Collapsibility is a unique engineering geological property of loess. Choosing appropriate parameters to build the prediction model of loess collapsibility is an essential step toward solving the loess collapsibility problem. A case study was performed for the loess in Xinyuan County of the Yili River Basin, China. A large amount of data was collected from preliminary geotechnical tests in this region. Mathematical statistics were applied to analyse the correlations between the loess collapsibility and soil parameters. Multiple linear regression and neural network theories were adopted to build this region’s prediction model of loess collapsibility. The results showed that microscopically, the soils in this region were predominantly flocculated structures. The soil particles were flaky and in bracket contact, and the pores were round or irregularly shaped. Regarding the material composition, the soils were primarily composed of quartz and albite, with a low hematite content. In the study area, the correlation coefficients between the collapsibility coefficient of the loess vs. the density, dry density, saturation, porosity ratio, and porosity varied between 0.628 and 0.857, indicating a strong or very strong correlation. In terms of predicting loess collapsibility, the effectiveness of neural networks based on RBF (radial basis function) and multiple linear regression models was contrasted. The latter was discovered to be more appropriate, dependable, and accurate, with an accuracy percentage of 94.42%. Simultaneously, the model’s assessment index is 0.014 for the root mean squared error (RMSE), 0.962 for the correlation coefficient (CC), 0.919 for the Nash–Sutcliffe efficiency coefficient (NSE), and −1.494 percent for the percent bias (PBIAS). It works well for estimating whether local loess may collapse. Therefore, the RBF neural network model built in the present study has adequate precision and meets the engineering requirements. Our research sheds new light on loess collapsibility assessment in this region.

Exposed to seasonal climate changes, the loess in the Ili region of Xinjiang, which has variable engineering properties, frequently undergoes freezing–thawing (F-T) and wetting–drying (W-D) cycles. In the present research, a series of uniaxial compression tests were conducted to investigate the collapsibility characteristics of the representative loess slope in the Ili region. In parallel, scanning electron microscopy (SEM) and nuclear magnetic resonance (NMR) tests were conducted. The test results obtained from the research indicated that both F-T cycles and W-D cycles exacerbate the deterioration of the loess, with the most severe effects observed after 6–10 cycles. Under the combined physical cycles, the microstructure of the loess progressively evolves from the relatively aggregated state to the dispersed one. Meanwhile, the porosity of the loess exhibited an initial increase with the number of W-D cycles, followed by an obvious decrease. Note that the pattern of the loess experiences fluctuation, which was achieved at the given point with the increased number of F-T cycles. It is suggested that the variability in loess wetting collapse is attributed to the irreversible alteration in the microstructure attributed to the combined cycles. The main reasons for the occurrence of loess collapse are the frost heaving force and the swelling–shrinking action. The impacts of W-D and F-T cycles on the loess obtained from this research can make a contribution to the in-depth understanding about loess collapse in the Ili valley.

The study of geothermal genesis mechanism is the basis for the evaluation and effective development of geothermal field resources. On the basis of previous research results, the formation mechanism of geothermal field in Qikexing Township was analysed and the geothermal resources were evaluated by identifying geothermal anomalies in the area. In this paper, two geothermal anomalies were identified based on remote sensing inversion, soil chemical exploration, shallow temperature measurement and the main heat-control fractures, and the distribution characteristics and causes of hot springs were comprehensively studied by means of hydrogeochemistry and isotope analysis. The results show that the sources of geothermal water recharge are atmospheric precipitation and ice melt water in the vicinity. The cations of the geothermal water are mainly Na⁺, with an anionic ratio of 68.75%, followed by Ca²⁺ and K⁺; the anions are mainly SO⁴₂₋, with an anionic ratio of 47.25%, followed by Cl⁻ and HCO₃⁻; and the geothermal water is of the Cl·SO₄-Na(Ca) type. The geothermal wells are mainly distributed along the active fracture spreading direction in the form of beads, and the maximum depth of thermal storage cycle is 2393 m. The temperature of thermal storage ranges from 49.4 to 93.7 ℃, and the heat source mainly comes from the heat transfer of mantle channel flow, the heat generated by the decay of radioactive elements, the heat generated by magmatic activities and so on. The results of the evaluation of geothermal resources in the study area show that the total geothermal resources are 1.38 × 10¹⁹ J/a, equivalent to 4.71 × 10⁸ t/a of standard coal. This study mainly focuses on the distribution law of hydrothermal geothermal resources in Yanqi Qikexing town and the geothermal genesis, which can provide a reference basis for the development and utilisation of geothermal resources in Yanqi County in the later stage.

