Blog

From 10th August to 16th October 2020 FORCE with help from AGILE will arrange a globally open machine learning contest. They want to find the team that is best at predicting lithology and the stratigraphy in wells in the North Sea. A curated public dataset is being prepared by them and will also be downloadable on TerraNubis in OpendTect format from August 10th.

TerraNubis is a commercial marketplace for value-added seismic products. The competition dataset will be free to download and to use in OpendTect. dGB Earth Sciences supports the FORCE competition by supplying you with the new machine learning system in OpendTect. You will be able to use all free and proprietary plugins on the competition data sets, which are also pre-loaded in a downloadable survey for instant use in OpendTect.

Getting started

• Watch the Machine Learning Webinar series of dGB Earth Sciences. It will show the steps needed to make and train your own models and goes over some of the basics and theory.
• Develop your own models documentation
• Machine Learning Workflow: Wells Log-Log Prediction (Density)
• Machine Learning Workflow: Wells Log-Log Prediction (Porosity)
• Machine Learning Workflow: Wells Lithology Classification
• Machine Learning Workflow: Seismic bodies (Supervised 3D)
• Machine Learning Workflow: Seismic Unet 3D Fault Predictor
• Machine Learning Workflow: 3D Seismic + Wells Rock Property Prediction
• Machine Learning Workflow: Seismic Image to Image Faults Prediction

Also, be sure to join us on a weekly online Q&A that will start in the week after the start of the competition. Our team will answer questions about software usage and about developing new deep learning models in the Python / Keras part of the environment.