PervoTransformer: Multi-Scale Transformer-Based Device Design and Atomistic Modeling of Perovskites
4 affiliations
- 1Department of Physics
- 2Quaid-i-Azam University Islamabad
- 3National University of Sciences & Technology Islamabad
- 4Kohsar University Murree Punjab
Abstract
Perovskite solar cell design involves a large and highly coupled space of material compositions, layer structures, and physical parameters, making systematic exploration of complete device architectures computationally challenging. This work introduces PervoTransformer, a transformer-based framework that represents complete device architectures as sequences and learns device-level behavior directly from this representation. A RoBERTa model is fine-tuned on SCAPS-generated device sequences spanning six perovskite families, including MAPbI3, FAPbI3, CsPbI3, and their Sn-based analogs. The model simultaneously predicts multiple performance metrics, including power conversion efficiency (PCE), short-circuit current density (Jsc), open-circuit voltage (Voc), and fill factor (FF), demonstrating the ability of transformer encoders to capture coupled, nonlinear dependencies across complete device stacks. To explore configurations beyond the training distribution, a GPT-2 model is fine-tuned using the same device-sequence representation to generate candidate architectures with new combinations of compositional and physical parameters. Generated configurations are screened for validity and uniqueness and subsequently evaluated using the fine-tuned RoBERTa model, enabling efficient exploration of under-sampled regions of the device design space. In parallel, machine-learned interatomic potentials based on the MACE framework are fine-tuned for CsSnX3 (X = Cl,Br, I) using available DFT data, enabling efficient structural relaxation and exploration of lead-free Sn-based perovskites. The resulting multiscale framework combines sequence-based transformer models for device-level design with machine-learned interatomic potentials for atomistic materials exploration, while retaining first-principles calculations for detailed physical validation. This approach provides a scalable strategy for navigating the coupled materials and device design spaces of perovskite solar cells while reducing reliance on computationally expensive simulations during initial exploration.
Related
- High-throughput Materials-to-Device Discovery of Lead-free Double Perovskites Beyond Radiative-limit Metrics
- Assigning the Low-Energy Excitons in Far-Red Photosystem II through Atomistic Modeling
- Quantum-accurate atomistic modeling of enzyme catalysis using a machine learned potential
- Sequential replica exchange with solute tempering for atomistic modeling of supramolecular polymer structures
- Atomistic Probability Kinetic Modeling of Polymer Functionalization: A Framework for Post-Functionalization and Upcycling of Polymers
BibTeX
@misc{hussain2026pervotransformer,
title = {{PervoTransformer: Multi-Scale Transformer-Based Device Design and Atomistic Modeling of Perovskites}},
author = {Wahid Hussain and Ali Hamza and Muhammad Sultan and Fouzia Perveen Malik},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15009607/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009607/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PervoTransformer: Multi-Scale Transformer-Based Device Design and Atomistic Modeling of Perovskites
AU - Wahid Hussain
AU - Ali Hamza
AU - Muhammad Sultan
AU - Fouzia Perveen Malik
PY - 2026
DA - 2026/09/29
PB - ChemRxiv
DO - 10.26434/chemrxiv.15009607/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009607/v1
AB - Perovskite solar cell design involves a large and highly coupled space of material compositions, layer structures, and physical parameters, making systematic exploration of complete device architectures computationally challenging. This work introduces PervoTransformer, a transformer-based framework that represents complete device architectures as sequences and learns device-level behavior directly from this representation. A RoBERTa model is fine-tuned on SCAPS-generated device sequences spanning six perovskite families, including MAPbI3, FAPbI3, CsPbI3, and their Sn-based analogs. The model simultaneously predicts multiple performance metrics, including power conversion efficiency (PCE), short-circuit current density (Jsc), open-circuit voltage (Voc), and fill factor (FF), demonstrating the ability of transformer encoders to capture coupled, nonlinear dependencies across complete device stacks. To explore configurations beyond the training distribution, a GPT-2 model is fine-tuned using the same device-sequence representation to generate candidate architectures with new combinations of compositional and physical parameters. Generated configurations are screened for validity and uniqueness and subsequently evaluated using the fine-tuned RoBERTa model, enabling efficient exploration of under-sampled regions of the device design space. In parallel, machine-learned interatomic potentials based on the MACE framework are fine-tuned for CsSnX3 (X = Cl,Br, I) using available DFT data, enabling efficient structural relaxation and exploration of lead-free Sn-based perovskites. The resulting multiscale framework combines sequence-based transformer models for device-level design with machine-learned interatomic potentials for atomistic materials exploration, while retaining first-principles calculations for detailed physical validation. This approach provides a scalable strategy for navigating the coupled materials and device design spaces of perovskite solar cells while reducing reliance on computationally expensive simulations during initial exploration.
ER -