AI Research at NJIT Paves Way for Lithium-Ion Battery Alternatives

Researchers from New Jersey Institute of Technology (NJIT) have used artificial intelligence to address a critical challenge in energy storage: identifying affordable, sustainable alternatives to lithium-ion batteries. In research published in Cell Reports Physical Science, an NJIT team led by Professor Dibakar Datta applied generative AI techniques to discover new porous materials for multivalent-ion batteries. These next-generation batteries, which use abundant elements such as magnesium, calcium, aluminum, and zinc, could provide a cost-effective and more sustainable option compared to lithium-ion batteries, which face supply constraints and environmental concerns.

Unlike lithium-ion batteries, which rely on ions carrying a single positive charge, multivalent-ion batteries use ions with two or three positive charges. This enables the potential for significantly greater energy storage. However, their larger size and higher charge have historically made it challenging to integrate multivalent ions efficiently into battery materials — a limitation directly addressed by the NJIT team’s AI-driven research.

“One of the biggest hurdles wasn’t a lack of promising battery chemistries — it was the sheer impossibility of testing millions of material combinations,” Datta said. “We turned to generative AI as a fast, systematic way to sift through that vast landscape and spot the few structures that could truly make multivalent batteries practical.

“This approach allows us to quickly explore thousands of potential candidates, dramatically speeding up the search for more efficient and sustainable alternatives to lithium-ion technology.”

To achieve this, the researchers developed a dual-AI approach: a Crystal Diffusion Variational Autoencoder (CDVAE) and a finely tuned Large Language Model (LLM). The CDVAE, trained on extensive datasets of known crystal structures, generated entirely new structures with diverse geometries. The LLM then identified candidates closest to thermodynamic stability, increasing the likelihood of practical synthesis.

“Our AI tools dramatically accelerated the discovery process, which uncovered five entirely new porous transition metal oxide structures that show remarkable promise,” said Datta. “These materials have large, open channels ideal for moving these bulky multivalent ions quickly and safely, a critical breakthrough for next-generation batteries.”

The team confirmed the stability and feasibility of the AI-generated structures through quantum mechanical simulations and additional stability assessments, validating their potential for real-world applications.

“This is more than just discovering new battery materials — it’s about establishing a rapid, scalable method to explore any advanced materials, from electronics to clean energy solutions, without extensive trial and error,” Datta said.

Next steps for the research include partnering with experimental laboratories to synthesize and test the AI-designed materials, moving closer to commercially viable multivalent-ion batteries.

About New Jersey Institute of Technology (NJIT):

New Jersey Institute of Technology is a public polytechnic university in Newark, New Jersey, recognized for its research and innovation in engineering, applied sciences, architecture, and design. NJIT conducts advanced research in sustainable energy, materials science, artificial intelligence, and other critical technology areas. Its faculty, students, and research teams work closely with industry partners and government agencies to develop practical solutions for global challenges.  To learn more about this and other research underway at NJIT, please click here.

Source/Image Credit: New Jersey Institute of Technology (NJIT)

---

(Editor’s Note: All trademarks mentioned in this article, including company names, product names, and logos, are the property of their respective owners. Use of these trademarks is for informational purposes only and does not imply any endorsement.)