.png){kind=icon}
.png){kind=icon}
Return
Reservoir temperature prediction utilizing a least squares boosting model optimized by kepler optimization algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.geothermics.2026.103612.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• This study proposes a Kepler Optimization Algorithm-based Least Squares Boosting (KOA-LSB) model. • Use Isolation Forest and SMOTE to process the dataset. • An explainable prediction named SHAP of reservoir temperature using machine learning was proposed. • The R2 of KOA-LSB is 0.98249, which can achieve the degree of accurate prediction. • SHAP interpretation revealed that SiO2 is the most influential variable for the model's prediction.