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 spatial shifts and vulnerability assessments of ecological niches for trees will offer fresh perspectives for sustainable development and preservation of forests, particularly within the framework of rapid climate change. Betula luminifera is a fast-growing native timber plantation species in China, but the natural resources have been severely damaged. Here, a comprehensive habitat suitability model (including ten niche-based GIS modeling algorithms) was developed that integrates three types of environmental factors, namely, climatic, soil, and ultraviolet variables, to assess the species contemporary and future distribution of suitable habitats across China. Our results suggest that the habitats of B. luminifera generally occur in subtropical areas (about 1.52 x 10(6) km(2)). However, the growth of B. luminifera is profoundly shaped by the nuances of its local environment, the most reasonable niche spaces are only 1.15 x 10(6) km(2) when limiting ecological factors (soil and ultraviolet) are considered, generally considered as the core production region. Furthermore, it is anticipated that species-suitable habitats will decrease by 10 and 8% with climate change in the 2050s and 2070s, respectively. Our study provided a clear understanding of species-suitable habitat distribution and identified the reasons why other niche spaces are unsuitable in the future, which can warn against artificial cultivation and conservation planning.

Global warming potentially increases precipitation and intensifies water exchange, thereby accelerating the hydrological cycle. The Tibetan Plateau (TP) is an Asian water tower in which the water budget varies and its anomaly exerts stress on resource availability. Few studies have quantified long-term water budgets across TP owing to scarcity of ground-based observations and uncertainties in remote sensing data. In this study, water budget components (i.e., precipitation, glacial melting [GM], evapotranspiration [ET], runoff, and soil moisture [SM] state) in TP are synthetically estimated for the past three decades. The water budget estimation benefits from a GM-coupled hydrological ensemble modeling, which is forced by nine precipitation products with seven from satellite methods. The results show that the ensemble modeling effectively captures the dynamics of runoff, ET, and terrestrial water storage. The long-term average annual water input (sum of precipitation and GM) was approximately 438 mm, with similar to 4 % contribution from GM, for which the annual ET and runoff take away was approximately 263 and 173 mm, respectively. From 1984 to 2015, the four water fluxes significantly increased with varying rates (2.3 mm/yr, precipitation; 0.9 mm/yr, GM; 1.5 mm/yr, ET; 1.1 mm/yr, runoff), which suggested an accelerating hydrological cycle. Particularly, increasing GM (similar to 5.8 mm/yr) in the Nyainqentanglha Mountains in southern TP induced high-yield runoff (>800 mm). These estimations aid in yielding robust solutions for water management in TP and neighboring regions. The accelerated hydrological cycle implies potential flooding risk and vulnerability of the hydrological system under climate change.

Mean annual ground temperature (MAGT) and active layer thickness (ALT) are key to understanding the evolution of the ground thermal state across the Arctic under climate change. Here a statistical modeling approach is presented to forecast current and future circum-Arctic MAGT and ALT in relation to climatic and local environmental factors, at spatial scales unreachable with contemporary transient modeling. After deploying an ensemble of multiple statistical techniques, distance-blocked cross validation between observations and predictions suggested excellent and reasonable transferability of the MAGT and ALT models, respectively. The MAGT forecasts indicated currently suitable conditions for permafrost to prevail over an area of 15.1 +/- 2.8 x 10(6) km(2). This extent is likely to dramatically contract in the future, as the results showed consistent, but region-specific, changes in ground thermal regime due to climate change. The forecasts provide new opportunities to assess future Arctic changes in ground thermal state and biogeochemical feedback.