Estimating onedimensional models from frequencydomain electromagnetic data using modular neural networks

An artificial neural network interpretation system is being used to interpret data from a frequencydomain electromagnetic (EM) geophysical system in near real time. The interpretation system integrates 45 separate networks in a data visualization shell. The networks produce interpretations at three different transmitterreceiver (TxRx) separations for halfspace and layeredearth interpretations. Modular neural networks (MNN's) were found to be the only paradigm that could successfully perform the layeredearth interpretations. An MNN with 16 inputs, five local experts, each with seven hidden processing elements, and three outputs was trained on 4795 patterns for 200 epochs. For twolayer models with a resistivity contrast greater than 2:1, resistivity estimates had greater than 96% accuracy for the firstlayer resistivity, greater than 98% for the secondlayer resistivity, and greater than 96% for the thickness of the first layer. If the contrast is less than 2:1, the resistivity accuracies are unaffected but thickness estimates for layers less than 2 m are unreliable. A TxRx separation of 16 m with maximum depth of penetration of 8 m was assumed for the example cited.