Evaluating the Hydraulic Conductivity of Modified Loess: A Machine Learning Approach

DOI

10.2991/978-94-6463-780-9_45How to use a DOI?

Keywords

Loess; hydraulic conductivity; dry density; additives; SVR model; Gray relational analysis

Abstract

This study focuses on Lanzhou loess, exploring its permeability under various modification methods through falling-head permeability tests. The research identifies the impact of dry density, particle size characteristics, particle gradation, and additives on the permeability of modified loess. The impact of each influencing factor was assessed through grey relational analysis. Based on the experimental results and grey relational analysis, a predictive model was developed using the machine learning method of Support Vector Machines to estimate the hydraulic conductivity of modified loess Considering the combined effects of various factors. The results contribute to understanding the factors that affect the permeability of modified loess and provide a tool for more accurate predictions in engineering applications. The SVR model outperformed traditional multiple predictive models in terms of prediction accuracy, with lower root mean square errors and higher correlation coefficients. This study provides valuable insights into the modification of loess for engineering applications, offering a predictive tool for permeability in future infrastructure projects in loess-rich regions.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Guoliang Ran
AU  - Tingting Li
AU  - Xi Zhang
PY  - 2025
DA  - 2025/07/03
TI  - Evaluating the Hydraulic Conductivity of Modified Loess: A Machine Learning Approach
BT  - Proceedings of the 2025 International Conference on Engineering Management and Safety Engineering (EMSE 2025)
PB  - Atlantis Press
SP  - 497
EP  - 508
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-780-9_45
DO  - 10.2991/978-94-6463-780-9_45
ID  - Ran2025
ER  -