Preprint · 2026 · Open access

A Closed-Loop Machine Learning and Digital Twin Framework for the Discovery of High- Performance Solid-State Electrolytes

Sahil Bhardwaj¹, Vikas Sidhu¹

Research Square · Published 7 May 2026 · DOI 10.21203/rs.3.rs-9345215/v1

Open PDFView at the publisherCite this paper

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

All highly cited Materials Science papers

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.