Towards a fully differentiable digital twin for solar cells

2025-12-02

AI Summary

Existing solar cell simulations are typically isolated modules, hindering end-to-end gradient-based joint optimization of annual energy yield (EY). To address this, we propose Sol(Di)²T—the first fully differentiable digital twin framework for photovoltaics—that unifies material properties, morphological parameters, optical/electrical physics-based simulations, and spatiotemporal climate-geographic conditions, enabling gradient-driven co-optimization across multiple scales. Leveraging differentiable programming, Sol(Di)²T tightly couples first-principles physical models with differentiable machine learning surrogate models, establishing an end-to-end differentiable pipeline from atomic-scale material descriptors to system-level EY prediction. Validated on organic photovoltaics, Sol(Di)²T achieves high-fidelity EY prediction under unseen operating conditions and identifies globally optimal device configurations. This represents a significant advance over conventional non-differentiable, fragmented simulation paradigms, enabling physics-informed, scalable, and differentiable photovoltaic design optimization.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Learning & Optimization for CV
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Maximizing energy yield (EY) - the total electric energy generated by a solar cell within a year at a specific location - is crucial in photovoltaics (PV), especially for emerging technologies. Computational methods provide the necessary insights and guidance for future research. However, existing simulations typically focus on only isolated aspects of solar cells. This lack of consistency highlights the need for a framework unifying all computational levels, from material to cell properties, for accurate prediction and optimization of EY prediction. To address this challenge, a differentiable digital twin, Sol(Di)$^2$T, is introduced to enable comprehensive end-to-end optimization of solar cells. The workflow starts with material properties and morphological processing parameters, followed by optical and electrical simulations. Finally, climatic conditions and geographic location are incorporated to predict the EY. Each step is either intrinsically differentiable or replaced with a machine-learned surrogate model, enabling not only accurate EY prediction but also gradient-based optimization with respect to input parameters. Consequently, Sol(Di)$^2$T extends EY predictions to previously unexplored conditions. Demonstrated for an organic solar cell, the proposed framework marks a significant step towards tailoring solar cells for specific applications while ensuring maximal performance.

Problem

• Develops a differentiable digital twin for solar cells
• Unifies material to cell properties for energy yield prediction
• Enables gradient-based optimization of solar cell performance

Innovation

• Differentiable digital twin for end-to-end solar cell optimization
• Machine-learned surrogate models enable gradient-based parameter optimization
• Unified framework integrates material properties to climatic conditions