Qapqal Xibe Autonomous County is located in the central Yili Basin of Xinjiang. It possesses significant potential for geothermal resource development, but the lack of in-depth research on deep geothermal genetic mechanisms and refined resource evaluation restricts its large-scale utilization. Therefore, this paper integrates regional geological surveys, borehole thermometry, geophysical exploration, and hydrochemical and isotopic tracing to reveal the formation mechanism of the geothermal field. Furthermore, it quantitatively evaluates the resource potential and analyzes uncertainties by combining the volumetric method, analytical method, and Monte Carlo simulations. The results indicate that the shallow geothermal gradient is 2.2 °C/100 m, while the deep gradient increases to 3.8 °C/100 m. The Gagestai Fault and its secondary faults serve as dominant channels for deep thermal fluid migration. The Cretaceous Donggou Formation and the Jurassic Badaowan Formation constitute a dual-layer high-quality reservoir, with measured reservoir temperatures of 42.50 °C and 91.25 °C, respectively. Isotopic and hydrochemical analyses infer that the geothermal water mainly originates from atmospheric precipitation and snowmelt in mountainous areas. After long-distance deep circulation, cation exchange, and heating by the basement heat source, the fluid upwells along the faults to accumulate, forming a typical layered confined fault-controlled geothermal system. Resource evaluation, verified by Monte Carlo simulations, demonstrates that the volumetric method exhibits higher robustness at the current exploration stage. The total recoverable heat in the study area is 8.19 × 10¹⁶ J, classifying it as a medium-sized geothermal field. Rational development of these resources could save approximately 2.75 × 10⁶ tons of standard coal and reduce CO₂ emissions by about 7.315 × 10⁶ tons. This study provides key parameters and a scientific basis for geothermal resource development in the Yili Basin, holding significant practical value for promoting the clean energy industry in Xinjiang and achieving the "dual carbon" goals.

The area around Wenquan County, Xinjiang, is home to numerous hot springs and abundant geothermal resources, offering significant potential for development and utilization. Currently, systematic research on the formation mechanisms of geothermal fields in this region remains relatively limited, which to some extent constrains the comprehensive development and utilization of Wenquan County’s geothermal resources. This study selected the area around Wenquan County as the study area and employed methods such as remote sensing interpretation, ground temperature measurement, geophysical exploration and drilling, geothermal gradient calculations, rock radioelement measurements, hydrochemical analysis, and isotope analysis to elucidate the genesis mechanisms of the geothermal field. The results indicate that: (1) The geothermal anomaly areas in the Wenquan County geothermal field are primarily controlled by fault structures such as F2, F4, F3-1, and F17. The average geothermal gradient reaches 11.53°C/100 m, and the heat flow value of 320 mW/m ² is significantly higher than the average heat flow value at the northwestern margin of the Junggar Basin in Xinjiang, indicating a favorable terrestrial heat flow background. (2) Within the study area, well-developed structural fissures formed at the intersections of F2, F17, and F3-1, coupled with fractured rock masses, provide favorable conditions for groundwater storage and hydrothermal exchange. Based on the silica geothermometer, the average reservoir temperature is estimated at 132.4°C. Analysis indicates that the geothermal reservoir is located within structurally fractured zones, extending in a strip-like pattern on the surface, and belongs to the medium-low temperature belt-type geothermal reservoir. (3) The geothermal water in the study area has a SO ₄ -Na hydrochemical type, originating from the infiltration of atmospheric precipitation in the southern Biezhentao Mountain area. It has undergone intense water-rock interactions, including hydrothermal alteration, sulfide oxidation, and decarbonation, transporting deep-seated heat to the surface through fault fracture zones. This study has essentially clarified the genesis model of the Wenquan County geothermal field, providing a crucial basis for the development and utilization of geothermal resources.

Loess compressibility is a crucial engineering parameter governing the deformation of loess foundations and the evolution of slope geohazards. Based on a comprehensive collection of physical, hydraulic, and mechanical parameters of loess in the Ili region, this study selected Huocheng, Nilka, and Xinyuan counties as typical study areas. Statistical methods were employed to a perform normality tests and necessary transformations on the data, followed by correlation analysis to identify key factors influencing the compression coefficient. Using Multiple Linear Regression (MLR) as a baseline, six machine learning models were constructed, including Random Forest (RF), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Support Vector Machine (SVM), Classification and Regression Tree (CART), and XGBoost models. The results indicate that the compression coefficient is significantly positively correlated with the void ratio and negatively correlated with dry density and compressibility modulus. Consequently, compressibility modulus, dry density, and void ratio were selected as core input indicators. All constructed models successfully predicted the compression coefficient and its engineering classification. Under the evaluation principle of “error metrics priority, classification accuracy auxiliary,” the MLP model achieved the best overall performance across the three counties, followed by the Random Forest model. This study provides a methodological basis for the rapid estimation of loess compressibility parameters and engineering judgment in the Ili region.