Here are some resources that might be useful throughout the competition.

For specific questions please contact our team by clicking this link.

Geophysics Resources

Seismic inversion WHITEPAPER

This whitepaper by Ikon Science has a good overview of conventional linearized AVO inversion. It compares it to a more modern approach using their popular Ji-Fi tool that accounts for facies (rock type).

If you are new to this domain, this will give you a good understanding of what we are trying to achieve with Machine Learning.

Click here to visit the article.

geoscience visualization software

We recommend that you use 3D software to visually QC and interpret your inputs/outputs. One free solution would be OpendTect from dGB Earth Sciences.

TerraNubis also has an OpendTect project built up with the Poseidon dataset where users can download. License: Creative Commons 3.0

Click here to download OpendTect, and here to see the TerraNubis project.

What is seismic data?

Seismic data is a record of the interactions of waves with the layers of rocks and materials in the subsurface. In geophysics, we study these interactions to generate an image of the subsurface for hydrocarbon exploration, geohazard mitigation, mineral exploration, etc.

In this competition, you will be using seismic data acquired off the coast of Australia. Your goal is to use the datasets to predict rock properties across the entire seismic volume based on the ground truth data available in the well logs.

AWS Cloud Resources

SageMaker tutorial

This competition will require that all final solutions be run in the cloud. Here is a quick training resource on how to train and deploy models using AWS SageMaker. This tutorial will likely go beyond the needs of the competition.

"In this tutorial, you learn how to use Amazon SageMaker to build, train, and deploy a machine learning (ML) model using the XGBoost ML algorithm. Amazon SageMaker is a fully managed service that provides every developer and data scientist with the ability to build, train, and deploy machine learning (ML) models quickly."

Click here to see the tutorial.

SageMaker: Getting Started

Kyle from AWS explains how to get started with SageMaker in this video. He made it specifically for our competition! He is awesome.

SageMaker: Cloning a Git Repository

Kyle from AWS explains how to clone a git repo to a SageMaker instance in this video. He made it specifically for our competition! He is awesome.

SageMaker: Installing Modules

Kyle from AWS explains how to install dependencies using a requirements.txt file for a SageMaker instance in this video. He made this available for our competition! He is awesome.