Crossline slices
Inline slices
SOLUTION APPROACH
SoftServe’s experts used state-of-the-art segmentation architectures like U-Net and FPN to automate geophysical data interpretation
The model takes 3D Seismic as input and after processing returns interpreted Seismic volume.
Pre-interpretation, 3D Seismic is split into 2D slices. This approach allows us to efficiently train networks with low amounts of 3D data via transfer learning.
BUSINESS VALUE
SEISMIC
DATA
INTERPRETATION
Deep learning technologies for geophysical data interpretation enable large volumes of data analysis and understanding of the relationship between various geological data types simultaneously.
REDUCING
MANUAL
OPERATION
The conservative workflow of seismic data interpretation requires manual work which is time-consuming and human-intensive. The model can supplement geoscientists in seismic interpretation to help interpret large amounts of data significantly faster, reducing pitfalls and dependencies on experience and bias.
ENHANCING
EXPLORATION
AND PRODUCTION
Faster processing and higher precision during seismic data interpretation accelerates future exploration decision making and empowers more accurate basin models to predict future production and field profitability.
WANT TO KNOW MORE?
Thank you
for your request!
We appreciate you contacting us. We have sent you an email from hello@connect.softserveinc.com
Have a great day ahead!
Read recently published White Paper
Contact Us
