Search Results (48)

On 20 April 2024, an extreme rainfall event occurred in Jiangwan Town Shaoguan City, Guangdong Province, China, where a historic 24 h precipitation of 206 mm was recorded. This triggered extensive landslides that destroyed residential buildings, severed roads, and drew significant societal attention. Rapid acquisition of landslide inventories, distribution patterns, and key controlling factors is critical for post-disaster emergency response and reconstruction. Based on high-resolution Planet satellite imagery, landslide areas in Jiangwan Town were automatically extracted using the Normalized Difference Vegetation Index (NDVI) differential method, and a detailed landslide inventory was compiled. Combined with terrain, rainfall, and geological environmental factors, the spatial distribution and causes of landslides were analyzed. Results indicate that the extreme rainfall induced 1426 landslides with a total area of 4.56 km², predominantly small-to-medium scale. Landslides exhibited pronounced clustering and linear distribution along river valleys in a NE–SW orientation. Spatial analysis revealed concentrations on slopes between 200–300 m elevation with gradients of 20–30°. Four machine learning models—Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were employed to assess landslide susceptibility mapping (LSM) accuracy. RF and XGBoost demonstrated superior performance, identifying high-susceptibility zones primarily on valley-side slopes in Jiangwan Town. Shapley Additive Explanations (SHAP) value analysis quantified key drivers, highlighting elevation, rainfall intensity, profile curvature, and topographic wetness index as dominant controlling factors. This study provides an effective methodology and data support for rapid rainfall-induced landslide identification and deep learning-based susceptibility assessment. Full article

The present study examines the application of four machine learning models—Multi-Layer Perceptron, Naive Bayes, Credal Decision Trees, and Random Forests—to assess landslide susceptibility using Mei County, China, as a case study. Aerial photographs and field survey data were integrated into a GIS system to develop a landslide inventory map. Additionally, 16 landslide conditioning factors were collected and processed, including elevation, Normalized Difference Vegetation Index, precipitation, terrain, land use, lithology, slope, aspect, stream power index, topographic wetness index, sediment transport index, plan curvature, profile curvature, and distance to roads. From the landslide inventory, 87 landslides were identified, along with an equal number of randomly selected non-landslide locations. These data points, combined with the conditioning factors, formed a spatial dataset for our landslide analysis. To implement the proposed methodological approach, the dataset was divided into two subsets: 70% formed the training subset and 30% formed the testing subset. A correlation analysis was conducted to examine the relationship between the conditioning factors and landslide occurrence, and the certainty factor method was applied to assess their influence. Beyond model comparison, the central focus of this research is the optimization of machine learning parameters to enhance prediction reliability and spatial accuracy. The results show that the Random Forests and Multi-Layer Perceptron models provided superior predictive capability, offering detailed and actionable landslide susceptibility maps. Specifically, the area under the receiver operating characteristic curve and other statistical indicators were calculated to assess the models’ predictive accuracy. By producing high-resolution susceptibility maps tailored to local geomorphological conditions, this work supports more informed land-use planning, infrastructure development, and early warning systems in landslide-prone areas. The findings also contribute to the growing body of research on artificial intelligence-driven natural hazard assessment, offering a replicable framework for integrating machine learning in geospatial risk analysis and environmental decision-making. Full article

Reduced-impact logging (RIL) has been recognized as a promising strategy for biodiversity conservation and carbon sequestration within sustainable forest management (SFM) areas. However, monitoring the forest understory—a critical area for assessing logging impacts—remains challenging due to limitations in conventional methods such as field inventories and global navigation satellite system (GNSS) surveys, which are time-consuming, costly, and often lack accuracy in complex environments. Additionally, aerial and satellite imagery frequently underestimate the full extent of disturbances as the forest canopy obscures understory impacts. This study examines the effectiveness of the relative density model (RDM), derived from airborne LiDAR data, for mapping and monitoring understory disturbances. A field-based validation of LiDAR-derived RDM was conducted across 25 sites, totaling 5504.5 hectares within the Jamari National Forest, Rondônia, Brazil. The results indicate that the RDM accurately delineates disturbances caused by logging infrastructure, with over 90% agreement with GNSS field data. However, the model showed the greatest discrepancy for skid trails, which, despite their lower accuracy in modeling, accounted for the largest proportion of the total impacted area among infrastructure. The findings include the mapping of 35.1 km of primary roads, 117.4 km of secondary roads, 595.6 km of skid trails, and 323 log landings, with skid trails comprising the largest proportion of area occupied by logging infrastructure. It is recommended that airborne LiDAR assessments be conducted up to two years post-logging, as impacts become less detectable over time. This study highlights LiDAR data as a reliable alternative to traditional monitoring approaches, with the ability to detect understory impacts more comprehensively for monitoring selective logging in SFM areas of the Amazon, providing a valuable tool for both conservation and climate mitigation efforts. Full article

