To increase the efficiency of offshore windfarm site evaluation we developed a boulder prediction tool using a 2D convolutional neural network based on the U-net architecture. This method is coupled with a unique weighting scheme that the interpreter creates during interactive training. This unique weighting allows the model to learn from the interpreter where boulders should and should not be labeled, as well as identify noise in the data.

Keywords:
upstream oil & gas, reservoir characterization, boulder prediction, geologist, artificial intelligence, prediction, international, exploration geophysicist, boulder, geological subdiscipline
Subjects:
Reservoir Characterization, Information Management and Systems, Seismic processing and interpretation
This content is only available via PDF.
Copyright 2023, Society of Exploration Geophysicists and the American Association of Petroleum Geologists
You can access this article if you purchase or spend a download.