Full text loading...
-
Crowdsourcing Salt Model Building: Kaggle-TGS Salt Identification Challenge
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 81st EAGE Conference and Exhibition 2019, Jun 2019, Volume 2019, p.1 - 5
Abstract
Can a data scientist without domain knowledge build a machine learning algorithm to identify salt? Can a deep learning network identify salt by training purely on images without any knowledge in geology? There are the fundamental questions at the core of of the Kaggle-TGS Salt Identification Challenge. These are the fundamental questions at the core of the Kaggle-TGS Salt Identification Challenge. In this study, we present an overview of our approach towards constructing the dataset and some results from the Gulf of Mexico showing the performance of salt segmentation algorithms that help us generate useful prior models for seismic interpreters. We also show the comparison of top results from Kaggle competition for TGS Salt Identification Challenge.