This study presents a new model to predict the static formation temperature at multiple oil fields using multiple machine learning algorithms. Results are compared with the real temperatures obtained from two wells. The model developed in this study predicts static formation temperature according to several machine learning algorithms including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. The following are the key findings: various geothermal wells in distinct fields or formations may have different machine learning connections. However, if a connection is defined using adequate field data, it is clear that static formation temperature can be approximated with great accuracy. Based on machine learning models, we developed a novel model for forecasting static formation temperature, examined the modeling data and outcomes, and found that Random Forest, Fuzzy logic, and K-nearest neighbors outperformed Artificial Neural Network. Therefore, the performance of the proposed model for estimating static well temperature achieved a mean absolute percentage (AAPE) of 0.003%, and the coefficient of determination (R 2 ) is 0.99%. When the classical (mathematical) methods were compared to the artificial intelligence methods, the artificial intelligence methods produced more accurate results with varying percentages. The findings generated by the unique new model computation and the measured test data are substantially matched when compared to computed data and observed temperature data. The novelty of this newly developed AI model is that it will serve as a practical and inexpensive tool for SFT determination in geothermal and petroleum wells.