How AI could help discover places to store captured CO2

Scientists estimate that up to 90pc of the carbon emissions from industrial use of fossil fuels could be captured in this way, although the practice requires a continued supply of suitable locations to store the captured carbon. The researchers from MIT caution that their algorithm is only as effective as the data which it has been fed. They plan to give it even more data in the future to train it to better analyse seismic waves. Laurent Demanet, a professor of applied mathematics and one of the authors of the paper, told MIT News: "Using this neural network will help us find the missing frequencies to ultimately improve the subsurface image and find the composition of the Earth." MIT's research was funded by petroleum refining business Total SA and the US Air Force.