Accelerating the discovery of battery electrode materials through data mining and deep learning models
Source abstract
Abstract
The availability of crystalline materials databases allows for building accurate machine learning (ML) models that can accelerate the exploration of materials chemical space for energy storage applications. In this work, we screen all inorganic materials included in the Materials Project and AFLOW databases as potential metal-ion battery electrodes. We develop an efficient protocol to mine and screen raw data in current databases and provide a new database of electrode materials by considering pairs of charged and discharged electrodes. This effort leads to a new database with over 190,000 instances, in contrast to the original battery database which contains about 5000. The expanded battery data set is then used to build regression-based deep neural network models for predicting average voltages and percentage volume changes upon charging and discharging, which present improvements of at least 28% for target properties with respect to previous models, and are now able to predict anode electrodes (low voltage region) as well as electrodes that will not work in electrochemical cells (negative voltages), overcoming the challenges identified in previous ML models for battery electrodes. Additionally, a further screening of the expanded database itself allowed us to identify 35 novel electrode candidates with excellent battery performance metrics.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Machine Learning in Materials Science · Fuel Cells and Related Materials · Advancements in Battery Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Advanced materials for energy storage10.1002/adma.200903328 ↗
2. Nature-inspired electrochemical energy-storage materials and devices10.1002/aenm.201601709 ↗
3. Energy storage technologies and real life applications–A state of the art review10.1016/j.apenergy.2016.06.097 ↗
4. A review of energy storage technologies for wind power applications10.1016/j.rser.2012.01.029 ↗
5. A review of energy storage types, applications and recent developments10.1016/j.est.2019.101047 ↗
6. The introduction of structure types into the inorganic crystal structure database ICSD10.1107/S0108767307038081 ↗
7. Commentary: The materials project: A materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
8. First-principles prediction of redox potentials in transition-metal compounds with LDA+U10.1103/PhysRevB.70.235121 ↗
9. AFLOW: An automatic framework for high-throughput materials discovery10.1016/j.commatsci.2012.02.005 ↗
10. Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD)10.1007/s11837-013-0755-4 ↗
11. The NOMAD laboratory: from data sharing to artificial intelligence10.1088/2515-7639/ab13bb ↗
12. Machine learning screening of metal-ion battery electrode materials10.1021/acsami.1c04627 ↗
13. Machine learning the voltage of electrode materials in metal-ion batteries10.1021/acsami.9b04933 ↗
14. An accurate machine learning calculator for the lithium-graphite system10.1088/2515-7655/abc96f ↗
15. M. Kim, S. Kang, H.G. Park, K. Park, K. Min, Maximizing the energy density and stability of Ni-Rich layered cathode materials with multivalent dopants via machine learning. Available at SSRN 4117000.
16. Accurate prediction of voltage of battery electrode materials using attention-based graph neural networks10.1021/acsami.2c00029 ↗
17. Machine learning: accelerating materials development for energy storage and conversion10.1002/inf2.12094 ↗
18. Searching for hidden perovskite materials for photovoltaic systems by combining data science and first principle calculations10.1021/acsphotonics.7b01479 ↗
19. Machine learning bandgaps of double perovskites10.1038/srep19375 ↗
20. Machine learning in catalysis10.1038/s41929-018-0056-y ↗
21. Machine learning for heterogeneous catalyst design and discovery10.1002/aic.16198 ↗
22. Liquid electrolyte informatics using an exhaustive search with linear regression10.1039/C7CP08280K ↗
23. Ab initio calculations of the redox potentials of additives for lithium-ion batteries and their prediction through machine learning10.1021/acsomega.8b00576 ↗
24. An efficient rule-based screening approach for discovering fast lithium ion conductors using density functional theory and artificial neural networks10.1039/C3TA13235H ↗
25. Accelerated materials design of lithium superionic conductors based on first-principles calculations and machine learning algorithms10.1002/aenm.201300060 ↗
26. Materials space of solid-state electrolytes: Unraveling chemical composition–structure–ionic conductivity relationships in garnet-type metal oxides using cheminformatics virtual screening approaches10.1039/C7CP00518K ↗
27. Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data10.1063/1.5093220 ↗
28. Holistic computational structure screening of more than 12000 candidates for solid lithium-ion conductor materials10.1039/C6EE02697D ↗
29. A critical review of machine learning of energy materials10.1002/aenm.201903242 ↗
30. AFLUX: The LUX materials search API for the AFLOW data repositories10.1016/j.commatsci.2017.04.036 ↗
31. The materials application programming interface (API): A simple, flexible and efficient API for materials data based on representational state transfer (REST) principles10.1016/j.commatsci.2014.10.037 ↗
32. Python materials genomics (pymatgen): A robust, open-source python library for materials analysis10.1016/j.commatsci.2012.10.028 ↗
33. Ab initio study of lithium intercalation in metal oxides and metal dichalcogenides10.1103/PhysRevB.56.1354 ↗
34. Density functional theory for battery materials10.1002/eem2.12056 ↗
35. Chollet · 2015
36. Gulli · 2017
37. Matminer: An open source toolkit for materials data mining10.1016/j.commatsci.2018.05.018 ↗
38. Random forests10.1023/A:1010933404324 ↗
39. Principal component analysis: A review and recent developments10.1098/rsta.2015.0202 ↗
40. Generalization by weight-elimination with application to forecasting
41. Dropout: A simple way to prevent neural networks from overfitting
42. Building a better battery10.1126/science.1198591 ↗
43. An outlook on low-volume-change lithium metal anodes for long-life batteries10.1021/acscentsci.0c00351 ↗
44. Recent progress in research on high-voltage electrolytes for lithium-ion batteries10.1002/cphc.201402175 ↗