Gully erosion is one of the major global environmental threats that frequently affects semi-humid to arid Mediterranean regions and contributes to a wide range of ecological problems. Recognizing vulnerable areas to gully erosion and creating a comprehensive gully erosion susceptibility map (GESM) can assist in the lessening of land degradation and damage to numerous infrastructures. The primary goal of this research is to build a random subspace-based function tree (RSFT), i.e., an ensemble model, and compare it with other standard models such as Fisher's linear discriminant analysis (FLDA), Nave Bayes tree (NBTree), J48 Decision Tree, and random forest (RF) models in order to identify which model generates the most accurate outcomes. Overall, a total number of 489 gully sites were utilised for modelling and validation purpose, with 377 (70 %) used for modelling and 112 (30 %) used for validation. Fourteen salient gully erosion conditioning factors (GECFs) were implemented for constructing the GESMs. The efficacy and significance of several GECFs were assessed through the random forest, or RF, model for gully erosion modelling. Using the GES maps, we computed the success rate curve (SRC) and prediction rate curve (PRC), as well as their areas under the curves (AUC). The AUC (SRC, PRC) scores for the RSFT model were 0.906 and 0.916, consequently, while the outcomes for the RF, NBTree, FLDA, and J48 models were 0.875 and 0.869, 0.861 and 0.859, 0.792 and 0.816, and 0.779 and 0.811. AUC findings indicated that the RSFT model delivered the most precise predictions, trailed by the RF, NBTree, FLDA, and J48 models. In terms of RMSE, each of the models performed adequately; however, RSFT exhibits the lowest RMSE values of all models, with 0.31 (training dataset) and 0.29 (validation dataset), which shows that RSFT is substantially more accurate than other models in forecasting gully erosionThus, the results of this research can be used by local managers and planners for environmental management. The results from our study suggests that all of the GESM models have high efficiency, and can be employed to formulate adequate measures for safeguarding of soil and water. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

Landslides pose significant impact on human life and society such as loss of livelihood, destruction of infrastructure, and damage to natural resources around the world. Due to existing complications in conditional factors of landslide, mapping and predicting landslide occurrences with high accuracy needs more attention. In light of this, we aim to develop an ensemble landslide susceptibility model named as support vector regression-grasshopper optimization algorithm (SVR-GOA). This model is validated along with other landslide susceptibility models such as artificial neural network (ANN), boosted regression tree (BRT), and elastic net models. The present study carried out over the Kalaleh Basin in Iran, in which we selected 140 landslides with 16 conditional factors to construct a geographic database of the region. The multicollinearity analysis was done on the hazard conditioning factors using variance inflation factor and tolerance indices. Similarly, significance of these factors and their association with selected locations were identified through random forest method. The state of the art of the study is implementing SVR-GOA in landslide susceptibility mapping, including this model we use other landslide models such as ANN, BRT, and elastic net for validation and development using the area under the curve (AUC), kappa, and root mean squared error values. Our results show lithology, slope degree, rainfall, topography position index, topography wetness index, surface area, and landuse/landcover were found to be the most influential conditioning factors. We have also observed that, despite accurate prediction, SVR-GOA outperforms the others by showing the highest AUC values around AUC = 0.930 and others show ANN (AUC = 0.833), BRT (AUC = 0.822) and elastic net (AUC = 0.726) respectively. This innovative approach to landslide mapping using SVR-GOA ensembles would enhance the advancement of landslide research at multiple scales. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

