site selection, settlements consider practicality and ceremony, which can not only meet basic living needs, but also divide internal functional zones based on the meaning implied by the orientation of the constellations. (3) The widespread use of iron farming tools has promoted the innovation of cultivation techniques, and the implementation of the substitution method has formed an ecological regulation system to cope with seasonal climate change while ensuring agricultural yield. The above results comprehensively reflect three types of ecological wisdom: “ecological adaptation wisdom of integrating homestead and farmland”, “spatial cognitive wisdom of analogy, heaven, law, and earth”, and “agricultural technology wisdom adapted to the times”. This study not only deepens our understanding of the cultural value of the Han Dynasty settlement site in Sanyangzhuang, but also provides a new theoretical perspective, an important paradigm reference, and a methodological reference for the study of ancient settlement ecological wisdom. Full article

Avalanche susceptibility mapping is vital for disaster prevention and infrastructure safety in cold mountain regions under climate change. Traditional machine learning (ML) approaches have demonstrated strong predictive capacity, yet their limited interpretability and difficulty in identifying threshold effects hinder their broader application in geohazard risk management. To overcome these limitations, this study develops an explainable ML framework that integrates remote sensing data, topographic and climatic variables, and SHapley Additive exPlanations for the Kanas Scenic Area transportation corridor in the Chinese Altay Mountains. The framework evaluates five classifiers: Random Forest, XGBoost, LightGBM, Soft Voting, and Stacking, and using sixteen conditioning factors that capture topography, climate, vegetation, and anthropogenic influences. Results show that LightGBM achieved the best performance, with an AUC of 0.9428, accuracy of 0.8681, F1-score of 0.8750, and Cohen’s kappa of 0.7366. To ensure transparency for risk decisions, SHAP analyses identify Terrain Ruggedness Index, wind speed, slope, aspect and NDVI as dominant drivers. The dependence plots reveal actionable thresholds and interactions, including a TRI plateau near 5–7, a slope peak between 30° and 40°, a wind effect that saturates above about 2.5 m s⁻¹, and a near-river high-risk belt within 0–2 km. The five-class map aligns with independent field observations, with more than three quarters of events falling in moderate to very high zones. By integrating explainable ML with remote sensing, this study advances avalanche risk assessment in cold region transportation corridors and strengthens the robustness of regional susceptibility mapping. Full article

The Loess Plateau is one of the most landslide-prone regions in China, where rainfall-induced shallow loess landslides severely constrain regional economic and social development. Therefore, investigating the stability of shallow loess slopes under rainfall conditions is of great significance. Taking Yuzhong County in Gansu Province as an example, this study uses the SINMAP model (Version 2.0) to assess slope stability. The areas of unstable zones under different rainfall intensities were identified, and the spatial distribution of hazard sites was analyzed to evaluate the applicability of this deterministic physical model in the study area. Furthermore, a Personnel Risk Level (PRL) determined by combining population density with the Stability Index (SI, defined as the probability that the factor of safety exceeds 1: SI = Prob (FS > 1)) was proposed and applied to assess the potential impact of landslides on local residents. The novelty of this study lies in three aspects: (1) targeting Yuzhong County (a loess region with scarce comprehensive landslide risk assessments) to fill the regional research gap, (2) quantifying PRL through a modified hazard index (HI = population density × (1/SI)) to achieve spatialized risk mapping for vulnerable populations, and (3) systematically analyzing the dynamic response of slope stability to five gradient rainfall intensities (from light rain to severe rainstorm) and verifying model sensitivity to key parameters. The results show that as rainfall intensity increases, stable areas gradually decrease while unstable areas expand, with stable zones progressively transforming into unstable ones. Greater rainfall intensity also leads to an increase in the number of landslides within unstable zones. The proposed PRL helps delineate the severity of hazards in different townships, providing new references for mitigating casualties and property losses caused by landslides. Full article

Soil organic carbon (SOC) plays a critical role in the global carbon cycle and serves as a sensitive indicator of climate change impacts, with its dynamics significantly influencing regional ecological security and sustainable development. This study focuses on the Songnen Plain in Northeast China—a key black soil agricultural region increasingly affected by water erosion, primarily through surface runoff and rill formation on gently sloping cultivated land. We aim to investigate the spatiotemporal dynamics of SOC stocks across different cultivated land erosion zones under projected future climate change scenarios. To quantify current and future SOC stocks, we applied a boosted regression tree (BRT) model based on 130 topsoil samples (0–30 cm) and eight environmental variables representing topographic and climatic conditions. The model demonstrated strong predictive performance through 10-fold cross-validation, yielding high R² and Lin’s concordance correlation coefficient (LCCC) values, as well as low mean absolute error (MAE) and root mean square error (RMSE). Key drivers of SOC stock spatial variation were identified as mean annual temperature, elevation, and slope aspect. Using a space-for-time substitution approach, we projected SOC stocks under the SSP245 and SSP585 climate scenarios for the 2050s and 2090s. Results indicate a decline of 177.66 Tg C (SSP245) and 186.44 Tg C (SSP585) by the 2050s relative to 2023 levels. By the 2090s, SOC losses under SSP245 and SSP585 are projected to reach 2.84% and 1.41%, respectively, highlighting divergent carbon dynamics under varying emission pathways. Spatially, SOC stocks were predominantly located in areas of slight (67%) and light (22%) water erosion, underscoring the linkage between erosion intensity and carbon distribution. This study underscores the importance of incorporating both climate and anthropogenic influences in SOC assessments. The resulting high-resolution SOC distribution map provides a scientific basis for targeted ecological restoration, black soil conservation, and sustainable land management in the Songnen Plain, thereby supporting regional climate resilience and China’s “dual carbon” goals. These insights also contribute to global efforts in enhancing soil carbon sequestration and achieving carbon neutrality goals. Full article