The completeness of landslide inventories and the selection of evaluation models significantly impact the accuracy of landslide susceptibility assessments. Conventional field geological survey methods and single remote-sensing technology struggle to reliably identify landslides under complex environmental conditions. Moreover, prevalent landslide susceptibility evaluation models are often plagued by issues such as subjectivity and overfitting. Therefore, we investigated the uncertainty in susceptibility modeling from the aspects of landslide inventory quality and model selection. The study focused on Luquan County in Yunnan Province, China. Leveraging multisource remote-sensing technologies, particularly emphasizing optical remote sensing and InSAR time-series deformation detection, the existing historical landslide inventory was refined and updated. This updated inventory was subsequently used to serve as samples. Nine evaluation indicators, encompassing factors such as distance to faults and tributaries, lithology, distance to roads, elevation, slope, terrain undulation, distance to the main streams, and average annual precipitation, were selected on the basis of the collation and organization of regional geological data. The information value and two coupled machine-learning models were formulated to evaluate landslide susceptibility. The evaluation results indicate that the two coupled models are more appropriate for susceptibility modeling than the single information value (IV) model, with the random forest model optimized by genetic algorithm in Group I2 exhibiting higher predictive accuracy (AUC = 0.796). Furthermore, comparative evaluation results reveal that, under equivalent model conditions, the incorporation of a remote-sensing landslide inventory significantly enhances the accuracy of landslide susceptibility assessment results. This study not only investigates the impact of landslide inventories and models on susceptibility outcomes but also validates the feasibility and scientific validity of employing multisource remote-sensing technologies in landslide susceptibility assessment. Full article

Forests are an important part of natural resources and play an important role in carbon sinks. We measured carbon sinks in provincial forest parks using data from four forest inventory surveys in China and the forest stock expansion method. Carbon emissions from forest tourism were also estimated using energy statistics and forest park tourism data. On this basis, spatial analysis was used to summarize the spatial and temporal evolution of the carbon balance and the analysis of influencing factors. The results show the following: (1) With the passage of time, the carbon emissions from forest tourism in all provinces have increased to different degrees, and the national forest tourism carbon emissions have increased from 1,071,390.231 (million tons) in 2003 to 286,255,829.7 (million tons) in 2018; spatially, the distribution of carbon emissions from forest tourism is uneven, with an overall high in the south and low in the north, and a high in the east and a low in the west. (2) The carbon sink of forest parks showed a trend of gradual growth and spatially formed a spatial pattern of high in the northeast and low in the southwest, which is consistent with the distribution of forest resources in China. (3) For forest tourism carbon emissions, the total number of tourists, tourism income, and playing roads are significant influencing factors, and the baseline regression coefficients are 0.595, 0.433, and 0.799, respectively, while for forest park carbon sinks, the number of forest park employees can play a certain positive role in carbon sinks, with the regression coefficient being 1.533. Full article

Natural disasters, notably landslides, pose significant threats to communities and infrastructure. Landslide susceptibility mapping (LSM) has been globally deemed as an effective tool to mitigate such threats. In this regard, this study considers the northern region of Pakistan, which is primarily susceptible to landslides amid rugged topography, frequent seismic events, and seasonal rainfall, to carry out LSM. To achieve this goal, this study pioneered the fusion of baseline models (logistic regression (LR), K-nearest neighbors (KNN), and support vector machine (SVM)) with ensembled algorithms (Cascade Generalization (CG), random forest (RF), Light Gradient-Boosting Machine (LightGBM), AdaBoost, Dagging, and XGBoost). With a dataset comprising 228 landslide inventory maps, this study employed a random forest classifier and a correlation-based feature selection (CFS) approach to identify the twelve most significant parameters instigating landslides. The evaluated parameters included slope angle, elevation, aspect, geological features, and proximity to faults, roads, and streams, and slope was revealed as the primary factor influencing landslide distribution, followed by aspect and rainfall with a minute margin. The models, validated with an AUC of 0.784, ACC of 0.912, and K of 0.394 for logistic regression (LR), as well as an AUC of 0.907, ACC of 0.927, and K of 0.620 for XGBoost, highlight the practical effectiveness and potency of LSM. The results revealed the superior performance of LR among the baseline models and XGBoost among the ensembles, which contributed to the development of precise LSM for the study area. LSM may serve as a valuable tool for guiding precise risk-mitigation strategies and policies in geohazard-prone regions at national and global scales. Full article

