Towards the Prediction of Electrochromic Properties of WO3 Films: Combination of Experimental and Machine Learning Approaches

Brandon Faceira (1) , Lionel Teule-Gay (1) , Gian-Marco Rignanese (2) , Aline Rougier

1 ICMCB - Institut de Chimie de la Matière Condensée de Bordeaux
2 IMCN - Institut de la matière condensée et des nanosciences / Institute of Condensed Matter and Nanosciences

WO3 is the state of the art of electrochromic oxide materials finding technological application in smart windows. In this work, a set of WO3 thin films were deposited by magnetron sputtering by varying total pressure, oxygen partial pressure and power. On each film two properties were measured, the electrochemical reversibility and the blue colour persistence of LixWO3 films in simulated ambient conditions. With the help of machine learning, prediction maps for such electrochromic properties namely colour persistence and reversibility were designed. High performance WO3 films were targeted by a global score which is the product of these two properties. The combined approach of experimental measurements and machine learning led to a complete picture of electrochromic properties depending of sputtering parameters providing an efficient tool in regards to time saving.

Domaines: Matériaux

Brandon Faceira, Lionel Teule-Gay, Gian-Marco Rignanese, Aline Rougier. Towards the Prediction of Electrochromic Properties of WO3 Films: Combination of Experimental and Machine Learning Approaches. Journal of Physical Chemistry Letters, 2022, 13 (34), pp.8111-8115. ⟨10.1021/acs.jpclett.2c02248⟩. ⟨hal-03763753⟩