skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on June 1, 2026

Title: Generative AI for discovering porous oxide materials for next-generation energy storage
The development of next-generation energy storage systems relies on discovering new materials that support multivalent-ion transport. Transition metal oxides (TMOs) are promising due to their structural versatility, high ionic conductivity, and ability to accommodate multiple charge carriers. However, their vast compositional and structural diversity makes traditional exploration inefficient. This work presents a generative AI framework combining a crystal diffusion variational autoencoder (CDVAE) and a fine-tuned large language model (LLM) to discover porous oxide materials. Thousands of candidate structures are generated and screened for structural validity, thermodynamic stability, and electronic properties using a graph-based machine learning model and density functional theory (DFT) calculations. CDVAE identifies a broader variety of structures, including five novel TMO-based candidates, while LLM excels in generating highly stable structures near equilibrium. This approach demonstrates the power of generative AI in accelerating the discovery of advanced battery materials for multivalent-ion storage.  more » « less
Award ID(s):
2237990
PAR ID:
10610635
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Cell Press
Date Published:
Journal Name:
Cell Reports Physical Science
ISSN:
2666-3864
Page Range / eLocation ID:
102665
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Energy & Environmental Science)
    null (Ed.)
    Due to the low cost and abundance of multivalent metallic resources (Mg/Al/Zn/Ca), multivalent rechargeable batteries (MRBs) are promising alternatives to Li-ion and Pb-acid batteries for grid-scale stationary energy storage applications. However, the high performance of inorganic electrode materials in Li-ion batteries does not extend to MRBs, because the high charge density of multivalent cations dramatically reduces their diffusivity in the crystal lattice of inorganic materials. To achieve high-performance MRBs, organic electrode materials (OEMs) with abundant structural diversity and high structural tunability offer opportunities. This review presents an overview of the state-of-the-art OEMs in MRBs, including non-aqueous rechargeable Mg/Al/Zn and aqueous rechargeable Mg/Al/Zn/Ca batteries. The advantages, challenges, development, mechanism, structure, and performance of OEMs in MRBs are discussed in detail. To provide a comprehensive and thorough understanding of OEMs in MRBs, the correlation between molecular structure and electrochemical behavior is also summarized and discussed. This review offers insights for the rational structure design and performance optimization of advanced OEMs in MRBs. 
    more » « less
  2. ; ; (, Energy Advances)
    Lithium-ion batteries (LIBs) are ubiquitous in everyday applications. However, Lithium (Li) is a limited resource on the planet and, therefore, not sustainable. As an alternative to lithium, earth-abundant and cheaper multivalent metals such as aluminum (Al) and calcium (Ca) have been actively researched in battery systems. However, finding suitable intercalation hosts for multivalent-ion batteries is urgently needed. Open-tunneled oxides represent a specific category of microparticles distinguished by the presence of integrated one-dimensional channels or nanopores. This work focuses on two promising open-tunnel oxides: Niobium Tungsten Oxide (NTO) and Molybdenum Vanadium Oxide (MoVO). The MoVO structure can accommodate a larger number of multivalent ions than NTO due to its larger surface area and different shapes. Specifically, the MoVO structure can adsorb Ca, Li, and Al ions with adsorption potentials ranging from around 4 to 5 eV. However, the adsorption potential for hexagonal channels of Al ion drops to 1.73 eV due to the limited channel area. The NTO structure exhibits an insertion/adsorption potential of 4.4 eV, 3.4 eV, and 0.9 eV for one Li, Ca, and Al, respectively. Generally, Ca ions are more readily adsorbed than Al ions in both MoVO and NTO structures. Bader charge analysis and charge density plots reveal the role of charge transfer and ion size in the insertion of multivalent ions such as Ca and Al into MoVO and NTO systems. Exploring open-tunnel oxide materials for battery applications is hindered by vast compositional possibilities. The execution of experimental trials and quantum-based simulations is not viable for addressing the challenge of locating a specific item within a large and complex set of possibilities. Therefore, it is imperative to conduct structural stability testing to identify viable combinations with sufficient pore topologies. Data mining and machine learning techniques are employed to discover innovative transitional metal oxide materials. This study compares two machine learning algorithms, one utilizing descriptors and the other employing graphs to predict the synthesizability of new materials inside a laboratory setting. The outcomes of this study offer valuable insights into the exploration of alternative naturally occurring multiscale particles. 
