open access publication

Article, 2023

Machine learning guided development of high-performance nano-structured nickel electrodes for alkaline water electrolysis

Applied Materials Today, ISSN 2352-9415, 2352-9407, Volume 35, Page 102005, 10.1016/j.apmt.2023.102005

Contributors

Jensen, Veronica Humlebæk [1] Moretti, Enzo Raffaele (Corresponding author) [1] Busk, Jonas [1] Christiansen, Emil Howaldt 0009-0004-3155-3684 [1] Skov, Sofie Marie [1] Jacobsen, Emilie [1] Kraglund, Mikkel Rykaer 0000-0002-1229-1007 [1] Bhowmik, Arghya 0000-0003-3198-5116 [1] Kiebach, Ragnar 0000-0002-4619-3894 (Corresponding author) [1]

Affiliations

  1. [1] Technical University of Denmark
    2. [NORA names: DTU Technical University of Denmark; University; Denmark; Europe, EU; Nordic; OECD]

Abstract

Utilizing a human in the loop Bayesian optimisation paradigm based on Gaussian process regression, we optimized an Ni electrodeposition method to synthesize nano-structured, high-performance hydrogen evolution reaction electrodes. Via exploration-exploitation stages, the synthesis process variables current density, temperature, ligand concentration and deposition time were optimized influencing the deposition layer morphology and, consequently, hydrogen evolution reaction activity. The resulting structures range from micrometre-sized, star-shaped features to nano-sized sandpaper-like structures with very high specific surface areas and good hydrogen evolution reaction activity. Using the overpotential at 10 mA cm−2 as the figure of merit, hydrogen evolution reaction overpotentials as low as -117 mV were reached, approaching the best known technical high surface area electrodes (e.g. Raney Ni). This is achieved with considerably fewer experiments than what would have been necessary with a linear grid search, as the machine learning model could capture the unintuitive interdependencies of the synthesis variables.

Keywords

Gaussian process regression, activity, alkaline, alkaline water electrolysis, area, cm-2, concentration, current density, density, deposited layer morphology, deposition, deposition time, electrode, electrodeposition method, electrolysis, evolution reaction activity, experiments, grid search, humans, hydrogen, hydrogen evolution reaction activity, hydrogen evolution reaction electrode, hydrogen evolution reaction overpotential, interdependence, layer morphology, learning, learning models, ligand, ligand concentration, loop, machine, machine learning, machine learning models, method, micrometer-sized, model, morphology, nano-structures, nickel electrode, optimisation paradigm, overpotential, paradigm, process, process regression, range, reaction activity, reaction overpotential, regression, search, stage, structure, structures range, surface, surface area, synthesis, synthesis process, synthesis variables, synthesized nano-structures, temperature, time, variable current density, variables, water electrolysis

Funders

  • Danish Agency for Science and Higher Education

Data Provider: Digital Science

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+