Heilongjiang Province, the largest commercial grain base in China, experiences significant challenges due to the environmental effects on its soil. The freezing and thawing cycle in this region leads to the transport of water and heat, as well as the exchange and transfer of energy. Consequently, this exacerbates the flooding disaster in spring and severely hampers farming activities such as plowing and sowing. To gain a better understanding of the freezing and thawing mechanisms of farmland soil in cold regions and prevent spring flooding disasters, this study focuses on Heilongjiang Province as a representative area in northeast China. The research specifically investigates the frozen and thawed soil of farmland, using a large-scale low-temperature laboratory to simulate both artificial and natural climate conditions in the cold zone. By employing the similarity principle of geotechnical model testing, the study aims to efficiently simulate the engineering prototypes and replicate the process of large-span and long-time low temperatures. The investigation primarily focuses on the evolution laws of key parameters, such as the temperature field and moisture field of farmland soil during the freeze–thaw cycle. The findings demonstrate that the cooling process of soil can be categorized into three stages: rapid cooling, slow cooling, and freezing stabilization. As the soil depth increases, the variability of the soil temperature gradually diminishes. During the melting stage, the soil’s water content exhibits a gradual increase as the temperature rises. The range of water content variation during thawing at depths of 30 cm, 40 cm, 50 cm, and 80 cm is 0.12% to 0.52%, 0.47% to 1.08%, 0.46% to 1.96%, and 0.8% to 3.23%, respectively. To analyze the hydrothermal coupling process of farmland soil during the freeze–thaw cycle, a theoretical model of hydrothermal coupling was developed based on principles of mass conservation, energy conservation, Darcy’s law of unsaturated soil water flow, and heat conduction theory. Mathematical transformations were applied after defining the relative degree of saturation and solid–liquid ratio as field functions with respect to the relative degree of saturation and temperature. The simulated temperature and moisture fields align well with the measured data, indicating that the water–heat coupling model established in this study holds significant theoretical and practical value for accurately predicting soil temperature and moisture content during the spring sowing period, as well as for efficiently and effectively utilizing frozen soil resources in cold regions.

The safety associated with the bearing capacity of pile foundations is intrinsically linked to the overall safety, stability, and economic viability of structural systems. In response to the need for rapid and precise predictions of pile bearing capacity, this study introduces a kernel extreme learning machine (KELM) prediction model optimized through a multi-strategy improved beetle optimization algorithm (IDBO), referred to as the IDBO-KELM model. The model utilizes the pile length, pile diameter, average effective vertical stress, and undrained shear strength as input variables, with the bearing capacity serving as the output variable. Initially, experimental data on pile bearing capacity was gathered from the existing literature and subsequently normalized to facilitate effective integration into the model training process. A detailed introduction of the multi-strategy improved beetle optimization algorithm (IDBO) is provided, with its superior performance validated through 23 benchmark functions. Furthermore, the Wilcoxon rank sum test was employed to statistically assess the experimental outcomes, confirming the IDBO algorithm’s superiority over other prevalent metaheuristic algorithms. The IDBO algorithm was then utilized to optimize the hyperparameters of the KELM model for predicting pile bearing capacity. In conclusion, the statistical metrics for the IDBO-KELM model demonstrated a root mean square error (RMSE) of 4.7875, a coefficient of determination (R²) of 0.9313, and a mean absolute percentage error (MAPE) of 10.71%. In comparison, the baseline KELM model exhibited an RMSE of 6.7357, an R² of 0.8639, and an MAPE of 18.47%. This represents an improvement exceeding 35%. These findings suggest that the IDBO-KELM model surpasses the KELM model across all evaluation metrics, thereby confirming its superior accuracy in predicting pile bearing capacity.

The hydrothermal properties of black soils in seasonal frozen regions are more complex during the freezing process. In the context of the freezing and thawing cycles of black soil within seasonal freeze–thaw regions, there is a limited application of mathematical models to characterize the interplay between water and thermal dynamics. Therefore, existing models for analyzing water and heat in black soil in seasonal frozen regions may not be applicable or accurate. The application of existing models to the water and heat problems of black soil in seasonal frozen regions is important and innovative. This study is grounded in Darcy’s law pertaining to unsaturated soil water flow and is informed by principles of mass conservation, energy conservation, and conduction theory. The research begins with the establishment of definitions for relative saturation and the solid–liquid ratio through mathematical transformations. Subsequently, a theoretical model is developed to represent the water–heat coupling in black soil, utilizing relative saturation and temperature as field functions. The model’s validity is confirmed through its integration with experimental data from a black soil freezing and thawing model test. Furthermore, the analysis delves into the distribution of the temperature field, water field, and ice content that arise from the phase change processes occurring during the freezing and thawing of black soil roadbed slopes. There is a theoretical basis for the prevention and control of disasters associated with black soil roadbed slopes in seasonal frozen areas.

To address the complexities associated with highly nonlinear phase transitions in subbase materials subjected to unidirectional freezing—where direct observation of internal states is challenging—and the limitations of conventional numerical methods in concurrently reconstructing multiphysical fields from sparse experimental data, this study investigates saturated subbase materials from the Dashixia Project. Laboratory freezing experiments were performed, and a two-dimensional axisymmetric physics-informed neural network (PINN) model integrating thermomechanical behavior, phase transition, and deformation was developed. The model incorporated the heat conduction equation (accounting for latent heat), the freezing fraction relaxation equation, and the effective deformation equation into the loss function, employing a continuous freezing fraction to represent phase-change phenomena. Additionally, constraints on the average displacement of the top surface, enhanced sampling near the freezing front, and a dynamic weighting strategy were introduced to improve model performance. This approach enabled the simultaneous prediction of temperature, freezing fraction, and displacement fields. The model achieved a temperature prediction root mean square error (RMSE) of 4.112 °C with an R² of 0.600, and a top-surface displacement prediction RMSE of 0.0051 with an R² of 0.993. Observations indicated that the freezing front predominantly progressed from the top downward, while the displacement field exhibited a partitioned pattern characterized by negative displacement in the lower region and positive displacement in the upper region. The proposed methodology offers a novel framework for multi-field reconstruction and frost heave prediction in subgrade materials under conditions of limited observational data.