Adaptive learning-driven high-throughput synthesis of oxygen reduction reaction Fe–N–C electrocatalysts
Source abstract
Abstract
Reducing human reliance on inefficient energy systems and fossil fuels has become more urgent due to the consequences of global climate change . However, traditional trial-and-error approaches have hampered our ability to accelerate the discovery and implementation of functional materials for efficient energy conversion devices, such as polymer electrolyte fuel cells (PEFCs). To address this, we develop an adaptive learning framework that integrates machine learning and state-of-the-art capabilities in high-throughput synthesis to achieve expedited optimization of iron-nitrogen-carbon PEFC oxygen reduction reaction (ORR) electrocatalysts. We use statistical inference, uncertainty quantification, and global optimization to build a computational design-of-experiment tool that identifies the optimum compositions to be investigated next to reduce the demands placed on experimental materials discovery. We benchmark the ability of the proposed strategy to discover optimum catalyst synthesis conditions in a six-dimensional search space when starting with a thirty-six-sample database. By following the adaptive learning strategy, we synthesize fourteen new catalysts from approximately ten billion unique compositions and discover four catalysts that outperform all original samples. The best machine learning-optimized catalyst is 33% more active than the highest-performing one in the initial database, showing an ORR activity seven times larger than those typically reported for the same class of materials.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Machine Learning in Materials Science · Electrocatalysts for Energy Conversion · Fuel Cells and Related Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (72)
Show source-provided references
1. The role of hydrogen and fuel cells in the global energy system10.1039/C8EE01157E ↗
2. New roads and challenges for fuel cells in heavy-duty transportation10.1038/s41560-021-00775-z ↗
3. Advanced oxygen electrocatalysts in energy conversion and storage
4. Catalysts for fuel cell transportation and hydrogen related uses10.1038/s41929-019-0320-9 ↗
5. Platinum group metal-free catalysts boost cost competitiveness of fuel cell vehicles10.1038/s41929-019-0291-x ↗
6. New roads and challenges for fuel cells in heavy-duty transportation10.1038/s41560-021-00775-z ↗
7. Electrochemistry and the future of the automobile10.1021/jz100553m ↗
8. Iron-based catalysts with improved oxygen reduction activity in polymer electrolyte fuel cells10.1126/science.1170051 ↗
9. Identification of catalytic sites for oxygen reduction in iron- and nitrogen-doped graphene materials10.1038/nmat4367 ↗
10. Recent advances in electrocatalysts for oxygen reduction reaction10.1021/acs.chemrev.5b00462 ↗
11. Single atomic iron catalysts for oxygen reduction in acidic media: particle size control and thermal activation10.1021/jacs.7b06514 ↗
12. Single atom catalysts: synthetic strategies and electrochemical applications10.1016/j.joule.2018.06.019 ↗
13. Toward platinum group metal-free catalysts for hydrogen/air proton-exchange membrane fuel cells10.1595/205651318X696828 ↗
14. Fe−N−C electrocatalyst with dense active sites and efficient mass transport for high-performance proton exchange membrane fuel cells10.1038/s41929-019-0237-3 ↗
15. Molecular design of single-atom catalysts for oxygen reduction reaction10.1002/aenm.201903815 ↗
16. Status and challenges for the application of platinum group metal-free catalysts in proton exchange membrane fuel cells10.1016/j.coelec.2020.08.009 ↗
17. Iron-based cathode catalyst with enhanced power density in polymer electrolyte membrane fuel cells10.1038/ncomms1427 ↗
18. Engineering nanostructures of PGM-free oxygen-reduction catalysts using metal-organic frameworks10.1016/j.nanoen.2016.11.033 ↗
19. Advanced electrocatalysts for the oxygen reduction reaction in energy conversion technologies10.1016/j.joule.2019.12.014 ↗
20. Atomically dispersed iron sites with a nitrogen-carbon coating as highly active and durable oxygen reduction catalysts for fuel cells10.1038/s41560-022-01062-1 ↗
21. Structural descriptors of zeolitic−imidazolate frameworks are keys to the activity of Fe−N−C catalysts10.1021/jacs.6b11248 ↗
22. Atomically dispersed metal catalysts for oxygen reduction10.1021/acsenergylett.9b00804 ↗
23. Molecular oxygen reduction in PEM fuel cells: evidence for the simultaneous presence of two active sites in Fe-based catalysts10.1021/jp020267f ↗
24. Combinatorial search for oxygen reduction reaction electrocatalysts: a review10.1016/j.jpowsour.2012.05.107 ↗
25. Machine learning for molecular and materials science10.1038/s41586-018-0337-2 ↗
26. Data-Driven materials science: status, challenges, and perspectives
27. Accelerating the discovery of materials for clean energy in the era of smart automation10.1038/s41578-018-0005-z ↗
28. Machine learning for renewable energy materials10.1039/C9TA02356A ↗
29. A critical review of machine learning of energy materials10.1002/aenm.201903242 ↗
30. Machine learning for electrocatalyst and photocatalyst design and discovery10.1021/acs.chemrev.2c00061 ↗
31. Machine learning for catalysis informatics: recent applications and prospects10.1021/acscatal.9b04186 ↗
32. Coupling high-throughput experiments and regression algorithms to optimize PGM-free ORR electrocatalyst systems10.1021/acsaem.0c01466 ↗
33. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach10.1038/nmat4717 ↗
34. Closed-loop optimization of fast-charging protocols for batteries with machine learning10.1038/s41586-020-1994-5 ↗
35. Identifying degradation patterns of lithium Ion batteries from impedance spectroscopy using machine learning10.1038/s41467-020-15235-7 ↗
36. Towards online optimisation of solid oxide fuel cell performance: combining deep learning with multi-physics simulation
37. Applying machine learning to boost the development of high-performance membrane electrode assembly for proton exchange membrane fuel cells10.1039/D0TA12571G ↗
38. Probabilistic machine learning and artificial intelligence10.1038/nature14541 ↗
39. Accelerated search for materials with targeted properties by adaptive design10.1038/ncomms11241 ↗
40. Accelerated Discovery of CO2 electrocatalysts using active machine learning10.1038/s41586-020-2242-8 ↗
41. Ball milling: a green mechanochemical approach for synthesis of nitrogen doped carbon nanoparticles10.1039/c3nr02328a ↗
42. Oxygen reduction reaction in a droplet on graphite: direct evidence that the edge is more active than the basal plane10.1002/anie.201406695 ↗
43. Highly active and stable single iron site confined in graphene nanosheets for oxygen reduction reaction10.1016/j.nanoen.2016.12.056 ↗
44. https://www.anl.gov/cse/highthroughput-research-laboratory.
