Title: Prediction of thermal conductivity of quartz chlorite schist rocks: a comparative study of MLR and ridge regression

Authors: A.K. Tripathi; S.K. Pal; Gurram Dileep; Aman Raj

Addresses: Department of Mining Engineering, Faculty of Mining Engineering, National Institute of Technology Karnataka, Surathkal, 575025, Karnataka, India ' Department of Mining Engineering, Faculty of Mining Engineering (Retd.), Indian Institute of Technology Kharagpur, Kharagpur, 721302, West Bengal, India ' Department of Mining Engineering, National Institute of Technology Karnataka, Surathkal, 575025, Karnataka, India ' Indian Institute of Technology Kharagpur, Kharagpur, 721302, West Bengal, India

Abstract: Thermal conductivity is a key physical property with broad applications in engineering and geosciences, particularly in energy-efficient building design, geothermal energy systems, and subsurface geological studies. Accurate determination of thermal conductivity is essential for understanding heat transfer mechanisms in rock materials. However, direct in-situ measurement is often impractical due to technical and logistical constraints. As a result, indirect estimation methods, which establish empirical relationships between thermal conductivity and various physico-mechanical properties, have gained attention. This study investigates the thermal conductivity of quartz chlorite schist through laboratory experiments, alongside measuring key physico-mechanical properties, including P-wave velocity, porosity, density, and uniaxial compressive strength (UCS). The objective is to analyse the correlations between thermal conductivity and these properties to develop a reliable predictive model. Multiple regression and ridge regression analysis are employed to derive an empirical equation for estimating thermal conductivity based on the measured parameters. The findings of this study contribute to improving indirect assessment techniques, which are valuable for geotechnical and geological applications where direct measurements are challenging.

Keywords: thermal conductivity; p-wave velocity; machine learning; predictive analysis.

DOI: 10.1504/IJMME.2025.146862

International Journal of Mining and Mineral Engineering, 2025 Vol.16 No.2, pp.194 - 212

Received: 09 Dec 2024
Accepted: 25 Feb 2025
Published online: 23 Jun 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article