    more » « less
  3. ; ; ; (, Journal of Materials Chemistry A)
    The zinc-ion battery (ZIB) has been a system of particular interest in the research community as a possible alternative to lithium-ion batteries (LIB), and much work has been devoted to finding a suitable host material. In this article, monoclinic V 2 (PO 4 ) 3 is investigated as a host material for reversible insertion of Zn 2+ . Initial chemical assessment via a facile microwave-assisted chemical insertion method indicates the possibility of Zn 2+ insertion into the host. Electrochemical assessment, however, exhibits a significant capacity fade. In-depth analysis on the average and local structure of Li 3 V 2 (PO 4 ) 3 , the empty host V 2 (PO 4 ) 3 , and the Zn-inserted V 2 (PO 4 ) 3 reveals that heavy distortion is induced upon Zn 2+ insertion into the V 2 (PO 4 ) 3 framework, which is believed to be a result of a strong host–guest interaction jeopardizing the structural integrity. This is further supported by the dissolution of most of the material during the chemical oxidation of the Zn-inserted V 2 (PO 4 ) 3 . The underlying structural inadequacy poses difficulties for monoclinic V 2 (PO 4 ) 3 to be a viable reversible host for Zn-ion batteries. This work suggests that not only the electrostatic repulsions of multivalent ions in a structure during diffusion, but also the structural stability of the host upon insertion of multivalent ions, must be considered for a better design of suitable host materials for multivalent-ion batteries. 
    more » « less
  4. ; ; ; ; (, American Society for Composites-DESTech publications)
    Carbon fiber-based structural lithium-ion batteries are attracting significant attention in the automotive and aerospace industries due to their dual capability of energy storage and mechanical load-bearing, leading to weight reduction. These batteries utilize lightweight carbon fiber (CF) composites, which offer excellent stiffness, strength-to-weight ratios, and electrical conductivity. Polyacrylonitrile-based CFs, comprising graphitic and amorphous carbon, are particularly suitable for Li-ion battery applications as they allow the storage of lithium ions. However, integrating lithium iron phosphate (LFP) into CFs poses challenges due to complex lab-scale processes and the use of toxic dispersants, hindering large-scale industrial compatibility. To address this, we investigate the development of water-based LFP-integrated CF structural Li-ion batteries. Homogeneous suspensions are created using cellulose nanocrystals (CNCs) to form hybrid structures. The battery system employs LFP-modified CF as the cathode, unsized CF as the anode, and a water-based electrolyte. The LFP-CNC-graphene nanoplatelet (GNP) hybrids are coated onto CFs through immersion coating. Scanning electron microscopy (SEM) images confirm the well-dispersed and well-adhered LFP-CNC-GNP structures on the CF surface, contributing to their mechanical interlocking and electrochemical performance. The batteries demonstrate a specific energy density of 62.67 Wh/kg and a specific capacity of 72.7 mAh/g. Furthermore, the cyclic voltammetry experiments reveal the stability of the LFP-CNC-GNP-coated CF batteries over 200 cycles without degradation. This research enables the engineering of hybrid nanostructured battery laminates using novel LFP-CNC-GNP-coated CFs, opening avenues for the development of innovative Li-ion structural batteries. 
    more » « less
  5. ; ; ; ; ; (, Proceedings of Gateways 2024)
    This paper reports on the lessons learned from developing and deploying campus-wide large language model (LLM) services at Purdue University for generative AI (GenAI) applications in education and research. We present a frame- work for identifying an LLM solution suite and identify key considerations related to developing custom solutions. While the GenAI ecosystem continues to evolve, the framework is intended to provide a tool- and organization-agnostic approach to guide leaders in conversations and strategy for future work and collaboration in this emerging field. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email