It is highly valuable to analyze and assess the landscape ecological risk of nature reserves to prevent and resolve ecological risks, as well as to effectively protect and maintain the sustainable development of nature reserves. Taking the forest landscape of the Lushan National Nature Reserve as its study object, this study performed grid processing for the nature reserve and classified forest landscape types using the Forest Resource Inventory Database in 2019. A landscape ecological index model was constructed to evaluate the ecological risk. Global and local Moran index values were used to reveal the autocorrelations for ecological risk. The geodetector method was used to comprehensively analyze the effects of natural and human factors on ecological risk. The results showed that, in general, the ecological risk level of the nature reserve was relatively low, as the proportion of the lowest-, lower-, and medium-risk areas to the total forestry land area accounted for 91.03%. The ecological risk ranking of each functional zone, from high to low, was in the order of the experimental zone, the buffer zone, and the core zone. The ecological risk levels of different forest landscape types were closely related to their area, spatial distribution, and succession stage, as well as human factors, such as the proximity to roads and settlements, etc. The forest landscape with the highest ecological risk was the Cunninghamia lanceolata (Lamb.) Hook. forest, and the forest landscape with the lowest ecological risk was other forestry land. Ecological risk had a positive spatial correlation and tended to be aggregated in space, demonstrating coupling with the proximity to roads and settlements. The ecological risk was affected by both human and natural factors, among which human factors played a dominant role. The proximity to roads and settlements, the relative humidity, and the temperature were the main driving factors. The interaction of pairwise factors had a stronger influence than that of single factors. Therefore, controlling the intensity of human activities and enhancing the coordination between humans and nature are beneficial for alleviating the ecological risks in the forest landscapes of nature reserves. Full article

Flood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution remote sensing products, i.e., synthetic aperture radar (SAR) images for flood inventory preparation and integrated four machine learning models (Random Forest: RF, Classification and Regression Trees: CART, Support Vector Machine: SVM, and Extreme Gradient Boosting: XGBoost) to predict flood susceptibility in Metlili watershed, Morocco. Initially, 12 independent variables (elevation, slope angle, aspect, plan curvature, topographic wetness index, stream power index, distance from streams, distance from roads, lithology, rainfall, land use/land cover, and normalized vegetation index) were used as conditioning factors. The flood inventory dataset was divided into 70% and 30% for training and validation purposes using a popular library, scikit-learn (i.e., train_test_split) in Python programming language. Additionally, the area under the curve (AUC) was used to evaluate the performance of the models. The accuracy assessment results showed that RF, CART, SVM, and XGBoost models predicted flood susceptibility with AUC values of 0.807, 0.780, 0.756, and 0.727, respectively. However, the RF model performed better at flood susceptibility prediction compared to the other models applied. As per this model, 22.49%, 16.02%, 12.67%, 18.10%, and 31.70% areas of the watershed are estimated as being very low, low, moderate, high, and very highly susceptible to flooding, respectively. Therefore, this study showed that the integration of machine learning models with radar data could have promising results in predicting flood susceptibility in the study area and other similar environments. Full article

Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data’s positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area’s road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods. Full article

