Water conveyance channels in cold and arid regions pass through several saline-alkali soil areas. Canal water leakage exacerbates the salt expansion traits of such soil, damaging canal slope lining structures. To investigate the mechanical properties of saline clay, this study conducted indoor tests, including direct shear, compression, and permeation tests, and scanning electron microscopy (SEM) analysis of soil samples from typical sites. This study aims to elucidate the impact of various factors on the mechanical properties of saline clay from a macro-micro perspective and reveal its physical mechanisms. A prediction model is formulated and validated. The findings indicate the following: (1) Cohesion in direct shear tests has a linear negative correlation with water content and a positive correlation with dry density and initially decreases with increasing salt content until 2%, after which it increases. The internal friction angle initially increases and then decreases with increasing water content, reaching a peak at the optimal water content, and then gradually increases with dry density while initially decreasing, followed by an increase in salt content, stabilizing thereafter. Water content, dry density, or salt content chiefly affect cohesion by influencing electrostatic attraction, van der Waals forces, particle cementation, and valence bonds at particle contact points. (2) Compression tests reveal a linear positive correlation between the compression coefficient and water content, a negative correlation with dry density, and a stepwise linear correlation with salt content, peaking at 2%. The compression index decreases with increasing water content and dry density, following a trend similar to that of the compression coefficient with increasing salt content. The rebound index shows a linear negative correlation with water content and dry density, transitioning from a negative to a positive correlation at 2% salt content. Scanning electron microscopy analysis revealed particle flattening and increased aggregation with increasing consolidation pressure, reducing compressibility. Large pores and three-dimensional porosity have the greatest influence on soil compressibility. (3) Permeability tests reveal an exponential negative correlation between the permeability coefficient and dry density. As the dry density increases, the particle arrangement becomes denser, decreasing the pore quantity, with micropores disproportionately impacting the permeability coefficient. An increase in salinity initially increases the permeability coefficient before it decreases. The boundary point of the 2% salt content divides the effect of salt ions from promoting free water flow to blocking seepage channels, with the proportion of micropores being the primary influencing factor. (4) Employing statistical theory and machine learning algorithms, dry density, water content, and salinity are used to predict mechanical index values. The improved particle swarm optimization-support vector regression (PSO-SVR) model has high accuracy and general applicability. These findings offer insights for the construction and upkeep of open channel projects in arid regions.

Permafrost, a major component of the cryosphere, is undergoing rapid degradation due to climate change, human activities, and other external disturbances, profoundly impacting ecosystems, hydroclimate, engineering geological stability, and infrastructure. In Northeast China, the thermal dynamics of Xing'an permafrost (XAP) are particularly complex, complicating the accurate assessment of its spatial extent. Many earlier mapping efforts, despite significant progress, fall short in accounting for some key local geo-environmental factors. Thus, this study introduces a new approach that incorporates four key driving factors-biotic, climatic, physiographic, and anthropogenic-by integrating multisource datasets and in situ observations. Four machine learning (ML) models [random forest (RF), support vector machine (SVM), logistic regression (LR), and extreme gradient boosting (XGB)] are applied to simulate permafrost distribution and probability, as well as to evaluate their performance. The results indicate that models' accuracy, ranked from highest to lowest, is as follows: RF (area under the curve (AUC) =0.88 and accuracy =0.81), XGB (0.86 and 0.77), LR (0.81 and 0.73), and SVM (0.76 and 0.66), with RF emerging as the most effective model for permafrost mapping in Northeast China. Analysis of the relationships between predictors and permafrost occurrence probability (POP) indicates that vegetation and snow cover exert nonlinear effects on permafrost, while human activities significantly reduce POP. Additionally, finer soil textures and higher soil organic matter content are positively correlated with increased POP. The modeling results, combined with field survey data, also show that permafrost is more prevalent in lowlands than in uplands, confirming the symbiotic relationship between permafrost and wetlands in Northeast China. This spatial variation is influenced by local microclimates, runoff patterns, and soil thermal properties. The primary sources of model error are uncertainties in the accuracy of multisource datasets at different scales and the reliability of observational data. Overall, ML models demonstrate great potential for mapping permafrost in Northeast China.

This study aims to improve the forecasting performance of slope stability for impacting environmental sustainability and infrastructure safety predictions by using the Binary Particle Swarm Optimization BPSO technique is utilized to select relevant features from the dataset, thereby improving the overall effectiveness of the predictive models. The research includes 108 slope stability examples, with the dataset split between 70% training and 30% validation. The dataset comprises seven input parameters: cohesiveness, slope angle, unit weight, angle of internal friction, slope height, pore water pressure coefficient, and factor of safety. The objective is to classify the slope status, turning the problem into a classification task. To obtain optimal hyper-parameters for the SVM model, Grid Search was exploited. The accuracy of the slope stability predictions given by several models was assessed using receiver operating characteristic (ROC) curves. The results indicate that the BPSO-SVM model outperforms the standalone SVM and BPSO models, serving as a robust computational tool capable of accurately predicting slope stability to enhance the environmental sustainability.

