Deep Learning in Geoscience Applications

Wednesday, March 10, 2021

11:00 am - 12:00 pm

About the Event

Applications of deep learning techniques in image analysis have recently increased in the domain of geoscience and seismic imaging. During this talk, Devarakota will present the concept of learning multiple related tasks and demonstrate on a use case that the multi-task learning (MTL) fashions common representations of related tasks (salt body and salt boundaries), and improves the accuracy of identifying and segmenting salt boundary structures. In the second example, he will reconstruct the regularly and irregularly missing in narrow-azimuth (NAZ) data using an encoder-decoder style convolutional neural network.

About the Speaker

Pandu Devarakota acts as team lead for subsurface and wells at Shell Global Solutions USA. Devarakota and his team are developing a range of technologies from machine learning to deep learning which focus on making advancements in AI adoption under Shell’s artificial intelligence (Shell.ai) initiative. He is currently acting as a chair for the data standards subcommittee in the SEG SEAM AI project.

REGISTER