Flash floods are often responsible for deaths and damage to infrastructure. The objective of this work is to create a data-driven model to understand how predisposing factors influence the spatial variation of the triggering factor (rainfall intensity) in the case of flash floods in the continental area of Portugal. Flash floods occurrences were extracted from the DISASTER database. We extracted the accumulated precipitation from the Copernicus database by considering two days of duration. The analysed predisposing factors for flooding were extracted considering the whole basin where each occurrence is located. These factors include the basin area, the predominant lithology, drainage density, and the mean or median values of elevation, slope, stream power index (SPI), topographic wetness index (TWI), roughness, and four soil properties. The Random Forest algorithm was used to build the models and obtained mean absolute percentage error (MAPE) around 19%, an acceptable value for the objectives of the work. The median of SPI, mean elevation and the area of the basin are the top three most relevant predisposing factors interpreted by the model for defining the rainfall input for flash flooding in mainland Portugal.

Malan loess is widely distributed on the Chinese Loess Plateau and poses great challenges to geotechnical, ecological, and agricultural practices due to its unique structure and collapsibility. It is essential to understand the evolution of these properties with depth to assess soil stability and reduce engineering risks in the area. This study investigates the mechanical properties and microstructural evolution of Malan loess with depth and employs multivariate statistical methods to explore their complex interrelationships. Oedometer-collapse tests reveal a 94.2 % reduction in collapsibility coefficient (delta s) from 0.0722 at 1 m to 0.0042 at 9 m, indicating a significant reduction in collapsibility with increasing depth. According to the results of the direct shear test, it showed that the shear strength initially decreases and then increases due to the combined effect of the water content and dry density. Scanning electron microscopy (SEM) images reveal the densification of the loess structure, with changes in particle contact from point to face contact and the evolution from macropores to mesopores and small pores as depth increases. Quantitative analysis by Avzio showed a decrease of 61.5 % in macropores area and an increase of 62.5 % in small pores area. The results obtained by Pearson's correlation analysis and random forest model showed that among these microstructural characteristics, the total pore area (%IncMSE = 22.77 %) is the most important factor influencing the collapsibility properties of loess and water content (%IncMSE = 17.72 %) acts a key role in controlling shear strength. Additionally, compared to traditional methods, the random forest model offers a more insightful understanding of nonlinear relationships and multifactorial coupling effects. These findings provide scientific guidance for geotechnical engineering in loess regions, aiding in risk mitigation and promoting sustainable construction.

The vadose zone acts as a natural buffer that prevents contaminants such as arsenic (As) from contaminating groundwater resources. Despite its capability to retain As, our previous studies revealed that a substantial amount of As could be remobilized from soil under repeated wet-dry conditions. Overlooking this might underestimate the potential risk of groundwater contamination. This study quantified the remobilization of As in the vadose zone and developed a prediction model based on soil properties. 22 unsaturated soil columns were used to simulate vadose zones with varying soil properties. Repeated wet-dry cycles were conducted upon the As-retaining soil columns. Consequently, 13.9-150.6 mg/kg of As was remobilized from the columns, which corresponds to 37.0-74.6 % of initially retained As. From the experimental results, a machine learning model using a random forest algorithm was established to predict the potential for As remobilization based on readily accessible soil properties, including organic matter (OM) content, iron (Fe) content, uniformity coefficient, D30, and bulk density. Shapley additive explanation analyses revealed the interrelated effects of multiple soil prop-erties. D30, which is inter-related with Fe content, exhibited the highest contribution to As remobilization, fol-lowed by OM content, which was partially mediated by bulk density.

