Gast ::
| Hauptseite > Publikationsdatenbank > Acceleration of Emerging Photovoltaics |
| Hauptseite > Publikationsdatenbank > Acceleration of Emerging Photovoltaics |
| Contribution to a conference proceedings | FZJ-2024-06994 |
;
2023
FUNDACIO DE LA COMUNITAT VALENCIANA SCITO València
This record in other databases:
Please use a persistent id in citations: doi:10.29363/nanoge.matsus.2024.349
Abstract: Organic or perovskite photovoltaics poses a multi-objective optimization problem in alarge multi-dimensional parameter space. Massive progress was achieved in developingmethods to accelerate solving such complex optimization tasks. We have demonstratedfor both types of semiconductors, that the combination of Gaussian Process Regression(GPR) and Bayesian Optimization (BO) are most efficient in predicting new materials,identify optimized processing conditions or invent alternative device architectures inlarger parameter rooms. For a 4 dim space (solvent, donor-acceptor ratio, spin speed,concentration) with about 1000 variations in a 10 % grid space, 30 samples are sufficientto find the optimum. For 6 dimensional spaces, the possible variations go into themillions and billions. Nevertheless, our automated lines, being operated in anautonomous optimization mode, were able to identify globalized optima within severalhundred´s of experiments. In the outlook we discuss whether these autonomouslyoperated research lines can as well handle unorthodox optimization problems such asthe recycling of organic or perovskite solar cells
|
The record appears in these collections: |
