Exploring the Hydraulic Properties of Unsaturated Soil Using Deep Learning and Digital Imaging Measurement

This work aims to improve the accuracy of traditional models for analyzing the hydraulic properties of unsaturated soil by integrating digital imaging measurement with deep learning techniques. The work first reviews current research on the basic characteristics of unsaturated soil and the applications of deep learning in this field. Next, it examines the impact of soil specimens’ physical properties on their hydraulic properties. This includes acquiring hydraulic parameters and the soil-water characteristic curve through full-surface digital imaging measurements. Finally, a soil hydraulic property model based on the backpropagation neural network (BPNN) is implemented, trained, and validated. Results indicate that the model’s predicted soil-water characteristic curve aligns closely with the experimental findings from previous studies. Moreover, the proposed BPNN-based unsaturated soil hydraulic property model uses the Levenberg–Marquardt algorithm, which reduces computational time and noise compared to alternative algorithms. Meanwhile, analysis of the model parameters suggests that ten neurons in the hidden layer provide optimal performance. By incorporating correlations between physical parameters, such as soil particle size and soil hydraulic properties, the model demonstrates lower error rates compared to other literature models. Overall, this BPNN model effectively represents the relationship between soil’s physical and hydraulic parameters, streamlining traditional soil correlation coefficient estimation.