Artificial Intelligence: How AI Could Help Find Underground Silos To Store CO2
Technology may soon recover CO2 from the atmosphere. The problem is where to store it.
Mankind’s emission-generating activities have loaded the atmosphere with carbon dioxide (CO2), thus triggering climate changes. However, promising technology that recovers the CO2 from the atmosphere is under development. This CO2 may either be resold or converted into blocks that can be used for construction. These blocks may also be stored permanently underground. The problem is to locate the ‘silos’ or natural structures below the surface where the carbon blocks can be parked. AI may help locate these structures from earthquake data. (engadget)
Low-frequency seismic waves the key
Scientists have long known that low-frequency seismic waves generated during earthquakes can pinpoint sub-surface structures. Unfortunately, it is difficult to capture these waves because of interference from the Earth’s natural seismic ‘hum.’
However, MIT researchers may have found a solution to this problem using machine learning and AI algorithms.
Training AI to simulate low-frequency seismic waves
Researchers Laurent Demanet, professor of applied mathematics at MIT, and Hongyu Sun, a graduate student in MIT’s Department of Earth, Atmospheric and Planetary Sciences, have authored a paper on the subject.
Appearing in the journal Geophysics, the paper details how the researchers trained a neural network on hundreds of different simulated earthquakes. They then presented the model with both high- and low-frequency waves data on these earthquakes.
The researchers then tested the now-trained algo on a simulated earthquake, feeding it with only high-frequency waves data. They found that the algo could mimic the physics of wave propagation and simulate the missing low-frequency waves.
“The ultimate dream is to be able to map the whole subsurface, and be able to say, for instance, ‘this is exactly what it looks like underneath Iceland, so now you know where to explore for geothermal sources,’” said co-author Demanet. “Now we’ve shown that deep learning offers a solution to be able to fill in these missing frequencies.”
Though the technology is promising, its success depends upon the quality of the earthquake data that trained the algo data in the first place. As they say, “garbage in, garbage out,” or GIGO.
The researchers, therefore, plan to increase the scope of the input data by including earthquakes of varying intensities and subterranean surfaces of different kinds.
Latest Alternative Investment News
Flowcarbon, co-founded by Adam Neumann, known for WeWork, is a climate technology company seeking to formalize the market for carbon offsets on the blockchain. The startup announced Tuesday its $70…
One hapless investor lost about 3 billion won ($2.4 million) in the LUNA and UST implosion earlier this month. A Korean social media personality going by the name of “Chancers”…
Scientists have long held the view that earthquakes are impossible to predict, being random events. But the potential for damage these natural events have, including the loss of life, have…
Digital Assets: Swiss Venture Firm CV VC Launches African Blockchain Early-Stage Fund; Issues African Blockchain Report
CV VC announced Monday at Davos the launch of its African Blockchain Early-Stage Fund to bring the advantages of the blockchain and its own expertise to enable Africa to transact…