The February 6, 2023 Kahramanmaras,-T & uuml;rkiye ,-T & uuml;rkiye earthquakes with moment magnitudes 7.7 and 7.6 resulted in substantial casualties, injuries and extensive infrastructure devastation. Soil liquefaction was identified as one of the contributing factors to the damages. In this study, a data-driven approach to assess liquefaction-prone areas within an artificial neural network (MultiLayer Perceptron- MLP) was proposed. The study area, selected to cover a region with the size of 11,500 km2 2 containing Amik and Kahramanmaras, , Plains, is governed mainly by active tectonism of the East Anatolian Fault Zone. The earthquakes were considered to be responsible for numerous liquefaction occurrences in both plains. Here, a comprehensive inventory of liquefied regions was compiled from aerial photogrammetric images taken in the days following the earthquakes. Considering the availability of suitable geospatial datasets, the key factors for liquefaction modeling were selected as distance to streams, land use and land cover, slope, and topographic wetness index, and normalized difference water index (NDWI) and normalized difference vegetation index (NDVI) derived from satellite images taken a few days before the earthquakes. The Holocene unit was used as a mask to perform modeling and prediction within this litho- logical type. The F1-score and overall accuracy values obtained from the MLP on a test dataset were 80% and 82%, respectively. The study showed that geospatial databases including airborne and satellite image products have great potential for assessing liquefaction hazard at regional scale, which can be used as base data for planning and conducting further field and laboratory studies to improve the accuracy in predictions.

Landslides are one of the important natural threats that often cause loss of life and property in Kazakhstan. One of the regions affected by landslides of different types and sizes that occur for different reasons in the country is the Rudny Altay Region in the east of Kazakhstan. This study deals with the landslide susceptibility assessment using remote sensing methods in Rudny Altai region of East Kazakhstan. The landslide inventory map was created based on historical information, remote sensing images, and field surveys. Images of 4 selected sites (Tikhaya, Berezovka, Manat and Chernovaya) were examined to determine potential landslide susceptibility. In combined Analytical Hierarchy Process method and GIS (AHP-GIS) used in this study, values are assigned to the selected indicators (layers) from low to high landslide susceptibility potential (1-5). Thus, to assess the potential of landslide processes, the following indicators were selected: calculated values of surface slope according to the NASADEM digital elevation model, soil density, average monthly precipitation OpenLandMap, and median values of the normalized difference vegetation index (NDVI). As a result, the data were obtained and maps of landslide susceptibility of the study areas were created. According to the research results, the highest coefficient of damage to the area by landslide processes is noted in Tikhaya, and the lowest - in Manat. On average, the coefficient of landslide damage in the Rudny Altai area is 0.03, which is a low indicator for this region. The results obtained with the study showed that about 25% of the study area had moderate to high landslide susceptibility. Accordingly, landslide susceptibility is high in the southwest and south of the study area, especially in mountainous areas where slopes are steep and in sloping areas in the south. It was revealed that the results obtained in this study are quite successful in determining the landslide susceptibility of the study area. The findings of the study can contribute in the effective management of the Rudny Altai Region.

In the last decades the Valtellina valley (northern Italy) has suffered from several catastrophic rainfall -induced shallow landslide events inducing debris flows. The growing of urban settlements has driven population to colonize areas at risk, where prediction and prevention actions are nowadays a challenge for geoscientists. Debris flows are widespread in mountain areas because occurring along steep slopes covered by loose regolith or soil coverings. Under such conditions, heavy rainfall events might cause slope instabilities due to the increase in pore water pressure depending on hydraulic and geotechnical properties as well as thicknesses of soil covers. Despite the initial small volumes, debris flows hazard is significant due to the sediment entrainment and volume increase of the involved material, high velocity and runout distance. In such a framework, predicting timing and position of slope instabilities as well as paths, volumes, and velocity of potential debris flows is of great significance to assess areas at risk and to settle appropriate countermeasures. In this work, back analyses of debris flows occurred in representative sites of the Valtellina valley were carried out with the aim of understanding their features and providing a methodological basis for slope to valley scale susceptibility mapping. Numerical modeling of slope stability and runout was completed allowing the identification of the detachment, transport, and deposition zones of previously occurred landslides, including other potentially unstable ones. Results from this study emphasize issues in performing distributed numerical modeling depending on the availability of spatially distributed soil properties which hamper the quality of physicsbased models. In the framework of hazard mapping and risk strategy assessments, the approach presented can be used to evaluate the possible runout phase of new potential debris flows recognized by geomorphological evidence and numerical modeling. Furthermore, analyses aimed to the probabilistic assessment of landslide spatial distribution, related to a specific value of rainfall threshold, can be considered as potentially applicable to multi -scale landslide hazard mapping and extendable to other similar mountainous frameworks.

