Lithofacies classification with transition-aware Neural Networks

Apply

Project Description

In the last couple of years, the use of Machine Learning has emerged in various areas of geoscience with the promise to automate the solution of otherwise manually intensive tasks or improve upon currently used algorithms. Lithofacies classification from well logs and seismic pre-stack data represents one of the earliest and most successful its use cases to date. Both tree- and neural network-based supervised learning methods are nowadays used to classify hundreds of well logs or entire seismic data in a matter of hours. Whilst providing high accuracy, most approaches currently ignore the fact that some classes cannot occur above others (e.g., oil is always found below gas) and, more in general, fail to produce consistent transition probabilities between the training data and predicted labels. In this project we will investigate a strategy for enforcing our prior knowledge about facies transitions through an ad-hoc extension of the cost function of NN-based classifiers. This will be followed by a thorough comparison with other state-of-the-art classifiers on synthetic and field data.
Program - Environmental Science and Engineering
Division - Physical Sciences and Engineering
Faculty Lab Link - https://mrava87.github.io
Field of Study - Geoscience

About the
Researcher

Matteo Ravasi

Matteo Ravasi

Desired Project Deliverables

The candidate will be tasked with: - Creating a synthetic dataset using basic principles of rock physics, fluid substitution and seismic modelling. - Develop and implement a novel, transition-aware NN-classifier and compare its performance with other state-of-the-art classifiers - Apply the newly developed method to a field benchmark well-log dataset (e.g., from SEG ML contest) and a field pre-stack seismic dataset (e.g., Volve data)

RECOMMENDED STUDENT ACADEMIC & RESEARCH BACKGROUND

BSc or MSc in geoscience or related discipline.
BSc or MSc in geoscience or related discipline.
Basic knowledge of a programming language (Python preferred)
Basic knowledge of a programming language (Python preferred)
Basic knowledge of Neural Networks
Basic knowledge of Neural Networks