With the recent enormous success of deep learning in speech, image, and natural language processing, people start to dream about an intelligent brain with the assist of a massive amount of computation power on large datasets. Nvidia, the hardware company behind all the rapid development of deep learning, put together an ad page demonstrate the successful stories of AI. More and more researchers/companies start to realize the value and deep learning and begin to explore its inspirational applications. However, the effect of applying deep learning related algorithms in seismic processing is somewhat scarce at this point.
In this post, I’d like to entertain the possible applications of deep learning in seismic processing with some introduction to exisiting trials. The basic seismic processing can be careless divided into roughly two areas:
In detection, we try to find and locate earthquake (seismic events) from the received signals on a seismic receiver sensor(s).