Intelligent Salt domes depth estimation through General Regression Neural Networks using gravity data, case study: salt dome of Mors oil field in Denmark

Artificial neural network (ANN) is an intelligent tool which mimics the human's brain. Today, this tool has a variety applications in science, engineering, social science, economic and etc. Along with these applications, it has a lot of wide usage in oil industry and geophysics as well. The method ofArtificial Neural Network is used as a suitable tool for intelligent interpretation of gravity data in this paper. We aim to model the salt dome in order to get the features of anomaly from gravity data by 2D forward modeling then a Multi-Layer Perceptron (MLP) and a Generalized Regression NeuralNetwork (GRNN) is trained for depth estimation of salt domes from gravity data. The approach was applied to both synthetic and real data. The real data is gravity data over Mors . Salt dome located in Denmark and the estimated depth is very close to the real depth of the salt dome and also very closes to normal full gradient method results

Keywords:

gravity , Salt dome , GRNN , Neural networks , oil field