Landslide susceptibility prediction (LSP) is the basis for risk management and plays an important role in social sustainability. However, the modeling process of LSP is constrained by various factors. This paper approaches the effect of landslide data integrity, machine-learning (ML) models, and non-landslide sample-selection methods on the accuracy of LSP, taking the Yinghu Lake Basin in Ankang City, Shaanxi Province, as an example. First, previous landslide inventory (totaling 46) and updated landslide inventory (totaling 46 + 176) were established through data collection, remote-sensing interpretation, and field investigation. With the slope unit as the mapping unit, twelve conditioning factors, including elevation, slope, aspect, topographic relief, elevation variation coefficient, slope structure, lithology, normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), distance to road, distance to river, and rainfall were selected. Next, the initial landslide susceptibility mapping (LSM) was obtained using the K-means algorithm, and non-landslide samples were determined using two methods: random selection and semi-supervised machine learning (SSML). Finally, the random forest (RF) and artificial neural network (ANN) machine-learning methods were used for modeling. The research results showed the following: (1) The performance of supervised machine learning (SML) (RF, ANN) is generally superior to unsupervised machine learning (USML) (K-means). Specifically, RF in the SML model has the best prediction performance, followed by ANN. (2) The selection method of non-landslide samples has a significant impact on LSP, and the accuracy of the SSML-based non-landslide selection method is controlled by the ratio of the number of landslide samples to the number of mapping units. (3) The quantity of landslides has an impact on how reliably the results of LSM are obtained because fewer landslides result in a smaller sample size for LSM, which deviates from reality. Although the results in this dataset are satisfactory, the zoning results cannot reliably anticipate the recently added landslide data discovered by the interpretation of remote-sensing data and field research. We propose that the landslide inventory can be increased by remote sensing in order to achieve accurate and impartial LSM since the LSM of adequate landslide samples is more reasonable. The research results of this paper will provide a reference basis for uncertain analysis of LSP and regional landslide risk management. Full article

Employing a small baseline subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) and hotspot analysis, this study identified 81 potential landslides in a 768.7 km² area of Xiaojin county, eastern Tibetan Plateau. Subsequent time-series deformation analysis revealed that these potential landslides are in the secondary creep stage. The newly identified landslides were compared to a landslide inventory (LI), established through field surveying, in terms of causative factors, including altitude, slope, relief amplitude, distance to river, distance to road, and slope curvature. From the comparison, the InSAR technique showed the following advantages: (1) it identified 25 potential landslides at high altitudes (>3415 m) in addition to the low-altitude landslides identified through the field survey. (2) It obtained approximately 37.5% and 70% increases in the number of potential landslides in the slope angle ranges of 20°–30° and 30°–40°, respectively. (3) It revealed significant increases in potential landslides in every relief amplitude bin, especially in the range from 58 m to 92 m. (4) It can highlight key geological factors controlling landslides, i.e., the stratigraphic occurrence and key joints as the InSAR technique is a powerful tool for identifying landslides in all dip directions. (5) It reveals the dominant failure modes, such as sliding along the soil–rock interface and/or interfaces formed by complicated combinations of discontinuities. This work presents the significant potential of InSAR techniques in gaining deeper knowledge on landslide development in alpine forest regions. Full article

Landslides are among the most relevant and potentially damaging natural risks, causing material and human losses. The department of Aube in France is well known for several major landslide occurrences. This study focuses on the assessment of Landslide Susceptibility (LS) using the Frequency Ratio (FR) as a statistical method, the Analytic Hierarchy Process (AHP) as a Multi-Criteria Decision-Making (MCDM) method, and Random Forest (RF) and k-Nearest Neighbor (kNN) as machine learning methods in the Aube department, northeast of France. Subsequently, the thematic layers of eight landslide causative factors, including distance to hydrography, density of quarries, elevation, slope, lithology, distance to roads, distance to faults, and rainfall, were generated in the geographic information system (GIS) environment. The thematic layers were integrated and processed to map landslide susceptibility in the study area. On the other hand, an inventory of landslides was carried out based on the database created by the French Geological Survey (BRGM), where 157 landslide occurrences were selected, and then RF and kNN models were trained to generate landslide maps (LSMs) of the study area. The generated maps were assessed by using the Area Under the Receiver Operating Characteristic Curve (ROC AUC). Subsequently, the accuracy assessment of the FR model revealed more accurate results (AUC = 66.0%) than AHP, outperforming the latter by 6%, while machine learning models results showed that RF gave better results than kNN (<7.3%) with AUC = 95%. Following the analysis of LS mapping results, lithology, distance to the hydrographic network, distance to roads, and elevation were the four main factors controlling landslide susceptibility in the study area. Future mitigation and protection activities within the Aube department can benefit from the present study mapping results, implicating an optimized land management for decision-makers. Full article

