High-throughput approaches in computational materials discovery often yield a combinatorial explosionthat makes the exhaustive rendering of complete structural and chemical spaces impractical. A commonbottleneck when ...High-throughput approaches in computational materials discovery often yield a combinatorial explosionthat makes the exhaustive rendering of complete structural and chemical spaces impractical. A commonbottleneck when screening new compounds with archetypal crystal structures is the lack of fast and reliabledecision-making schemes to quantitatively classify the computed candidates as inliers or outliers (too distortedstructures). Machine learning-aided workflows can solve this problem and make geometrical optimizationprocedures more efficient. However, for this to occur, there is still a lack of appropriate combinations ofsuitable geometrical descriptors and accurate unsupervised models which are capable of accurately differentiating between systems with subtle structural changes. Here, considering as a case study the compositionalscreening of cubic Li-argyrodites solid electrolytes, we tackle this problem head on. We find that Steinhardtorder parameters are very accurate descriptors of the cubic argyrodite structure to train a range of commonunsupervised outlier detection models. And, most importantly, the approach enables us to automatically classifycrystal structures with uncertainty control. The resulting models can then be used to screen computed structureswith respect to an user-defined error threshold and discard too distorted structures during geometricaloptimization procedures. Implemented as a decision node in computer-aided materials discovery workflows,this approach can be employed to perform autonomous high-throughput screening methods and make the useof computational and data storage resources more efficient.展开更多
基金supported by Umicore and is part of R&D&I project PID2019-106519RB-I00 funded by MCIN/AEI,Spain/10.13039/501100011033.
文摘High-throughput approaches in computational materials discovery often yield a combinatorial explosionthat makes the exhaustive rendering of complete structural and chemical spaces impractical. A commonbottleneck when screening new compounds with archetypal crystal structures is the lack of fast and reliabledecision-making schemes to quantitatively classify the computed candidates as inliers or outliers (too distortedstructures). Machine learning-aided workflows can solve this problem and make geometrical optimizationprocedures more efficient. However, for this to occur, there is still a lack of appropriate combinations ofsuitable geometrical descriptors and accurate unsupervised models which are capable of accurately differentiating between systems with subtle structural changes. Here, considering as a case study the compositionalscreening of cubic Li-argyrodites solid electrolytes, we tackle this problem head on. We find that Steinhardtorder parameters are very accurate descriptors of the cubic argyrodite structure to train a range of commonunsupervised outlier detection models. And, most importantly, the approach enables us to automatically classifycrystal structures with uncertainty control. The resulting models can then be used to screen computed structureswith respect to an user-defined error threshold and discard too distorted structures during geometricaloptimization procedures. Implemented as a decision node in computer-aided materials discovery workflows,this approach can be employed to perform autonomous high-throughput screening methods and make the useof computational and data storage resources more efficient.
