# Pitfalls in Artificial Intelligence Powered Discovery Due to Electrocatalyst Evaluation Methodologies

https://mdr.nims.go.jp/datasets/8e4bdd42-3d36-4b12-8dae-80602687d112

## File

- [Pitfalls in Artificial Intelligence_revised_clean_v2.docx](https://mdr.nims.go.jp/filesets/1aa9d9f3-8999-4948-a459-4f85baea9d96/download) ([Detail](https://mdr.nims.go.jp/filesets/1aa9d9f3-8999-4948-a459-4f85baea9d96.md))

## Id

8e4bdd42-3d36-4b12-8dae-80602687d112

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2025-11-04T01:15:51.962711Z

## Updated at

2026-04-30T03:01:11.491392Z

## Published at

2026-05-22T23:31:12.944060Z

## Doi

https://doi.org/10.48505/nims.5849

## First published url

https://doi.org/10.1021/acselectrochem.5c00153

## Date published

2025-09-04

## Recorded date published

2025-9-4

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Pitfalls in Artificial Intelligence Powered Discovery Due to Electrocatalyst
    Evaluation Methodologies
  title_type: original
  lang: en

## Description

- description: The explosive increase in popularity and increased accessibility to
    artificial intelligence and data science tools have opened the door for exploring
    previously deemed “too large” experimental spaces efficiently in experimental
    chemistry. This is of special interest for the field of electrocatalysis, where
    the development of new materials has relied largely on trial-and-error approaches
    that are not time- and resource-efficient. By leveraging these approaches, we
    can more effectively find promising electrocatalyst compositions and synthesis
    conditions that result in lower overpotentials and higher electrocatalyst durability.
    In this Technical Note, we use oxygen evolution electrocatalysts as a model to
    highlight potential pitfalls in the use of data-driven strategies for electrocatalyst
    development, focusing on the important choice of optimization metrics, normalization
    of data, and common errors that may appear during these kinds of approaches.
  description_type: abstract
  lang: und

## Creator

- name: Abraham Castro Garcia
  role: author
- name: Ken Sakaushi
  role: author
  orcid: https://orcid.org/0000-0003-4797-9087
  organization: National Institute for Materials Science

## Contact agent



## Publisher

organization: American Chemical Society (ACS)

## Managing organization



## Keyword

- subject: machine learning
  schema: not_defined

## Rights

- description: This document is the Accepted Manuscript version of a Published Work
    that appeared in final form in ACS Electrochemistry, copyright © 2025 American
    Chemical Society after peer review and technical editing by the publisher. To
    access the final edited and published work see https://doi.org/10.1021/acselectrochem.5c00153.
  identifier: http://rightsstatements.org/vocab/InC/1.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: ACS Electrochemistry
  volume: '1'
  issue: '9'
  start_page: 1871
  end_page: 1877

## Conference



## Related item



## Funding

- funder_name: University of Cambridge
- identifier: JPMJAP2421
  funder_name: Japan Science and Technology Agency
- identifier: JPMJGX23H2
  funder_name: Japan Science and Technology Agency
- funder_name: National Institute for Materials Science
- funder_name: Churchill College, University of Cambridge

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 1aa9d9f3-8999-4948-a459-4f85baea9d96
  filename: Pitfalls in Artificial Intelligence_revised_clean_v2.docx
  content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
  size: 1039363
  md5: 3b9723c783c355ce33c5d18e466d8a55

## Thumbnail

fileset_id: 1aa9d9f3-8999-4948-a459-4f85baea9d96
filename: Pitfalls in Artificial Intelligence_revised_clean_v2.docx