Extreme gradient boosting regression model for soil thermal conductivity

The thermal conductivity estimation for the soil is an important step many geothermal applications. But it a difficult and complicated process since involves variety of factors that have significant effects on soils such as moisture granular structure. In this study, regression was performed with extreme gradient boosting algorithm to develop model estimating value. performance measured unseen test data. As result, proposed reached 0.18 RMSE, 0.99 R2, 3.18% MAE values which state encouraging.