American Chemical Society
Browse
jz501331m_si_001.pdf (1.03 MB)

Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO2 Capture

Download (1.03 MB)
journal contribution
posted on 2015-12-17, 04:03 authored by Michael Fernandez, Peter G. Boyd, Thomas D. Daff, Mohammad Zein Aghaji, Tom K. Woo
In this work, we have developed quantitative structure–property relationship (QSPR) models using advanced machine learning algorithms that can rapidly and accurately recognize high-performing metal organic framework (MOF) materials for CO2 capture. More specifically, QSPR classifiers have been developed that can, in a fraction of a section, identify candidate MOFs with enhanced CO2 adsorption capacity (>1 mmol/g at 0.15 bar and >4 mmol/g at 1 bar). The models were tested on a large set of 292 050 MOFs that were not part of the training set. The QSPR classifier could recover 945 of the top 1000 MOFs in the test set while flagging only 10% of the whole library for compute intensive screening. Thus, using the machine learning classifiers as part of a high-throughput screening protocol would result in an order of magnitude reduction in compute time and allow intractably large structure libraries and search spaces to be screened.

History