Inferring geological structural features from geophysical and geological mapping data using machine learning algorithms

We present an automated approach for inferring surface geological structures from geophysical survey data. Our method employs machine learning, using mapped as labels and filtered surveys reference maps. compared the performance of eight main learning algorithms their 32 branches. Applied to Geological Survey Victoria's database Bendigo Zone, following appropriate choice features, 3-class classification model subspace K-nearest neighbour methods achieves a stable validated 92% accuracy in around 1 min. The fault-only 97% 6 This shows that structural features on may be inferred between one three data types: gravity, airborne total magnetic intensity first vertical derivative intensity. It prospect research suggests combined with useful efficient determining existence features.