Advancing Subsurface Exploration: Precision Fault Detection in Vertical Electrical Sounding Data Through Machine Learning Innovations

13 May 2024
7:00 AM (CDT)

In near-surface geophysics, accurate fault detection in Vertical Electrical Sounding (VES) data is crucial for subsurface exploration and characterization. Traditional manual methods are time-consuming and subjective, necessitating automated solutions for enhanced efficiency and precision. This project aims to develop a novel approach leveraging machine learning techniques to automate fault detection in VES data. The project’s purpose is to streamline the fault detection process, enabling rapid and objective identification of subsurface faults, thereby facilitating more informed decision-making in geological and engineering applications. The approach involves preprocessing VES data, extracting informative features, and training machine learning models to classify fault zones accurately. Results demonstrate the effectiveness of the proposed approach in accurately detecting faults from VES data with high precision and recall. The trained model exhibits robust performance even with a relatively small dataset, showcasing its potential for practical deployment in real-world scenarios. Through rigorous evaluation and validation, the project underscores the viability of machine learning as a powerful tool for enhancing fault detection in near-surface geophysics. In conclusion, this project underscores the transformative potential of machine learning in revolutionizing subsurface exploration methodologies. By automating fault detection in VES data, it offers a promising solution to expedite geological assessments and optimize resource allocation in various industries reliant on subsurface characterization.

Speaker Bio

Joshua Areola

Joshua Areaola is a recent applied geophysics graduate passionate about Earth’s processes, teaching, and technology. As an ICT instructor, he teaches Python and R programming online and in person. Fluent in English, he uses data science and machine learning to solve problems with projects. He merges geophysics and advanced analytics for impactful solutions.