ABSTRACT
Thermal conductivity is a parameter of interest in a wide variety of applications, such as the geological final disposal of spent nuclear fuel or geothermal energy. Traditional methods for estimating thermal conductivity rely on laboratory testing or time-consuming in-situ measurements that provide at best sparse data. Thus, there exists a demand for methods that can produce reliable and comprehensive thermal conductivity data faster and more cost-effectively. This study continues to explore the possibility of predicting thermal conductivity based on optical image data using machine learning.