The electrical conductivity of soil is closely associated with various physical properties of the soil, and accurately establishing the interrelationship between them has long been a critical challenge limiting its widespread application. Traditional approaches in geotechnical engineering have relied on specific conduction mechanisms and simplifying assumptions to construct theoretical models for electrical conductivity. This paper adopts a different approach by using machine learning methods to predict the electrical conductivity of clay materials. A reliable dataset was generated using the quartet structure generation set to create random clay microstructures and calculate their electrical conductivity. Based on this dataset, machine learning methods such as least squares support vector machine and backpropagation neural networks outperform theoretical models in terms of prediction accuracy and resistance to interference, with a coefficient of determination (R2) exceeding 0.995 when unaffected by disturbances. The computation of Shapley values for input features aids in explicating the machine learning model. The results reveal that saturation is a key feature in predicting electrical conductivity, while porosity and constrained diameter are relatively less important. Finally, an already trained model is applied to the one-dimensional electroosmosis-surcharge preloading consolidation theory. The results of the calculations demonstrate that neglecting changes in soil electrical conductivity during electroosmosis can lead to an overestimation of the absolute values of anode excess pore water pressure and soil settlement.

Petroleum pollution in soil is very damaging to the areas affected by the accidental release of petroleum hydrocarbons and has destructive impacts on natural resources and environmental health. Therefore, its monitoring and analysis are critical, however, due to the cost and time associated with chemical approaches, finding a quick and cost-effective analytical method is valuable. This study was conducted to evaluate the potential of using visible near infrared (Vis-NIR) spectroscopy to predict total petroleum hydrocarbons (TPH) in polluted soils around the Shadegan ponds, in southern Iran. One hundred soil samples showing various degrees of pollution were randomly collected from topsoil (0-10 cm). The soil samples were analyzed for TPH using Vis-NIR reflectance spectroscopy in the laboratory and then following application of preprocessing transformation, partial least squares PLS regression as well as two machine learning models including random forest (RF), and support vector machine (SVM) were examined. The results showed that the reflectance values at 1725 nm and 2311 nm, respectively, served as indicative TPH reflectance features, exhibiting weaker reflection with rising TPH. Among the preprocessing methods, the baseline correction method indicated the highest performance than the others. According to the evaluation model criteria in the validation dataset, the efficiency of the three selected models was observed in the following order SVM > RF > PLS regression. The SVM model provided the best performance in the validation dataset with r(2) = 0.85, root mean of square (RMSEP = 1.59 %, and the ratio of prediction to deviation (RPD) = 2.6. Overall, this study provided strong evidence supporting the considerable potential of Visible-NIR spectroscopy as a rapid and cost-effective technique for estimating TPH levels in oil-contaminated soils, surpassing traditional chemical analytical methods. Applying the mid-infrared spectrum (MIR) in combination with Visible-NIR data is expected to provide more comprehensive and accurate results when assessing soils in polluted areas, thereby enhancing the accuracy and reliability of the results across a diverse range of soil types.

Increasing global warming has led to the incremental retreat of glaciers, which in turn affects the water supply of the rivers dependent on glacier melts. This is further affected by the increases in flooding that is attributable to heavy rains during the snowmelt season. An accurate estimation of streamflow is important for water resources planning and management. Therefore, this paper focuses on improving the streamflow forecast for Kaidu River Basin, situated at the north fringe of Yanqi basin on the south slope of the Tianshan Mountains in Xinjiang, China. The interannual and decadal scale oceanic-atmospheric oscillations, i.e.,Pacific decadal oscillation (PDO), North Atlantic oscillation (NAO), Atlantic multidecadal oscillation (AMO), and El Nino-southern oscillation (ENSO), are used to generate streamflow volumes for the peak season (April-October) and the water year, which is from October of the previous year to September of the current year for a period from 1955-2006. A data-driven model, least-square support vector machine (LSSVM), was developed that incorporated oceanic atmospheric oscillations to increase the streamflow lead time. Based on performance measures, predicted streamflow volumes are in agreement with the measured volumes. Sensitivity analyses, performed to evaluate the effect of individual and coupled oscillations, revealed a stronger presence of coupled PDO, NAO, and ENSO indices within the basin. The AMO index shows a pronounced effect when individually compared with the other oscillation modes. Additionally, model-forecasted streamflow is better than that for climatology. Overall, very good streamflow predictions are obtained using the SVM modeling approach. Furthermore, the LSSVM streamflow predictions outperform the predictions obtained from the most widely used feed-forward back-propagation models, artificial neural network, and multiple linear regression. The current paper contributes in improving the streamflow forecast lead time, and identified a coupled climate signal within the basin. The increased lead time can provide useful information to water managers in improving the planning and management of water resources within the Kaidu River Basin. (C) 2013 American Society of Civil Engineers.