Scholarlink

<p>The vast chemical compositional space presents challenges in catalyst development using traditional methods. Machine learning (ML) offers new opportunities, but current ML models are typically limited to screening a single catalyst type. In this work, we developed an efficient ML model to predict hydrogen evolution reaction (HER) activity across diverse catalysts. By minimizing features, we introduced a key energy-related feature <i>φ</i> = <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41524_2025_1607_Article_IEq1.gif" Format="GIF" Height="21" Rendition="HTML" Resolution="72" Type="Linedraw" Width="65" /> </InlineMediaObject> <EquationSource Format="TEX">\({{\rm{Nd}}0}^{2}/{\rm{\psi }}0\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mrow> <mi mathvariant="normal">Nd</mi> <mn>0</mn> </mrow> <mrow> <mn>2</mn> </mrow> </msup> <mo>/</mo> <mi mathvariant="normal">ψ</mi> <mn>0</mn> </mrow> </math></EquationSource> </InlineEquation>, which correlates with HER free energy. Using just ten features, the Extremely Randomized Trees model achieved <i>R</i>² = 0.922. We predicted 132 new catalysts from the Material Project database, among which several exhibited promising HER performance. The time consumed by the ML model for predictions is one 200,000th of that required by traditional density functional theory (DFT) methods. The model provides an efficient approach for discovering high-performance HER catalysts using a small number of key features and offers insights for the development of other catalysts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A machine learning model with minimize feature parameters for multi-type hydrogen evolution catalyst prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月24日

查看全文
  • Chao Wang,
  • Bing Wang,
  • Changhao Wang,
  • Aojian Li,
  • Zhipeng Chang,
  • Ruzhi Wang

摘要

The vast chemical compositional space presents challenges in catalyst development using traditional methods. Machine learning (ML) offers new opportunities, but current ML models are typically limited to screening a single catalyst type. In this work, we developed an efficient ML model to predict hydrogen evolution reaction (HER) activity across diverse catalysts. By minimizing features, we introduced a key energy-related feature φ =  \({{\rm{Nd}}0}^{2}/{\rm{\psi }}0\) Nd 0 2 / ψ 0 , which correlates with HER free energy. Using just ten features, the Extremely Randomized Trees model achieved R² = 0.922. We predicted 132 new catalysts from the Material Project database, among which several exhibited promising HER performance. The time consumed by the ML model for predictions is one 200,000th of that required by traditional density functional theory (DFT) methods. The model provides an efficient approach for discovering high-performance HER catalysts using a small number of key features and offers insights for the development of other catalysts.