Gas station sites pose potential risks of soil and groundwater contamination, which not only threatens public health and property but may also damage the assets and reputation of businesses and government entities. Given the complex nature of soil and groundwater contamination at gas station sites, this study utilizes field data from basic and environmental information, maintenance information for tank and pipeline monitoring, and environmental monitoring to develop machine learning models for predicting potential contamination risks and evaluating high-impact risk factors. The research employs three machine learning models: XGBoost, LightGBM, and Random Forest (RF). To compare the performance of these models in predicting soil and groundwater contamination, multiple performance metrics were utilized, including Receiver Operating Characteristic (ROC) curves, Precision-Recall graphs, and Confusion Matrix (CM). The Confusion Matrix analysis revealed the following results: accuracy of 85.1-87.4 %, precision of 86.6-88.3 %, recall of 83.0-87.2 %, and F1 score of 84.8-87.8 %. Performance ranking across all metrics consistently showed: XGBoost > LightGBM > RF. The area under the ROC curve and precision-recall curve for the three models were 0.95 (XGBoost), 0.94 (LightGBM), and 0.93 (RF), respectively. While all three machine learning approaches demonstrated satisfactory predictive capabilities, the XGBoost model exhibited optimal performance across all evaluation metrics. This research demonstrates that properly trained machine learning models can serve as effective tools for environmental risk assessment and management. These findings have significant implications for decision-makers in environmental protection, enabling more accurate prediction and control of contamination risks, thereby enhancing the preservation of ecological systems, public health, and property security.

Endocrine-disrupting chemicals (EDCs) are ubiquitous emerging environmental contaminants. However, the comprehensive impact of EDCs on soil ecosystems, particularly on the model organism Eisenia fetida, remains inadequately understood due to disparate experimental and assessment methods. A meta-analysis was conducted to analyze the effects of EDCs on earthworm functional traits, including survival, behavior, growth, reproduction, and cellular responses. The analysis revealed that EDCs significantly impaired earthworm survival (-17.5%, p < 0.05), behavior (- 62.2%, p < 0.001), growth (-11.5%, p < 0.001), and reproduction (- 36.7%, p < 0.001). EDCs induced substantial oxidative stress, evidenced by a 36.5% (p <0.001) increase in reactive oxygen species (ROS) production and elevated oxidative damage. The antioxidant defense system showed compensatory activation, with enhanced superoxide dismutase (10.0%) and catalase (8.90%) activities and glutathione levels (23.3%) (p < 0.001). The present study found chemical-specific toxicity patterns with heavy metals causing the most severe effects on behavior and reproduction. Toxicity profiles varied with exposure concentration and duration, revealing complex dose-response and temporal relationships. These findings provide crucial insights for the ecological risk assessment of EDCs and establish a foundation for developing targeted mitigation strategies. Furthermore, the findings highlight the importance of taking multiple endpoints into account when evaluating the toxicity of EDCs and suggest possible directions for future research.

The parameters of the soil water characteristic curve (SWCC) play a pivotal role in the examination of unsaturated soil behavior. This study employs three machine learning models-random forest (RF), extreme gradient boosting (XGBoost), and multiexpression programming (MEP)-to predict the SWCC using key soil properties. Among them, the RF model demonstrated the most robust performance in SWCC prediction. The Shapley Additive Explanation (SHAP) analysis further reveals that suction is the most influential factor affecting SWCC predictions, with other input parameters also contributing significantly. Additionally, the MEP model offers a straightforward expression for SWCC estimation and, thus, proved practical for predicting embankment responses and exhibited superior accuracy over traditional methods, such as the Arya and Paris model (ACAP). For a precise assessment of the hydromechanical response of the embankment subjected to infiltration, an increase in pore pressure is observed when employing the MEP model compared to the ACAP model for fine-grained soils. The findings emphasize the potential of RF and MEP in enhancing SWCC prediction and their practical implications for soil engineering applications.

Corn earworm, Helicoverpa zea Boddie (Lepidoptera: Noctuidae), is a common herbivore that causes economic damage to agronomic and specialty crops across North America. The interannual abundance of H. zea is closely linked to climactic variables that influence overwintering survival, as well as within-season host plant availability that drives generational population increases. Although the abiotic and biotic drivers of H. zea populations have been well documented, prior temporal H. zea modeling studies have largely focused on mechanistic/simulation approaches, long term distribution characterization, or degree day-based phenology within the growing season. While these modeling approaches provide insight into H. zea population ecology, growers remain interested in approaches that forecast the interannual magnitude of moth flights which is a key knowledge gap limiting early warning before crops are planted. Our study used trap data from 48 site-by-year combinations distributed across North Carolina between 2008 and 2021 to forecast H. zea abundance in advance of the growing season. To do this, meteorological data from weather stations were combined with crop and soil data to create predictor variables for a random forest H. zea forecasting model. Overall model performance was strong (R2 = 0.92, RMSE = 350) and demonstrates a first step toward development of contemporary model-based forecasting tools that enable proactive approaches in support of integrated pest management plans. Similar methods could be applied at a larger spatial extent by leveraging national gridded climate and crop data paired with trap counts to expand forecasting models throughout the H. zea overwintering range.

