Machine Learning-based Prediction of In-Situ Stresses at the Utah FORGE Geothermal site

Engineering

• In Situ Stress 100%
• Learning System 100%
• Subsurface 71%
• Ultrasonics 71%
• Wave Velocity 28%
• Perceptron 28%
• Wellbore 14%
• Predicted Model 14%
• Effective Solution 14%
• Hydraulic Fracturing 14%
• Stress Model 14%
• Horizontal Wells 14%
• Rock Formation 14%
• Random Forest 14%
• Prediction Performance 14%
• Root-Mean-Squared Error 14%
• K-Means Classification Algorithm 14%
• Machine Learning Algorithm 14%
• Geomechanical Model 14%
• Geothermal Well 14%
• Maximum Horizontal Stress 14%

Earth and Planetary Sciences

• Machine Learning 100%
• Utah 100%
• Ultrasonics 75%
• Ultrasonic Radiation 50%
• Self Organizing Systems 50%
• Machine Learning Model 50%
• Acoustic Velocity 25%
• Hydraulic Fracturing 25%
• Extreme Gradient Boosting 25%

Keyphrases

• Unsupervised K-means 14%
• Robust Machine Learning Algorithms 14%