Home icon

Powering AI/ML with MDIO seismic streaming from the OSDU® Data Platform

Industries Blog



The article discusses a collaboration between TGS and AWS to improve seismic data management and AI/ML workflows using the Multi-Dimensional Input Output (MDIO) format within the OSDU Data Platform.

  • MDIO is an open-source data storage format that enables efficient computational workflows for high-dimensional energy datasets
  • Provides 41% storage cost reduction through Zstd compression and improved data access
  • Allows seamless integration with machine learning libraries like NumPy, TensorFlow, and PyTorch
  • Enables on-demand streaming and targeted data retrieval for seismic data
  • Supports AI/ML workflows such as denoising, deghosting, and salt body segmentation in seismic imaging

The solution leverages AWS services like Energy Data Insights (EDI) to provide efficient, centralized data management and enable advanced AI/ML applications in the oil and gas industry.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Aug 12
2024
Empowering collaboration with the OSDU Data Platform for reservoir modeling
May 14
2025
Maximizing seismic insights: how Petrobras uses S-Cube’s cloud native XWI solution built on AWS Graviton
Feb 19
2024
A light in the dark—illuminating dark data with the OSDU Data Platform
Apr 28
2026
Real-time data streaming for AI workloads with Confluent on AWS

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.