An evolutionary-driven AI model discovering redox-stable organic electrode materials for alkali-ion batteries

• Data-driven approaches have been revolutionizing materials science and materials discovery in the past years. Especially when coupled with other computational physics methods, they can be applied in complex high-throughput schemes to discover novel materials, e.g. for batteries. In this direction, the present work provides a robust AI-driven framework, to accelerate the discovery of novel organic-based materials for Li-, Na- and K-ion batteries. This platform is able to predict the open-circuit voltage of the respective battery and provide an initial assessment of the materials redox stability. The model was employed to screen 45 million small molecules in the search for novel high-potential cathodes, resulting in a proposed shortlist of 3202, 689 and 702 novel compounds for Li-, Na- and K-ion batteries, respectively, considering only the redox stable candidates. 

Subject headings

NATURVETENSKAP  -- Kemi -- Materialkemi (hsv//swe)

NATURAL SCIENCES  -- Chemical Sciences -- Materials Chemistry (hsv//eng)

NATURVETENSKAP  -- Kemi -- Fysikalisk kemi (hsv//swe)

NATURAL SCIENCES  -- Chemical Sciences -- Physical Chemistry (hsv//eng)

Keyword

Batteries

Artificial intelligence

Organic electrode

High-voltage cathode material

Redox stability

Physics

Fysik

Publication and Content Type

ref (subject category)

art (subject category)