Machine learning for the redox potential prediction of molecules in organic redox flow battery
Source abstract
Abstract
Organic redox flow batteries (ORFB) are recognized as an innovative technology for the large-scale storage of renewable energy. The redox potential of organic redox-active molecules plays a vital role in their performance. Advanced screening techniques like high-throughput experiment and machine learning (ML) have significantly enhanced organic material performance and transformed the field of ORFB. However, the scarcity of experimental data poses a considerable challenge for ML model development in this domain. In our study, we developed lightweight graph-based Gaussian process regression (GPR) models with GPU-accelerated marginalized graph kernel and hybrid kernel to predict the redox potentials of organic redox-active molecules for ORFBs, specifically focusing on small datasets. To evaluate model accuracy, we created a new experimental database of organic redox-active molecules by the data from hundreds of published papers and assembled previous computational datasets. We also considered some key parameters, such as pH conditions and solvent type, to assess their impact on redox potential prediction. Our GPR model predicted redox potentials with high accuracy across all datasets using minimal training data. The study provides powerful tools for molecule screening and design and delivers valuable guidance on designing training datasets for costly experiments.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Advanced battery technologies research · Fuel Cells and Related Materials · Electrochemical Analysis and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (65)
Show source-provided references
1. A comparative study of all-vanadium and iron-chromium redox flow batteries for large-scale energy storage10.1016/j.jpowsour.2015.09.100 ↗
2. Designing better flow batteries: an overview on fifty years' research10.1021/acsenergylett.4c00773 ↗
3. Iron-based flow batteries to store renewable energies10.1007/s10311-018-0709-8 ↗
4. Functional materials for aqueous redox flow batteries: merits and applications10.1039/D3CS00703K ↗
5. Advances in redox flow batteries - a comprehensive review on inorganic and organic electrolytes and engineering perspectives10.1002/aenm.202400721 ↗
6. Status and prospects of organic redox flow batteries toward sustainable energy storage10.1021/acsenergylett.9b01332 ↗
7. Reversible ketone hydrogenation and dehydrogenation for aqueous organic redox flow batteries10.1126/science.abd9795 ↗
8. Benchmarking organic active materials for aqueous redox flow batteries in terms of lifetime and cost10.1038/s41467-023-42450-9 ↗
9. Physics-informed CoKriging model of a redox flow battery10.1016/j.jpowsour.2022.231668 ↗
10. Physics-guided continual learning for predicting emerging aqueous organic redox flow battery material performance10.1021/acsenergylett.4c00493 ↗
11. Physics-informed machine learning of redox flow battery based on a two-dimensional unit cell model10.1016/j.jpowsour.2023.233548 ↗
12. Redox potential control by drug binding to cytochrome P450 3A410.1021/ja074864x ↗
13. Evaluation of homogeneous electrocatalysts by cyclic voltammetry10.1021/ic500658x ↗
14. Biogeochemical redox processes and their impact on contaminant dynamics10.1021/es9026248 ↗
15. Incremental tuning up of fluorous phenazine acceptors10.1002/chem.201504122 ↗
16. Molecular design of fused-ring phenazine derivatives for long-cycling alkaline redox flow batteries10.1021/acsenergylett.9b02676 ↗
17. High-throughput experimentation and computational freeway lanes for accelerated battery electrolyte and interface development research10.1002/aenm.202102678 ↗
18. DFT calculation, a practical tool to predict the electrochemical behaviour of organic electrolytes in aqueous redox flow batteries10.1016/j.jpowsour.2023.232817 ↗
19. Development of a multi-step screening procedure for redox active molecules in organic radical polymer anodes and as redox flow anolytes10.1002/jcc.27299 ↗
20. Large-scale virtual high-throughput screening for the identification of new battery electrolyte solvents: evaluation of electronic structure theory methods10.1039/C4CP00547C ↗
21. Benchmark study of electrochemical redox potentials calculated with semiempirical and DFT methods10.1021/acs.jpca.0c05052 ↗
22. RedDB, a computational database of electroactive molecules for aqueous redox flow batteries10.1038/s41597-022-01832-2 ↗
23. Predicting redox potentials by graph-based machine learning methods10.1002/jcc.27380 ↗
24. Density functional theory and machine learning for electrochemical square-scheme prediction: an application to quinone-type molecules relevant to redox flow batteries10.1039/D3DD00091E ↗