45. Oxygen reduction activities compared in rotating-disk electrode and proton exchange membrane fuel cells for highly active Fe-N-C catalysts10.1016/j.electacta.2012.09.057 ↗
46. Deactivation of Fe-N-C catalysts during catalyst ink preparation process10.1016/j.cattod.2019.03.067 ↗
47. Oxygen reduction on a high-surface area Pt:Vulcan carbon catalyst: a thin-film rotating ring-disk electrode study10.1016/S0022-0728(00)00407-1 ↗
48. Elucidation of Fe-N-C electrocatalyst active site functionality via in-situ X-ray absorption and operando determination of oxygen reduction reaction kinetics in a PEFC10.1016/j.apcatb.2019.117929 ↗
49. https://scikit-learn.org/stable/.
50. Hastie · 2009
51. Efficient global optimization of expensive black-box functions10.1023/A:1008306431147 ↗
52. A new method of locating the maximum point of an arbitrary multipeak curve in the presence of noise10.1115/1.3653121 ↗
53. Powell · 2013
54. No free lunch theorems for optimization10.1109/4235.585893 ↗
55. Communication - on the lack of correlation between the voltammetric redox couple and ORR activity of Fe-N-C catalysts10.1149/1945-7111/abb97c ↗
56. Double layer capacitance measurements to characterize the water instruction into porous materials10.1021/acs.jpcc.6b07861 ↗
57. Electrochemical and capacitive properties of thin-layer carbon black electrodes10.1016/j.jpowsour.2008.03.048 ↗
58. Determination of surface area of carbon-black by simple cyclic voltammetry measurements in aqueous H2SO410.1016/j.jiec.2013.02.013 ↗
59. Electrochemical supercapacitors based on industrial carbon blacks in aqueous H2SO410.1023/A:1017529920916 ↗
60. Correlation between capacitances of porous carbons in acidic and aprotic EDLC electrolytes10.1016/j.elecom.2007.01.031 ↗
61. PGM-Free oxygen-reduction catalyst development for proton-exchange membrane fuel cells: challenges, solutions, promises10.1021/accountsmr.1c00226 ↗
62. Directly converting Fe-doped metal–organic frame works into highly active and stable Fe-N-C catalysts for oxygen reduction in acid10.1016/j.nanoen.2016.04.042 ↗
63. Single atomic iron catalysts for oxygen reduction in acidic media: particle size control and thermal activation10.1021/jacs.7b06514 ↗
64. Thermally driven structure and performance evolution of atomically dispersed FeN4 sites for oxygen reduction10.1002/anie.201909312 ↗
65. Catalysis of graphitization10.1002/jctb.5010200409 ↗
66. High-performance electrocatalysts for oxygen reduction derived from polyaniline, iron and cobalt10.1126/science.1200832 ↗
67. Atomically dispersed iron catalysts for polymer electrolyte fuel cells10.1039/C9EE00877B ↗
68. Establishing reactivity descriptors for platinum group metal (PGM)-free Fe-N-C catalysts for PEM fuel cells10.1039/D0EE01013H ↗
69. Effect of Furfuryl alcohol on metal organic framework-based Fe/N/C electrocatalysts for polymer electrolyte membrane fuel cells10.1016/j.electacta.2013.12.022 ↗
70. Enhancement of Fe-N-C carbon catalyst activity for the oxygen reduction reaction: effective increment of active sites by short and repeated heating process10.1039/C8RA08359B ↗
71. Heat-treated Fe/N/C catalysts for O2 electroreduction: are active sites hosted in micropores?10.1021/jp057135h ↗
72. Physics informed machine learning10.1038/s42254-021-00314-5 ↗