Regression model for stabilization energies associated with anion ordering in perovskite-type oxynitrides

Significance 

Perovskite-type materials exhibit varying physical properties owing to their variety of composition thus explaining their potential applications related to solar energy conversion. Specifically, oxynitrides having narrower bandgaps have been widely studied. Their physical properties depend on the structural ordering of anions. However, they involve numerous possible anion orderings that makes it difficult to use quantum chemistry calculation method to predict their physical properties due to high optimization cost involved. Machine learning, suitable for predicting realistic physical properties for randomly selected structures, was recently proposed to reduce the high cost. This technique has been, therefore, extended to predict the thermodynamic phase stability of perovskite-type oxides and bandgap energies.

Dr. Masanori Kaneko, Dr. Mikiya Fujii, Professor Koichi Yamashita and Dr. Kazunari Domen from the University of Tokyo together with Dr. Takashi Hisatomi from Shinshu University explored the use of machine learning based on density functional theory calculations involving small supercells to predict stable anion ordering of perovskite-type oxynitrides. A model for predicting the total energy was generated through machine learning while the Metropolis method was used to predict stable anion ordering. The supercells structure obtained through the Metropolis method was validated by comparing to density functional theory calculations results. The work is published in Journal of Energy Chemistry.

Just like cluster expansion methods, machine learning can handle large systems. Additionally, it can effectively take into consideration the long-range effects in any crystal structure regardless of the symmetry in question. Therefore, it was possible to correctly predict anion ordering in large-scale supercells within perovskite-type oxynitrides. Consequently, the total energy of perovskite-type oxynitrides was directly determined from randomly selected initial atomic placements at less structural optimization cost. For instance, machine learning significantly reduced the computation cost by more than 99.99% thus more economically viable.

A regression model based on density functional theory calculations was successfully established by machine learning. The accuracy of the total energy prediction was observed to be influenced by the explanatory variables reflecting the local anion ordering and associated with long-range interactions and chemical bonds. Ridge regression produced the most accurate model for the reproduction of the local anion ordering with well-coordinated stable supercells. With optimized anion ordering, it was possible to rapidly obtain stable anion orders through a combination of this predictive model and Metropolis method without the need for most stable supercell input.

Among the supercells used for machine learning, those predicted by the Metropolis method followed by predictive exhibited superior stability with total energy close to that calculated by density functional theory. The results indicated that the developed predictive model enhanced the accuracy of exploring stable anion ordering. This approach could also be extended in predicting electronic properties such as the bandgap energy.

In summary, the study demonstrated a method for predicting the properties of functional materials with complex compositions based on machine learning at reasonable computational costs. Considering that the approach is based on the most realistic elemental arrangements together with reasonable computational loads, Dr. Kaneko the first author told Advances in Engineering that their study will advance stabilization of energies associated with anion ordering in perovskite-type oxynitrides.

Regression model for stabilization energies associated with anion ordering in perovskite-type oxynitrides - Advances in Engineering

About the author

Koichi Yamashita, Emeritus professor of the University of Tokyo, received his PhD from Kyoto University in 1982 supervised by Prof. Kenichi Fukui. He was postdoctoral fellow with Prof. William H. Miller at the University of California, Berkeley for 1982-84. He moved to Okazaki in 1984 to join the group of Prof. Keiji Morokuma as Research Associate at Division of Theoretical Study of Institute of Molecular Science. In 1991 he became Senior Researcher at Institute of Fundamental Chemistry directed by Prof. Kenichi Fukui. In 1994 he moved to Tokyo to join the group of Prof. Kimihiko Hirao as Associate Professor in Department of Applied Chemistry at University of Tokyo. He became Full Professor at the University of Tokyo, Department of Chemical System Engineering, in 1997 and retired in 2018. In 2019 he was appointed as Specially-appointedProfessor of Kyoto University and Visiting Professor of Tokyo Metropolitan University.

His research interests include ab initiomethods, quantum reaction dynamics, nonadiabatic processes in condensed phases and modeling of energy conversion processes, such as artificial photosynthesis and photovoltaics.

About the author

Masanori Kaneko is a postdoctoral researcher of ESICB (Elements Strategy Initiative for Catalysts and Batteries Interplay between Experimental and Theoretical Studies), Kyoto University.

In 2010, he entered the Department of Physics, Faculty of Science and Technology, Tokyo University of Science, to study quantum mechanics and theory of relativity.

At that time he started focusing on the properties of various materials by means of these theories.

After he graduated in 2014, he entered the Department of Chemical System Engineering, Graduate School of Engineering, The University of Tokyo, under the supervision of Prof. Koichi Yamashita, in order to investigate photocatalyst mediated water splitting processes.

Still to study the same topic, in 2018, he moved to the laboratory of Prof. Kazunari Domen in the same department and received his Ph.D. in 2019.

He has been in the Prof. Koichi Yamashita group of Kyoto University ESICB since 2019.

Nowadays, his research interests are solar-to-energy conversion processes (e.g. photocatalytic water splitting) studied by means of first-principles calculations based on Density Functional Theory and machine learning.

Reference

Kaneko, M., Fujii, M., Hisatomi, T., Yamashita, K., & Domen, K. (2019). Regression model for stabilization energies associated with anion ordering in perovskite-type oxynitrides. Journal of Energy Chemistry, 36, 7-14.

Go To Journal of Energy Chemistry

Check Also

Recovery of micronutrients and heavy metals from digestate - Advances in Engineering

Recovery of micronutrients and heavy metals from digestate