Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes
High-throughput approaches in computational materials discovery often yield a combinatorial explosion that makes the exhaustive rendering of complete structural and chemical spaces impractical. A common bottleneck when screening new compounds with archetypal crystal structures is the lack of fast an...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-08-01
|
| Series: | Energy and AI |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546822000180 |
| _version_ | 1811216001705967616 |
|---|---|
| author | A. Gallo-Bueno M. Reynaud M. Casas-Cabanas J. Carrasco |
| author_facet | A. Gallo-Bueno M. Reynaud M. Casas-Cabanas J. Carrasco |
| author_sort | A. Gallo-Bueno |
| collection | DOAJ |
| description | High-throughput approaches in computational materials discovery often yield a combinatorial explosion that makes the exhaustive rendering of complete structural and chemical spaces impractical. A common bottleneck when screening new compounds with archetypal crystal structures is the lack of fast and reliable decision-making schemes to quantitatively classify the computed candidates as inliers or outliers (too distorted structures). Machine learning-aided workflows can solve this problem and make geometrical optimization procedures more efficient. However, for this to occur, there is still a lack of appropriate combinations of suitable 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 compositional screening of cubic Li-argyrodites solid electrolytes, we tackle this problem head on. We find that Steinhardt order parameters are very accurate descriptors of the cubic argyrodite structure to train a range of common unsupervised outlier detection models. And, most importantly, the approach enables us to automatically classify crystal structures with uncertainty control. The resulting models can then be used to screen computed structures with respect to an user-defined error threshold and discard too distorted structures during geometrical optimization 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 use of computational and data storage resources more efficient. |
| first_indexed | 2024-04-12T06:32:22Z |
| format | Article |
| id | doaj.art-69e0e59ecb794a31b5f9ae6af571ebc0 |
| institution | Directory Open Access Journal |
| issn | 2666-5468 |
| language | English |
| last_indexed | 2024-04-12T06:32:22Z |
| publishDate | 2022-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy and AI |
| spelling | doaj.art-69e0e59ecb794a31b5f9ae6af571ebc02022-12-22T03:43:59ZengElsevierEnergy and AI2666-54682022-08-019100159Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytesA. Gallo-Bueno0M. Reynaud1M. Casas-Cabanas2J. Carrasco3Center for Cooperative Research on Alternative Energies (CIC energiGUNE), Basque Research and Technology Alliance (BRTA), Álava Technology Park, Albert Einstein 48, 01510 Vitoria-Gasteiz, SpainCenter for Cooperative Research on Alternative Energies (CIC energiGUNE), Basque Research and Technology Alliance (BRTA), Álava Technology Park, Albert Einstein 48, 01510 Vitoria-Gasteiz, SpainCenter for Cooperative Research on Alternative Energies (CIC energiGUNE), Basque Research and Technology Alliance (BRTA), Álava Technology Park, Albert Einstein 48, 01510 Vitoria-Gasteiz, Spain; IKERBASQUE, Basque Foundation for Science, María Díaz de Haro 3, 48013, Bilbao, SpainCenter for Cooperative Research on Alternative Energies (CIC energiGUNE), Basque Research and Technology Alliance (BRTA), Álava Technology Park, Albert Einstein 48, 01510 Vitoria-Gasteiz, Spain; Corresponding author.High-throughput approaches in computational materials discovery often yield a combinatorial explosion that makes the exhaustive rendering of complete structural and chemical spaces impractical. A common bottleneck when screening new compounds with archetypal crystal structures is the lack of fast and reliable decision-making schemes to quantitatively classify the computed candidates as inliers or outliers (too distorted structures). Machine learning-aided workflows can solve this problem and make geometrical optimization procedures more efficient. However, for this to occur, there is still a lack of appropriate combinations of suitable 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 compositional screening of cubic Li-argyrodites solid electrolytes, we tackle this problem head on. We find that Steinhardt order parameters are very accurate descriptors of the cubic argyrodite structure to train a range of common unsupervised outlier detection models. And, most importantly, the approach enables us to automatically classify crystal structures with uncertainty control. The resulting models can then be used to screen computed structures with respect to an user-defined error threshold and discard too distorted structures during geometrical optimization 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 use of computational and data storage resources more efficient.http://www.sciencedirect.com/science/article/pii/S2666546822000180Unsupervised outlier detectionMachine learningStructural distortionSolid-state batteryBattery designCrystal structure |
| spellingShingle | A. Gallo-Bueno M. Reynaud M. Casas-Cabanas J. Carrasco Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes Energy and AI Unsupervised outlier detection Machine learning Structural distortion Solid-state battery Battery design Crystal structure |
| title | Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes |
| title_full | Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes |
| title_fullStr | Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes |
| title_full_unstemmed | Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes |
| title_short | Unsupervised machine learning to classify crystal structures according to their structural distortion: A case study on Li-argyrodite solid-state electrolytes |
| title_sort | unsupervised machine learning to classify crystal structures according to their structural distortion a case study on li argyrodite solid state electrolytes |
| topic | Unsupervised outlier detection Machine learning Structural distortion Solid-state battery Battery design Crystal structure |
| url | http://www.sciencedirect.com/science/article/pii/S2666546822000180 |
| work_keys_str_mv | AT agallobueno unsupervisedmachinelearningtoclassifycrystalstructuresaccordingtotheirstructuraldistortionacasestudyonliargyroditesolidstateelectrolytes AT mreynaud unsupervisedmachinelearningtoclassifycrystalstructuresaccordingtotheirstructuraldistortionacasestudyonliargyroditesolidstateelectrolytes AT mcasascabanas unsupervisedmachinelearningtoclassifycrystalstructuresaccordingtotheirstructuraldistortionacasestudyonliargyroditesolidstateelectrolytes AT jcarrasco unsupervisedmachinelearningtoclassifycrystalstructuresaccordingtotheirstructuraldistortionacasestudyonliargyroditesolidstateelectrolytes |