Preprint · 2026 · Open access
A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes
Research Square · Published 7 May 2026 · DOI 10.21203/rs.3.rs-9345215/v1
In brief
“A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes” is a 2026 preprint by Sahil Bhardwaj¹ and Vikas Sidhu¹, published in Research Square. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.
- Citations
- 0
- References
- 4
- Authors
- 2
Abstract
The development of solid-state electrolytes (SSEs) with high ionic conductivity remains a critical challenge for next-generation batteries. Traditional trial-and-error discovery methods are time-consuming, and computational screening approaches often lack experimental validation. In this work, we present a closed-loop framework integrating machine learning (ML) with a physics-based digital twin (DT) to accelerate SSE discovery. A Random Forest model trained on 497 experimentally validated Li-based SSEs predicts ionic conductivity using composition-based descriptors. The model achieves a mean absolute error of approximately 0.91 log₁₀(S cm⁻¹) and an R² of 0.68. A Bayesian optimization strategy is employed to explore the Li-garnet compositional space, leading to the identification of an optimized composition, Li₆.₂₀Ga₀.₂₀Ta₀.₀₇La₃Zr₂O₁₂, with predicted ionic conductivity of 5.86 × 10⁻⁴ S cm⁻¹. The digital twin further validates this candidate through full-cell discharge simulation. This framework demonstrates an efficient and scalable approach for accelerating materials discovery in solid-state batteries.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Bhardwaj¹, S., & Sidhu¹, V. (2026). A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes. Research Square. https://doi.org/10.21203/rs.3.rs-9345215/v1
MLA 9
Bhardwaj¹, Sahil, and Vikas Sidhu¹. “A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-9345215/v1.
Chicago
Bhardwaj¹, Sahil and Vikas Sidhu¹. 2026. “A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes.” Research Square. https://doi.org/10.21203/rs.3.rs-9345215/v1.
Harvard
Bhardwaj¹, S. and Sidhu¹, V. (2026) ‘A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes’, Research Square. doi:10.21203/rs.3.rs-9345215/v1.
IEEE
S. Bhardwaj¹ and V. Sidhu¹, “A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes,” Research Square, 2026, doi: 10.21203/rs.3.rs-9345215/v1.
BibTeX
@misc{bhardwaj12026closed,
title = {{A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes}},
author = {Bhardwaj¹, Sahil and Sidhu¹, Vikas},
howpublished = {Research Square},
year = {2026},
doi = {10.21203/rs.3.rs-9345215/v1},
url = {https://doi.org/10.21203/rs.3.rs-9345215/v1}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- solid electrolytes
- solid-state batteries
- ionic conductivity prediction
- digital twin
- random forest
- Bayesian optimization
- garnet solid electrolyte
Work with this paper
Most-cited papers in Materials Science
- Electric Field Effect in Atomically Thin Carbon FilmsKostya S. Novoselov, Andre K. Geim, Sergey V. Morozov and 5 more · Science · 2004 · 67,474 citations
- Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenidesROBERT D. SHANNON · Acta Crystallographica Section A · 1976 · 66,944 citations
- Ab initio molecular dynamics for liquid metalsGeorg Kresse, J. Häfner · Physical review. B, Condensed matter · 1993 · 46,320 citations
- Helical microtubules of graphitic carbonSumio Iijima · Nature · 1991 · 43,639 citations
- The rise of grapheneAndre K. Geim, Kostya S. Novoselov · Nature Materials · 2007 · 40,328 citations
Questions about this paper
How do I cite this paper in APA style?
Bhardwaj¹, S., & Sidhu¹, V. (2026). A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes. Research Square. https://doi.org/10.21203/rs.3.rs-9345215/v1
How many times has this paper been cited?
0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Research Square: sign in and open the PDF from this page.
Who wrote this paper?
Sahil Bhardwaj¹, Vikas Sidhu¹.
What is the DOI of this paper?
10.21203/rs.3.rs-9345215/v1, permanently at https://doi.org/10.21203/rs.3.rs-9345215/v1. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.