Symmetric Autoencoder Based Method For Detection Of Sub Surface Anomalies And A System Thereof

Abstract: SYMMETRIC AUTOENCODER-BASED METHOD FOR DETECTION OF SUB-SURFACE ANOMALIES AND A SYSTEM THEREOF The present disclosure utilizes a novel cost-effective and time-efficient tool to detect sub-surface anomalies, utilizing measured noise from a passive seismic source. The seismic waves produced by the noise from the passive seismic source are captured by seismic sensors, which are, in turn, collected and processed by a data acquisition system to distinguish the signature of the anomaly amidst the noise generated by the passive seismic source using a symmetric autoencoder (SymAE). The SymAE is trained to learn the capability of disentangling subsurface information, which is coherent across multiple noise gathers, from the remaining source effects. The SymAE extracts backscattered surface waves attributed to the anomaly, utilizing nearly half the recorded noise compared to that required for cross-correlation stacking approaches. Fig. 1

Patent Information

Applicants

Inventors

Specification

Documents

Application Documents

Search Strategy