Computed tomography technology has contributed greatly to the visualization of soil internal structure. Complex topological structure and spatial distribution of pores have become a focal area for studying the spatiotemporal evolution of soil structure. This is significant for understanding soil functions and ecological processes. Image-processing software, such as ImageJ and Image Pro-Plus, is widely used to visualize and quantify soil pores. However, it does not account for the irregularity and heterogeneity of pore structure, leading to low segmentation accuracy and inaccurate description of pore morphology. Therefore, we used the simplified convolutional network (SCN) method to segment the pore structure and proposed a parallel thinning method to extract the pore skeleton structure. Thereafter, using three-dimensional modelling and quantitative analysis, we initially examined the spatiotemporal evolution of soil pores during freeze–thaw cycles. Based on the custom rule model and soil pore real model, we evaluated the performance of the distance transform method and parallel thinning method in extracting the pore skeleton structure. The parallel thinning method more effectively described the topological characteristics of pores, and the pore skeleton model had better centrality, refinement and connectivity. Quantitative analysis of pore characteristics illustrates that, although freeze–thaw cycles can affect pore structure at different scales, they do not regularly affect pore macroporosity and the three-dimensional fractal dimension. These results illustrate that the soil pore structure of the viscous layer is sensitive to freeze–thaw cycles and provides preliminary evidence that seasonal freeze–thaw cycles can cause a soil water retention effect and weaken resistance to erosion. This study presents a novel technique for examining soil function at the pore scale and a theoretical foundation for future research on soil structure and hydrology.

中文翻译：

---

基于土壤CT图像的孔隙三维形态结构模型表征与定量分析

计算机断层扫描技术为土壤内部结构的可视化做出了巨大贡献。复杂的拓扑结构和孔隙空间分布已成为研究土壤结构时空演化的重点领域。这对于理解土壤功能和生态过程具有重要意义。图像处理软件，如 ImageJ 和 Image Pro-Plus，被广泛用于可视化和量化土壤孔隙。然而，它没有考虑孔隙结构的不规则性和异质性，导致分割精度低和孔隙形态描述不准确。因此，我们采用简化卷积网络（SCN）方法对孔隙结构进行分割，并提出了一种并行细化方法来提取孔隙骨架结构。此后，使用三维建模和定量分析，我们初步研究了冻融循环过程中土壤孔隙的时空演变。基于自定义规则模型和土壤孔隙真实模型，我们评估了距离变换方法和平行细化方法在提取孔隙骨架结构方面的性能。平行细化方法更有效地描述了孔隙的拓扑特征，孔隙骨架模型具有更好的中心性、细化性和连通性。孔隙特征的定量分析表明，虽然冻融循环可以在不同尺度上影响孔隙结构，但它们并没有规律地影响孔隙大孔隙度和三维分形维数。这些结果说明粘性层的土壤孔隙结构对冻融循环敏感，并提供了初步证据表明季节性冻融循环会引起土壤保水效应并减弱土壤侵蚀的抵抗力。本研究提出了一种在孔隙尺度上检测土壤功能的新技术，并为未来土壤结构和水文研究奠定了理论基础。