Application of Artificial Intelligence in Static Formation Temperature Estimation

This study presents a new model to predict the static formation temperature in multiple geothermal fields using multiple machine learning algorithms. Both artificial intelligence and non-artificial intelligent algorithms were used for this prediction. The model developed in this study predicts static formation temperature using several machine learning algorithms, including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. Results are compared with the real temperatures obtained from two geothermal wells. The random forest, fuzzy logic, and k-nearest neighbors algorithms outperformed the artificial neural network, with the random forest algorithm achieving higher accuracy. The MAE of the random forest algorithm was 0.7% and the RMSE was 0.9%. The MAE values for the other machine learning algorithms ranging from 1.5 to 8.4%, and the RMSE values ranged from 2 to 20.8%. Artificial intelligence methods were found to be more accurate than non-artificial intelligence (mathematical) methods, with varying percentages. The results 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 artificial intelligence model is that it serves as a practical and inexpensive tool for static formation temperature determination in geothermal and petroleum wells.