EXTREME GRADIENT BOOSTING REGRESSION MODEL FOR SOIL THERMAL CONDUCTIVITY

Creative Commons License

Yurttakal A. H.

THERMAL SCIENCE, vol.25, 2021 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 25
  • Publication Date: 2021
  • Doi Number: 10.2298/tsci200612001y
  • Journal Name: THERMAL SCIENCE
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Directory of Open Access Journals
  • Yozgat Bozok University Affiliated: Yes

Abstract

The thermal conductivity estimation for the soil is an important step for many geothermal applications. But it is a difficult and complicated process since it involves a variety of factors that have significant effects on the thermal conductivity of soils such as soil moisture and granular structure. In this study, regression was performed with the extreme gradient boosting algorithm to develop a model for estimating thermal conductivity value. The performance of the model was measured on the unseen test data. As a result, the proposed algorithm reached 0.18 RAISE, 0.99 R-2, and 3.18% MAE values which state that the algorithm is encouraging.