A machine learning-based approach for constructing a 3D apparent geological model using multi-resistivity data

Engineering

• Resistivity Model 100%
• Random Forest 100%
• Clay Layer 100%
• Learning System 100%
• Model Building 50%
• Electromagnetic Transient 50%
• Metrics 50%
• Radial Basis Function 50%
• Receiver Operating Characteristic 50%
• Operating-Characteristic Curve 50%
• Machine Learning Technique 50%
• Borehole 50%
• Coastal Area 50%
• Matrix Analysis 50%
• Target Area 50%
• Support Vector Machine 50%
• Confusion Matrix 50%

Keyphrases

• Resistivity 100%
• Geological Model 100%
• Machine Learning-based Approach 100%
• Supervised Machine Learning 33%
• Clay Layer 33%
• Choushui River Alluvial Fan 33%
• Python 33%
• Gravel Layer 33%
• 3D Resistivity Modeling 33%
• Taiwan 16%
• Support Vector Machine 16%
• Receiver Operating Characteristic Curve 16%
• Building Model 16%
• Transient Electromagnetic 16%
• Modeling Techniques 16%
• Coastal Area 16%
• Low Resistivity 16%
• Electromagnetic Data 16%
• Statistical Methods 16%
• Superior Performance 16%
• High Resistivity 16%
• Borehole Data 16%
• Sediment Type 16%
• Sand Layer 16%
• Resistivity Anomaly 16%
• Random Forest Algorithm 16%
• Valuable Insight 16%
• Comprehensive Approach 16%
• Tree Support 16%
• Evaluation Metrics 16%
• Data Coverage 16%
• Vertical Electrical Sounding 16%
• Extreme Gradient Boosting(XGBoost) 16%
• Resistivity Value 16%
• Random Tree 16%
• Sandy Clay 16%
• Radial Basis Function Interpolation 16%
• Confusion Matrix Analysis 16%
• Clayey Sand 16%

Earth and Planetary Sciences

• Machine Learning 100%
• Alluvial Fan 66%
• Taiwan 33%
• Borehole 33%
• Coastal Region 33%
• Interpolation 33%
• Vertical Electrical Sounding 33%
• Support Vector Machine 33%
• Matrices (Mathematics) 33%
• Sandy Clay 33%