25. Universal solvation model based on solute electron density and on a continuum model of the solvent defined by the bulk dielectric constant and atomic surface tensions10.1021/jp810292n ↗
26. Fast and accurate calculation of hydration energies of molecules and ions10.1039/D0CP02667K ↗
27. G4 accuracy at DFT cost: unlocking accurate redox potentials for organic molecules using systematic error cancellation10.1039/C9CP06622E ↗
28. Aqueous transition-metal cations as impurities in a wide gap oxide: the Cu2+/Cu+ and Ag2+/Ag+ redox couples revisited10.1021/jp506691h ↗
29. Bridging the experiment-calculation divide: machine learning corrections to redox potential calculations in implicit and explicit solvent models10.1021/acs.jctc.1c01040 ↗
30. Prediction of redox power for photocatalysts: synergistic combination of DFT and machine learning10.1021/acs.jctc.3c00286 ↗
31. Machine learning-aided first-principles calculations of redox potentials10.1038/s41524-024-01295-6 ↗
32. Additivity rules for the estimation of molecular properties. Thermodynamic properties10.1063/1.1744539 ↗
33. Antioxidant properties of carotenoids:: QSAR prediction of their redox potentials
34. A mixed quantum chemistry/machine learning approach for the fast and accurate prediction of biochemical redox potentials and its large-scale application to 315 000 redox reactions10.1021/acscentsci.9b00297 ↗
35. Nesměrák · 2023 · 139
36. High-throughput screening of promising redox-active molecules with MolGAT10.1021/acsomega.3c01295 ↗
37. Attribute driven inverse materials design using deep learning Bayesian framework10.1038/s41524-019-0263-3 ↗
38. Material search for Li-ion battery electrolytes through an exhaustive search with a Gaussian process10.1016/j.cplett.2019.136622 ↗
39. Liquid electrolyte informatics using an exhaustive search with linear regression10.1039/C7CP08280K ↗
40. Integrated supervised and unsupervised machine learning approach to map the electrochemical windows over 4500 solvents for battery applications10.1021/acsami.4c06243 ↗
41. Machine learning for flow batteries: opportunities and challenges10.1039/D2SC00291D ↗
42. High-throughput electrochemical characterization of aqueous organic redox flow battery active material10.1149/1945-7111/acfcde ↗
43. An integrated high-throughput robotic platform and active learning approach for accelerated discovery of optimal electrolyte formulations10.1038/s41467-024-47070-5 ↗
44. High-throughput solubility determination for data-driven materials design and discovery in redox flow battery research
45. Designing strategies to tune reduction potential of organic molecules for sustainable high capacity battery application10.1039/C6TA09760J ↗
46. Molecular structure–redox potential relationship for organic electrode materials: density functional theory–Machine learning approach
47. Electrochemical and density functional theory modeled reduction of enolized 1,3-diketones10.1016/j.electacta.2011.03.083 ↗
48. Experimental and theoretical predictors for redox potentials of bispyridinylidene electron donors10.1002/cphc.202400092 ↗
49. Descriptors for electrolyte-renormalized oxidative stability of solvents in lithium-ion batteries10.1021/acs.jpclett.9b02717 ↗
50. The aprotic electrochemistry of quinones10.1016/j.bbabio.2022.148558 ↗
51. A biomimetic high-capacity phenazine-based anolyte for aqueous organic redox flow batteries10.1038/s41560-018-0167-3 ↗
52. New insights into phenazine-based organic redox flow batteries by using high-throughput DFT modelling10.1039/D0SE00687D ↗
53. Machine learning properties of electrolyte additives: a focus on redox potentials10.1021/acs.iecr.0c05055 ↗
54. Ab initio calculations of the redox potentials of additives for lithium-ion batteries and their prediction through machine learning10.1021/acsomega.8b00576 ↗
55. Predicting the redox potentials of phenazine derivatives using DFT-assisted machine learning10.1021/acsomega.1c06856 ↗
56. UMAP: Uniform Manifold approximation and projection10.21105/joss.00861 ↗
57. Computational design of molecules for an all-quinone redox flow battery10.1039/C4SC03030C ↗
58. Graphical Gaussian process regression model for aqueous solvation free energy prediction of organic molecules in redox flow batteries10.1039/D1CP04475C ↗
59. Prediction of atomization energy using graph kernel and active learning10.1063/1.5078640 ↗
60. Tang, Y. H., Selvitopi, O., Popovici, D. T. & Buluç, A. in 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 728-738..10.1109/IPDPS47924.2020.00080 ↗
61. The ORCA quantum chemistry program package10.1063/5.0004608 ↗
62. A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu10.1063/1.3382344 ↗
63. Quantum calculation of molecular energies and energy gradients in solution by a conductor solvent model10.1021/jp9716997 ↗
64. Extended tight-binding quantum chemistry methods
65. Robust and efficient implicit solvation model for fast semiempirical methods10.1021/acs.jctc.1c00471 ↗