A team of scientists at Los Alamos National Laboratory is applying machine-learning algorithms to subsurface imaging that will impact a variety of applications, including energy exploration, carbon capture and sequestration and estimating pathways of subsurface contaminant transport, according to new research published in IEEE Signal Processing Magazine. "The subsurface is extremely complex and full of uncertainty, and knowledge of its physical properties is vital for a variety of applications," said Youzuo Lin of Los Alamos' Energy and Earth System Science group and lead author of the paper. "This paper is the first systematic survey on physics-guided machine-learning techniques for computational wave imaging." The authors reviewed more than a 100 research articles, organizing them within a structured framework that highlights the most significant recent innovations in this area. These insights will be of value not only for subsurface imaging, but also for other computational wave imaging problems such as medical ultrasound imaging and acoustic sensing for materials science. The process of obtaining subsurface data from surface measurements is called seismic inversion.

Oil company Total has almost tripled the performance of Pangea, a supercomputer it uses for analyzing subsurface imaging in search of new oilfields. Pangea's performance is now 6.7 petaflops (floating-point operations per second), up from 2.3 petaflops, the French company said Tuesday. That's enough to put it among the 10 fastest supercomputers in the world, according to Total, which based its claim on rankings published last November by Top500.org, the international supercomputer ranking organization. Total's claim is based on the assumption that no other computer has been similarly upgraded in the meantime, something we won't know for sure until the next edition of the list is published in June. But there's another wrinkle that might cast doubt on Total's top 10 status, and that's what exactly the 2.3 petaflop figure represents.