In the construction of deep foundation pits, early warning measures are essential to reduce construction risks and prevent personnel injuries. In underground structure and pressure analysis, soil layer and support structure data are indispensable. Therefore, soil layer reconstruction serves as a critical step, while sparse borehole data limit the accuracy of traditional reconstruction methods. This paper proposes a machine learning-based soil layer reconstruction method to address this issue. First, various types of borehole and soil layer data are generated by simulating the formation process of Earth’s soil layers, thereby providing sufficient training data. Subsequently, a coding algorithm is designed to extract soil layer features as inputs for the convolutional neural network. Finally, 3D meshing is performed on the soil layer generated from real boreholes, and soil model rendering is achieved through a voxel clustering algorithm. The algorithm achieved an accuracy rate of over 90% in tests and demonstrated excellent robustness. By applying this algorithm, we successfully reconstructed the soil layers at a typical foundation pit site in a Chinese city, validating its effectiveness in real-world scenarios and its potential for large-scale engineering applications.

This work investigated the stabilization mechanisms and β-carotene encapsulation characteristics of cellulose nanofibrils (CNFs) stabilized Pickering emulsions (PE) prepared by different emulsification processes. For 48 days of storage, ultrasound-prepared Pickering emulsions (US-PE) stabilized by at least 2.0 wt.% CNFs have obvious cream stabilization, and high-pressure homogenization-prepared Pickering emulsions (HPH-PE) stabilized by over 1.6 wt.% CNFs have excellent cream stabilization. The stabilization of HPH-PE, which was superior to that of US-PE, mainly relied on the steric stabilization of CNFs’ space networks. Although the encapsulation efficiency of β-carotene in US-PE was higher than that in HPH-PE when the CNF concentration was over 1.2 wt.%, the retention rate of β-carotene in US-PE was obviously lower than that in HPH-PE. So, the internal space structure of CNF-stabilized HPH-PE was conducive to stabilizing the emulsion and protecting the bioactive molecule.

High-fidelity computational fluid dynamics (CFD) remains computationally expensive for steady aerodynamic prediction under multi-condition and variable-geometry configurations, which limits rapid design iteration. To address this issue, this study proposes a data-driven surrogate framework for aircraft surface flow-field prediction on irregular meshes. The framework combines a geometry-unification strategy for variable rudder-deflection configurations with KM-GAT, a hybrid neural architecture that integrates graph attention and KAN-based nonlinear feature transformation. Geometry unification maps the surface flow fields associated with different rudder-deflection states onto a common zero-deflection reference template, thereby establishing consistent mesh correspondence and fixed prediction locations across samples while retaining the rudder angle as an operating-condition variable. The KM-GAT model further combines topology-aware message passing with localized nonlinear refinement, while the Huber loss is adopted to improve training robustness for CFD-derived data. Experiments on the F-22 research model show that the proposed framework achieves lower prediction errors and more concentrated error distributions than baseline MLP and GNN-based models. Qualitative comparisons further indicate that KM-GAT better preserves localized high-gradient structures, including pressure transitions and vortex-dominated regions. These results suggest that the proposed framework provides an effective surrogate modeling strategy for variable-geometry aerodynamic flow field prediction.