Εξειδίκευση τύπου :	Άρθρο σε επιστημονικό περιοδικό
Τίτλος:	A Robust Machine Learning Algorithm for the Prediction of Methane Adsorption in Nanoporous Materials
Δημιουργός/Συγγραφέας:	Fanourgakis G.S. Gkagkas K. Tylianakis E. [EL] Κλώντζας, Εμμανουήλ[EN] Klontzas, Emmanuel Froudakis G.
Εκδότης:	American Chemical Society
Ημερομηνία:	2019
Γλώσσα:	Αγγλικά
ISSN:	1089-5639
DOI:	10.1021/acs.jpca.9b03290
Άλλο:	PubMed ID: 31264869
Περίληψη:	In the present study, we propose a new set of descriptors that, along with a few structural features of nanoporous materials, can be used by machine learning algorithms for accurate predictions of the gas uptake capacities of these materials. All new descriptors closely resemble the helium atom void fraction of the material framework. However, instead of a helium atom, a particle with an appropriately defined van der Waals radius is used. The set of void fractions of a small number of these particles is found to be sufficient to characterize uniquely the structure of each material and to account for the most important topological features. We assess the accuracy of our approach by examining the predictions of the random forest algorithm in the relative small dataset of the computation-ready, experimental (CoRE) MOFs (4700 structures) that have been experimentally synthesized and whose geometrical/structural features have been accurately calculated before. We first performed grand canonical Monte Carlo simulations to accurately determine their methane uptake capacities at two different temperatures (280 and 298 K) and three different pressures (1, 5.8, and 65 bar). Despite the high chemical and structural diversity of the CoRE MOFs, it was found that the use of the proposed descriptors significantly improves the accuracy of the machine learning algorithm, particularly at low pressures, compared to the predictions made based solely on the rest structural features. More importantly, the algorithm can be easily adapted for other types of nanoporous materials beyond MOFs. Convergence of the predictions was reached even for small training set sizes compared to what was found in previous works using the hypothetical MOF database.
Τίτλος πηγής δημοσίευσης:	Journal of Physical Chemistry A
Τόμος/Κεφάλαιο:	123
Τεύχος:	28
Σελίδες:	6080-6087
Θεματική Κατηγορία:	[EL] Φυσική και θεωρητική χημεία[EN] Physical and theoretical chemistry
Αξιολόγηση από ομότιμους (peer reviewed):	Ναι
Κάτοχος πνευματικών δικαιωμάτων:	© 2019 American Chemical Society.
Σημειώσεις:	College of Environmental Science and Forestry, State University of New York, ESF; Seattle Science Foundation, SSF: 2016-050-0503-8189; European Commission, EC; State Scholarships Foundation, IKY; European Social Fund, ESF; Toyota Motor Europe, TME This work has been financially supported by Toyota Motor Europe NV/SA. E.K. has been funded by State Scholarships Foundation (SSF), grant number 2016-050-0503-8189, and cofinanced by the European Union (European Social Fund (ESF)) and Greek national funds through the action entitled “Reinforcement of Postdoctoral Researchers”, in the framework of the Operational Programme “Human Resources Development Program, Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF) 2014–2020.
Εμφανίζεται στις συλλογές:	Ινστιτούτο Θεωρητικής και Φυσικής Χημείας (ΙΘΦΧ) - Επιστημονικό έργο