For several years, Oil & Gas industry, just like many others, is trying its hardest to implement machine learning into its workflows. If done right, deep learning can enhance accuracy and simultaneously speed up the entire pipeline of oil production, from the very early stages of exploration to drilling.
But, needless to say, researchers must carefully inspect hundreds of architectures and training approaches before the deployment of neural networks into the daily work of seismic specialists. This calls for quick model prototyping, which in turn needs the ability to rapidly generate data.
Unfortunately, core formats for storing volumetric seismic information…
This is the second part of a cycle, where we continue to demonstrate our horizon detection workflow. Crucial concepts of the task, its history, and importance for seismic exploration, as well as its quality assessment, are covered in the previous part of the publication; it is highly recommended to read it before proceeding. This time, we will look at:
- data generation in seismic exploration tasks
- neural network architectures
- techniques to enhance detected surfaces
- infrastructure for model deployment
Once more, let’s dig in!
Data generation
Seismic volumes are generated by sending a (usually acoustic) signal into the ground and registering its response: this…
In recent years, machine learning and specifically deep learning has captured the attention of all industries, and Oil & Gas is no exception. Obviously, the end goal of petroleum companies is to extract oil; yet, one must first find prominent locations inside the Earth to do so.
That is where seismic exploration comes in: it is the study of subterranean formations to help us locate structures underneath. There are a lot of stages of seismic exploration, from processing the raw acoustic signal traces into a regular fixed-grid volume to detecting subterranean facies inside of it. …
Sergey Tsimfer
Sergey Tsimfer is a Data Analyst at Gazprom-Neft who works on seismic tasks, including reservoir modelling and horizon detection via deep learning approaches.
