The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning

Abstract

The aim of this work is to predict suitable chemical compositions for the development of new ceramic oxygen gas separation membranes, avoiding doping with toxic cobalt or expensive rare earths. For this purpose, we have chosen the system Sr1−xBax(Ti1−y−zVyFez)O3−δ (cubic perovskite-type phases). We have evaluated available experimental data, determined missing crystallographic information using bond-valence modeling and programmed a Python code to be able to generate training data sets for property predictions using machine learning. Indeed, suitable compositions of cubic perovskite-type phases can be predicted in this way, allowing for larger electronic conductivities of up to σe = 1.6 S/cm and oxygen conductivities of up to σi = 0.008 S/cm at T = 1173 K and an oxygen partial pressure pO2 = 10−15 bar, thus enabling practical applications.

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO3-δ Perovskites with High Oxide Ionic Conductivity

“…The incorporation of atomic properties as descriptors enhanced the predictive power of the model, enabling researchers to obtain reliable estimations of the oxide ionic conductivity for a wide range of perovskite compositions. Schlenz et al developed a Python program called Pecon.py by fitting and interpolating experimental data. The program enabled the calculation of the composition, temperature, and oxygen partial pressure for the cubic-phase perovskite system (Sr 1– x Ba x )­(Ti 1‑ y ‑ z V y Fe z )­O 3‑δ .…”

Machine Learning Design of Perovskite Catalytic Properties

“…[25][26][27][28][29] However, the prediction of perovskite catalytic properties with ML remains in the nascent stages, [30][31][32][33] with only a handful of papers using ML to predict properties like ASR and oxygen conductivity. [34][35][36][37] A schematic outline of the present work is shown in Figure 1. The O p-band center property correlations mentioned above can be considered a primitive ML model, where the model has a single feature, the O p-band center, and the model type is often a basic univariate linear regressor.…”

Deep learning based on small sample dataset: prediction of dielectric properties of SrTiO 3 -type perovskite with doping modification

“…Although there have been advances in algorithms and computing conditions, performing large-scale first-principles calculations is still very expensive. In the meantime, the abundance of accessible databases in materials science has made the use of data-driven machine learning (ML) methods possible, which are increasingly being used to bypass these calculations [16,17]. Examples of perovskite property prediction include band characteristics [18], optimal composition [19], dielectric performance [20], bandgap energy [21] and dielectric breakdown strength [22].…”