TY - JOUR
TI - Extreme gradient boosting regression model for soil thermal conductivity
AU - Yurttakal Ahmet Haşim
JN - Thermal Science
PY - 2021
VL - 25
IS - 101
SP - 1
EP - 7
PT - Article
AB - 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 RMSE, 0.99 R2, and 3.18% MAE values which state that the algorithm is encouraging.