Different slope geohazards have different causal mechanisms. This study aims to propose a method to investigate the decision-making mechanisms for the susceptibility of different slope geohazards. The study includes a geospatial dataset consisting of 1203 historical slope geohazard units, including slope creeps, shallow slides, rockfalls and debris flows, and 584 non-geohazard units, and 22 initial condition factors. Following a 7:3 ratio, the data were randomly divided into a test set and a training set, and an ensemble SMOTE-RF-SHAP model was constructed. The performance and generalization ability of the model were evaluated by confusion matrix and the receiver operating characteristic (ROC) for the four types of geohazards. The decision-making mechanism of different geohazards was then identified and investigated using the Shapley additive explanations (SHAP) model. The results show that the hybrid optimization improves the overall accuracy of the model from 0.486 to 0.831, with significant improvements in the prediction accuracy for all four types of slope geohazards, as well as reductions in misclassification and omission rates. Furthermore, this study reveals that the main influencing factors and spatiotemporal distribution of different slope geohazards exhibit high similarity, while the impacts of individual factors and different factor values on different slope geohazards demonstrate significant differences. For example, prolonged continuous rainfall can erode rock masses and lead to slope creep, increased rainfall may trigger shallow mountain landslides, and sudden surface runoff can even cause debris flows. These findings have important practical implications for slope geohazards risk management. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).

China has a vast land area, with mountains accounting for 1/3 of the country's land area. Flooding in these areas can cause significant damage to human life and property. Therefore, rainstorms and flood hazards in Huangshan City should be accurately assessed and effectively managed to improve urban resilience, promote green and low-carbon development, and ensure socio-economic stability. Through the Random Forest (RF) algorithm and the Soil Conservation Service (SCS) model, this study aimed to assess and demarcate rainstorm and flood hazard risks in Huangshan City. Specifically, Driving forces-Pressure-State-Impact-Response (DPSIR)'s framework was applied to examine the main influencing factors. Subsequently, the RF algorithm was employed to select 11 major indicators and establish a comprehensive risk assessment model integrating four factors: hazard, exposure, vulnerability, and adaptive capacity. Additionally, a flood hazard risk zoning map of Huangshan City was generated by combining the SCS model with a Geographic Information System (GIS)-based spatial analysis. The assessment results reveal significant spatial heterogeneity in rainstorm and flood risks, with higher risks concentrated in low-lying areas and urban fringes. In addition, precipitation during the flood season and economic losses were identified as key contributors to flood risk. Furthermore, flood risks in certain areas have intensified with ongoing urbanization. The evaluation model was validated by the 7 July 2020 flood event, suggesting that Huangshan District, Huizhou District, and northern Shexian County suffered the most severe economic losses. This confirms the reliability of the model. Finally, targeted flood disaster prevention and mitigation strategies were proposed for Huangshan City, particularly in the context of carbon neutrality and green urbanization, providing decision-making support for disaster prevention and emergency management. These recommendations will contribute to enhancing the city's disaster resilience and promoting sustainable urban development.

Offshore wind power is a hot spot in the field of new energy, with foundation construction costs representing approximately 30% of the total investment in wind farm construction. Offshore wind turbines are subjected to long-term cyclic loads, and seabed materials are prone to causing stiffness degradation. The accurate disclosure of the mechanical properties of marine soil is critical to the safety and stability of the foundation structure of offshore wind turbines. The stiffness degradation laws of mucky clay and silt clay from offshore wind turbines were firstly investigated in the study. Experiments found that the variations in the elastic modulus presented L-type attenuation under small cyclic loads, and the degradation coefficient fleetingly decayed to the strength progressive line under large cyclic loads. Based on the experimental results, a random forest prediction model for the elastic modulus of the submarine soil was established, which had high prediction accuracy. The influence of testing the loading parameters of the submarine soil on the prediction results was greater than that of the soil's physical property parameters. In criticality, the CSR had the greatest impact on the prediction results. This study provides a more efficient method for the stiffness degradation assessment of submarine soil materials in offshore wind farms.