The scope of the current study is to create a gas adsorption characterization tool of porous materials using machine learning algorithms.
This approach is a promising alternative to the stochastic molecular simulations methods (Monte Carlo (MC)),
which takes time and resources.
The tasks consist of producing the data:
(a) finding the structures,
(b) running the MC simulations,
and applying a set of machine learning algorithms in order to predict the gas storage properties for a set of gases:
(i) choosing/creating the necessary features,
(ii) perform an exploratory analysis,
(iii) testing different algorithms,
(iv) train the model
Bibliography:
[1] G. S. Fanourgakis, K. Gkagkas, E. Tylianakis, E. Klontzas, and G. Froudakis, “A Robust Machine Learning Algorithm for the Prediction of Methane Adsorption in Nanoporous Materials,” J. Phys. Chem. A, vol. 123, no. 28, pp. 6080–6087, Jul. 2019.
[2] G. Borboudakis, T. Stergiannakos, M. Frysali, E. Klontzas, I. Tsamardinos, and G. E. Froudakis, “Chemically intuited, large-scale screening of MOFs by machine learning techniques,” npj Comput. Mater., vol. 3, no. 1, pp. 1–6, 2017.