Ice-rich permafrost thaws in response to rapid Arctic warming, and ground subsidence facilitates the formation of thermokarst lakes. Thermokarst lakes transform the surface energy balance of permafrost, affecting geo-morphology, hydrology, ecology, and infrastructure stability, which can further contribute to greenhouse gas emissions. Currently, the spatial distribution of thermokarst lakes at large scales remains a challenging task. Based on multiple high-resolution environmental factors and thermokarst lake inventories, we used machine learning methods to estimate the spatial distributions of present and future thermokarst lake susceptibility (TLS) maps. We also identified key environmental factors of the TLS map. At 1.8 x 106 km2, high and very high susceptible regions were estimated to cover about 10.4 % of the region poleward of 60 degrees N, which were mainly distributed in permafrost-dominated lowland regions. At least 23.9 % of the area of TLS maps was projected to disappear under representative concentration pathway scenarios (RCPs), with increased susceptibility levels in northern Canada. The slope was the key conditioning factor for the occurrence of thermokarst lakes in Arctic permafrost regions. Compared with similar studies, the reliability of the TLS map was further evaluated using probability calibration curve and coefficient of variation (CV). Our results provide a means for assessing the spatial distribution of thermokarst lakes at the circum-Arctic scale but also improve the understanding of their dynamics in response to the climate system.

s The rapidly warming climate on the Qinghai-Tibet Plateau (QTP) leads to permafrost degradation, and the thawing of ice-rich permafrost induces land subsidence to facilitate the development of thermokarst lakes. Thermokarst lakes exacerbate the instability of permafrost, which significantly alters regional geomorphology and hydrology, affecting biogeochemical cycles. However, the spatial distribution and future changes in thermokarst lakes have rarely been assessed at large scales. In this study, we combined various conditioning factors and an inventory of thermokarst lakes to assess the spatial distribution of susceptibility maps using machine-learning algorithms. The results showed that the extremely randomized trees (EXT) performed the best in the susceptibility modeling process, followed by random forest (RF) and logistic regression (LR). According to the assessment based on EXT, the high- and very high-susceptibility area of the present (2000-2016) susceptibility map was 196,222 km(2), covering 19.67% of the permafrost region of the QTP. In the future (the 2070s), the area of the susceptibility map was predicted to shrink significantly under various representative concentration pathway scenarios (RCPs). The susceptibility map area would be reduced to 37.06% of the present area in RCP 8.5. This paper also performed correlation and importance analysis on the conditioning factors and thermokarst lakes, which indicated that thermokarst lakes tended to form in areas with flat topography and high soil moisture. The uncertainty of the susceptibility map was further assessed by the coefficient of variation (CV). Our results demonstrate a way to study the spatial distribution of thermokarst lakes at the QTP scale and provide a scientific basis for understanding thermokarst processes in response to climate change.

Thermokarst lakes (TLs) caused by the thaw of massive ground ice in ice-rich permafrost landscapes are increasing and have strong impacts on the hydro-ecological environment and human infrastructure on the Qinghai-Tibet Plateau (QTP), however, its spatial distribution characteristics and environmental controls have not been underrepresented at the local scale. Here, we analyzed the spatial distribution of small TLs along the Qinghai-Tibet Engineering Corridor (QTEC) based on high-resolution (up to 2.0 m) satellite images. The TLs gathered in the plains and upland plateau and covered 8.3% of the QTEC land. We deployed a random-frost method to investigate the suitable environmental conditions for TLs. Climate including summer rainfall and the air temperature was the most important factor controlling the TL distribution, followed by topography and soil characteristics that affected the ground ice content. TL susceptibility was mapped based on the combinations of climate, soil, and topography grid data. On average, around 20% of the QTEC area was in a high to very-high-susceptibility zone that is likely to develop TLs in response to climate change. This study improved the understanding of controlling factors for TL development but also provided insights into the conditions of massive ground ice and was helpful to assess the impacts of climate change on ecosystem processes and engineering design.