High-throughput parameter estimation from experimental data using Bayesian Inference with accelerated sampling

npj Computational Materials, vol. 12

Abstract

Abstract BIAS (Bayesian Inference with Accelerated Sampling) is a high-throughput parameter estimation framework designed to rapidly infer the root causes of device underperformance in real time. It integrates a deep neural network surrogate model with accelerated Markov Chain Monte Carlo (MCMC) sampling to efficiently explore high-dimensional parameter spaces and identify needle-like regions corresponding to the ground truth values of key physical parameters. BIAS is scalable to complex systems and has been used to infer eight underlying parameters in perovskite solar cell stacks with a speedup of 4800× compared to conventional Bayesian inference methods. Its rapid and robust inference capabilities make it suitable for integration into high-throughput fabrication workflows, enabling real-time feedback that links process variations to changes in material properties and their impact on device performance. By embedding BIAS in high-throughput fabrication cycles, researchers can accelerate the transition from novel materials to devices and obtain real-time insight into how novel material properties translate in the context of a device, and the root cause of performance limitations.

Authors 6

1. Basita Das corresponding

   Massachusetts Institute of Technology

   Affiliation as printed

   Massachusetts Institute of Technology, Cambridge, MA, USA

   Massachusetts Institute of Technology

2. William Heymann

   Forschungszentrum Jülich

   Affiliation as printed

   IBG-1 Biotechnology, Forschungszentrum Jülich, Jülich, NRW, Germany

   Forschungszentrum Jülich

3. Yueming Wang

   Forschungszentrum Jülich

   Affiliation as printed

   IMD-3 Photovoltaics, Forschungszentrum Jülich, Jülich, NRW, Germany

   IMD-3 Photovoltaics, Forschungszentrum Jülich

4. Uwe Rau Aachen Faculty of Electrical Engineering and Information Technology

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Faculty of Electrical Engineering and Information Technology, RWTH Aachen University, Aachen, NRW, Germany

   IMD-3 Photovoltaics, Forschungszentrum Jülich, Jülich, NRW, Germany

   IMD-3 Photovoltaics, Forschungszentrum Jülich

5. Thomas Kirchartz

   Forschungszentrum Jülich · University of Duisburg-Essen

   Affiliation as printed

   Faculty of Engineering and CENIDE, University of Duisburg-Essen, Essen, NRW, Germany

   IMD-3 Photovoltaics, Forschungszentrum Jülich, Jülich, NRW, Germany

   IMD-3 Photovoltaics, Forschungszentrum Jülich

6. Tonio Buonassisi corresponding

   Massachusetts Institute of Technology

   Affiliation as printed

   Massachusetts Institute of Technology, Cambridge, MA, USA

   Massachusetts Institute of Technology