Geophysical Signal Processing Using Neural Networks

A comprehensive book for the geophysical exploration community on the role of neural networks in seismic signal processing problems, specifically in seismic pattern recognition, and well log data inversion. It uses the theory of John J. Hopfield, who won the 2024 Nobel Prize in Physics, to detect the seismic pattern, to solve the seismic horizon picking, and to determine the seismic velocity picking. Key topics include perceptron for classification of seismic Ricker wavelets and detection of seismic anomalies, neural network for seismic principal component analysis, Hough transform neural network for seismic pattern detection, simulated annealing for seismic pattern detection, cellular neural network for seismic pattern recognition, improved machine learning and deep learning, well log data inversion using multilayer perceptron (MLP), and expanded radial basis function network (RBF).

Features

• Covers significant advancements in deep learning and neural networks used for seismic pattern recognition.
• Presents Hopfield neural networks for seismic signal processing.
• Explores well log data inversion using neural networks.
• Discusses simulated annealing for pattern detection and seismic applications.
• Explains the need for neural networks in the petroleum industry for oil and gas exploration.

This is an excellent book for graduate and postgraduate students, and professionals in the petroleum, oil, and gas industries, as well as those with an interest in geophysical exploration.