New materials library could help AI design better sodium-ion batteries

edited by Sadie Harley, reviewed by Robert Egan

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

Add to Preferred Sources Visual abstract. Credit: Journal of Materials Chemistry A (2026). DOI: 10.1039/d6ta04588j The start of a new battery materials library could pave the way for future AI models to help scientists design sodium-ion batteries that charge faster, last longer and store more energy, according to new research from the University of Surrey.

Sodium-ion batteries are being developed as a promising alternative to conventional lithium-ion batteries, as sodium is much more abundant and widely available. However, improving the amount of energy they can hold and how well they perform over repeated charging is a major barrier to their wider use.

In a new study published in the Journal of Materials Chemistry A, researchers investigated how changing the chemical makeup of sodium manganese oxide could improve its performance as a cathode—a key battery component that helps determine how much energy a battery can store and how well it performs.

The team created a library of 28 different compositions, substituting some of the manganese with varying amounts of iron, titanium and vanadium, before comparing how each performed when tested in sodium-ion batteries.

The results showed that iron was linked to higher energy-storage capacity, vanadium improved stability over repeated charging and discharging, and small amounts of titanium improved performance at higher rates. Some titanium-containing compositions also retained more than 90% of their capacity after 100 cycles.

An automated approach was developed to analyze the large amounts of data generated by the experiments, with the resulting data set used to train a machine-learning model. While the current library is too small for reliable predictions, expanding it could eventually allow AI to identify new battery compositions before they are made and tested in the lab.

Dr. Daniel Commandeur, lecturer at the School of Chemistry and Chemical Engineering and corresponding author of the study, said, "We rely heavily on lithium-ion batteries, but lithium resources are relatively scarce and unevenly distributed around the world. Sodium is far more abundant, making sodium-ion batteries an important technology to develop.

"The challenge is finding materials that deliver the performance we need. This work is a first step toward building the larger data sets needed for machine learning to guide that search—helping us identify promising materials faster and accelerate the development of better sodium-ion batteries."

Expanding the approach to a much wider range of cathode materials could create the larger, high-quality data sets needed for machine learning to help speed up the discovery of new battery materials.

Eden Marks, Ph.D. student in space engineering and co-lead author of the study, said, "What stood out most was how relatively small changes in composition could shift the balance between how much energy a material can store, how it performs at higher rates and how well it lasts. Mapping those relationships gives us a much clearer picture of where to look next."

In the future, expanding the materials composition library could help scientists tailor sodium-ion cathodes to different performance needs—whether the priority is storing more energy, charging faster or lasting through more charge cycles.

Eden Marks et al., Probing the composition space of V, Fe, and Ti substituted sodium manganese oxides for next-generation sodium-ion cathodes, Journal of Materials Chemistry A (2026). DOI: 10.1039/d6ta04588j Journal information: Journal of Materials Chemistry A

BSc Life Sciences & Ecology. Microbiology lab background with pharmaceutical news experience in oil, gas, and renewable industries. Full profile →

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →