Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing

Abstract We demonstrate a multi-fidelity (MF) machine learning ensemble framework for the inverse design of photonic surfaces, trained on a dataset of 11,759 samples that we fabricate using high throughput femtosecond laser processing. The MF ensemble combines an initial low fidelity model for gener...

Full description

Saved in:
Bibliographic Details
Main Authors: Luka Grbčić, Minok Park, Mahmoud Elzouka, Ravi Prasher, Juliane Müller, Costas P. Grigoropoulos, Sean D. Lubner, Vassilia Zorba, Wibe Albert de Jong
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01518-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850196830477877248
author Luka Grbčić
Minok Park
Mahmoud Elzouka
Ravi Prasher
Juliane Müller
Costas P. Grigoropoulos
Sean D. Lubner
Vassilia Zorba
Wibe Albert de Jong
author_facet Luka Grbčić
Minok Park
Mahmoud Elzouka
Ravi Prasher
Juliane Müller
Costas P. Grigoropoulos
Sean D. Lubner
Vassilia Zorba
Wibe Albert de Jong
author_sort Luka Grbčić
collection DOAJ
description Abstract We demonstrate a multi-fidelity (MF) machine learning ensemble framework for the inverse design of photonic surfaces, trained on a dataset of 11,759 samples that we fabricate using high throughput femtosecond laser processing. The MF ensemble combines an initial low fidelity model for generating design solutions, with a high fidelity model that refines these solutions through local optimization. The combined MF ensemble can generate multiple disparate sets of laser-processing parameters that can each produce the same target input spectral emissivity with high accuracy (root mean squared errors < 2%). SHapley Additive exPlanations analysis shows transparent model interpretability of the complex relationship between laser parameters and spectral emissivity. Finally, the MF ensemble is experimentally validated by fabricating and evaluating photonic surface designs that it generates for improved efficiency energy harvesting devices. Our approach provides a powerful tool for advancing the inverse design of photonic surfaces in energy harvesting applications.
format Article
id doaj-art-7e7385e3d8e44b50888f80cbb62d27d0
institution OA Journals
issn 2057-3960
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-7e7385e3d8e44b50888f80cbb62d27d02025-08-20T02:13:20ZengNature Portfolionpj Computational Materials2057-39602025-02-0111111310.1038/s41524-025-01518-4Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processingLuka Grbčić0Minok Park1Mahmoud Elzouka2Ravi Prasher3Juliane Müller4Costas P. Grigoropoulos5Sean D. Lubner6Vassilia Zorba7Wibe Albert de Jong8Applied Mathematics and Computational Research Division, Computing Science Area, Lawrence Berkeley National LaboratoryEnergy Storage and Distributed Resources Division, Energy Technologies Area, Lawrence Berkeley National LaboratoryEnergy Storage and Distributed Resources Division, Energy Technologies Area, Lawrence Berkeley National LaboratoryEnergy Storage and Distributed Resources Division, Energy Technologies Area, Lawrence Berkeley National LaboratoryComputational Science Center, National Renewable Energy Laboratory, GoldenEnergy Storage and Distributed Resources Division, Energy Technologies Area, Lawrence Berkeley National LaboratoryEnergy Storage and Distributed Resources Division, Energy Technologies Area, Lawrence Berkeley National LaboratoryEnergy Storage and Distributed Resources Division, Energy Technologies Area, Lawrence Berkeley National LaboratoryApplied Mathematics and Computational Research Division, Computing Science Area, Lawrence Berkeley National LaboratoryAbstract We demonstrate a multi-fidelity (MF) machine learning ensemble framework for the inverse design of photonic surfaces, trained on a dataset of 11,759 samples that we fabricate using high throughput femtosecond laser processing. The MF ensemble combines an initial low fidelity model for generating design solutions, with a high fidelity model that refines these solutions through local optimization. The combined MF ensemble can generate multiple disparate sets of laser-processing parameters that can each produce the same target input spectral emissivity with high accuracy (root mean squared errors < 2%). SHapley Additive exPlanations analysis shows transparent model interpretability of the complex relationship between laser parameters and spectral emissivity. Finally, the MF ensemble is experimentally validated by fabricating and evaluating photonic surface designs that it generates for improved efficiency energy harvesting devices. Our approach provides a powerful tool for advancing the inverse design of photonic surfaces in energy harvesting applications.https://doi.org/10.1038/s41524-025-01518-4
spellingShingle Luka Grbčić
Minok Park
Mahmoud Elzouka
Ravi Prasher
Juliane Müller
Costas P. Grigoropoulos
Sean D. Lubner
Vassilia Zorba
Wibe Albert de Jong
Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
npj Computational Materials
title Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
title_full Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
title_fullStr Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
title_full_unstemmed Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
title_short Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
title_sort inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing
url https://doi.org/10.1038/s41524-025-01518-4
work_keys_str_mv AT lukagrbcic inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT minokpark inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT mahmoudelzouka inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT raviprasher inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT julianemuller inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT costaspgrigoropoulos inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT seandlubner inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT vassiliazorba inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing
AT wibealbertdejong inversedesignofphotonicsurfacesviamultifidelityensembleframeworkandfemtosecondlaserprocessing