Fig. 6From: Machine learning to identify geologic factors associated with production in geothermal fields: a case-study using 3D geologic data, Brady geothermal field, NevadaBiplot of signal-1 (S1) vs signal-2 (S2). Production wells (red) are enclosed by the red dashed polygon. The production wells and the faults, dilation, and faultdense variables have relatively high S2 values and relatively low S1 values indicating that these variables control the separation of the production wells from the rest of the data setBack to article page