Rapid urbanization and climate change effects may cause dramatic changes in ecosystem functions in cities, thereby inevitably affecting the growth performance of old trees. Few studies have explored species diversity and spatial differentiation in Benin urban areas. This study aims to explore this dimension of urban ecology in order to build resilience to climate change in the city of Cotonou. Its objective was to determine the predominant level of tree diversity in the city’s land use units. The urban green frame was subdivided into six land use units, namely, establishments, residences, green spaces, commercial areas, administrative areas, and roads. The forest inventories were carried out in 149 plots with surfaces evaluated at 2500 m² each. The IVI, an index that highlights the relative density, relative dominance, and relative frequency of species, has been used to characterize the place occupied by each species in relation to all species in urban ecosystems. This shows ecological importance through the diversity and quality of ecosystems, communities, and species. A total of 62 tree species in 55 genera and 27 families were recorded. The results show that the flora of the city of Cotonou is characterized by a strong preponderance of exotic species with some differences in species presence. The most abundant species with high ecological importance (IVI) in the different types of land use of the city are Terminalia catappa (IVI = 121.47%), Terminalia mantaly (IVI = 90.50%), Mangifera indica (IVI = 64.06%), and Khaya senegalensis (IVI = 151.16%). As the use of ecosystem services is recommended to tackle urban climate hazards, this study shows that direct development of this urban vegetation could improve the resilience of urban life to climate hazards through the provision of urban ecosystem services, potential ecological infrastructure foundations, and urban nature-based solutions. Full article

The expansion of mountainous urban areas and road networks can influence the terrain, vegetation, and material characteristics, thereby altering the susceptibility of landslides. Understanding the relationship between human engineering activities and landslide occurrence is of great significance for both landslide prevention and land resource management. In this study, an analysis was conducted on the landslide caused by Typhoon Megi in 2016. A representative mountainous area along the eastern coast of China—characterized by urban development, deforestation, and severe road expansion—was used to analyze the spatial distribution of landslides. For this purpose, high-precision Planet optical remote sensing images were used to obtain the landslide inventory related to the Typhoon Megi event. The main innovative features are as follows: (i) the newly developed patch generating land-use simulation (PLUS) model simulated and analyzed the driving factors of land-use land-cover (LULC) from 2010 to 2060; (ii) the innovative stacking strategy combined three strong ensemble models—Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM)—to calculate the distribution of landslide susceptibility; and (iii) distance from road and LULC maps were used as short-term and long-term dynamic factors to examine the impact of human engineering activities on landslide susceptibility. The results show that the maximum expansion area of built-up land from 2010 to 2020 was 13.433 km², mainly expanding forest land and cropland land, with areas of 8.28 km² and 5.99 km², respectively. The predicted LULC map for 2060 shows a growth of 45.88 km² in the built-up land, mainly distributed around government residences in areas with relatively flat terrain and frequent socio-economic activities. The factor contribution shows that distance from road has a higher impact than LULC. The Stacking RF-XGB-LGBM model obtained the optimal AUC value of 0.915 in the landslide susceptibility analysis in 2016. Furthermore, future road network and urban expansion have intensified the probability of landslides occurring in urban areas in 2015. To our knowledge, this is the first application of the PLUS and Stacking RF-XGB-LGBM models in landslide susceptibility analysis in international literature. The research results can serve as a foundation for developing land management guidelines to reduce the risk of landslide failures. Full article

Landslide occurrence in Colombia is very frequent due to its geographical location in the Andean mountain range, with a very pronounced orography, a significant geological complexity and an outstanding climatic variability. More specifically, the study area around the Bogotá-Villavicencio road in the central sector of the Eastern Cordillera is one of the regions with the highest concentration of phenomena, which makes its study a priority. An inventory and detailed analysis of 2506 landslides has been carried out, in which five basic typologies have been differentiated: avalanches, debris flows, slides, earth flows and creeping areas. Debris avalanches and debris flows occur mainly in metamorphic materials (phyllites, schists and quartz-sandstones), areas with sparse vegetation, steep slopes and lower sections of hillslopes; meanwhile, slides, earth flows and creep occur in Cretaceous lutites, crop/grass lands, medium and low slopes and lower-middle sections of the hillslopes. Based on this analysis, landslide susceptibility models have been made for the different typologies and with different methods (matrix, discriminant analysis, random forest and neural networks) and input factors. The results are generally quite good, with average AUC-ROC values above 0.7–0.8, and the machine learning methods are the most appropriate, especially random forest, with a selected number of factors (between 6 and 8). The degree of fit (DF) usually shows relative errors lower than 5% and success higher than 90%. Finally, an integrated landslide susceptibility map (LSM) has been made for shallower and deeper types of movements. All the LSM show a clear zonation as a consequence of the geological control of the susceptibility. Full article