Usage of Machine Learning Algorithms for Structural Boundaries Reconstruction Using The Non-Seismic Methods Data with Feature Selection

Abstract

Summary Non-seismic methods (NSM) in geophysics are a crucial addition to classical seismic information. It helps to make decisions at early stages of geological exploration in case of limited information value conditions and provide a new knowledge about geological structure. While seismic exploration remains as the most spreading technique in field geophysics, non-seismic methods predominantly play a role of auxiliary methods, more often particular cases advocate self-sufficiency of NSM in application to exploration geophysical problems. The restoration of structural boundaries is especially important to restore structural boundaries in the space between seismic survey profiles. A simple solution in the form of interpolation does not provide the necessary prediction accuracy, and requires the creation of a complex, often nonlinear model, which is possible using machine learning (ML) methods. There is a large number of features at one measurement point – the values of the geophysical fields and their transformations (derivatives, filters in a window of different widths). The analysis of the importunateness of each feature before training the ML algorithm allows you to increase the accuracy of the constructed model.