Artificial Intelligence to solve the ‘zeolite conundrum’

MIT Energy Initiative awards seed fund grant to find novel catalysts.

The MIT Energy Initiative (MITEI) has awarded a grant to Rafael Gómez-Bombarelli, assistant professor at the Department of materials science and engineering, from its million dollar ‘seed fund’ program that supports early-stage innovative energy research at MIT through an annual competitive process.

The monies will be used to apply artificial intelligence to solve the ‘zeolite conundrum’ whereby, despite millions of possible molecular configurations of the nano frameworks, to date only 248 have been discovered. Zeolites are widely used in refining as molecular sieves and catalysts.

The ‘Automatic design of structure‐directing agents for novel realizable zeolites’ program will use machine learning and simulation to accelerate the discovery cycle of zeolites and ‘expedite progress toward a variety of innovative energy solutions’. Hitherto, discovery of these new frameworks has relied mostly on trial-and-error in the lab, a slow and labor-intensive approach. Gómez- Bombarelli will be using theory to speed up that process. ‘Using machine learning and first-principles simulations, we’ll design small molecules to dock on specific pores and direct the formation of targeted structures. The computational approach will drive new synthetic outcomes in zeolites faster’.

For more on zeolite, read Thomas Degnan’s 2000 paper Applications of zeolites in petroleum refining.

Click here to comment on this article

Click here to view this article in context on a desktop

© Oil IT Journal - all rights reserved.