Data-efficient prediction of OLED optical properties enabled by transfer learning
It has long been desired to enable global structural optimization of organic light-emitting diodes (OLEDs) for maximal light extraction. The most critical obstacles to achieving this goal are time-consuming optical simulations and discrepancies between simulation and experiment. In this work, by lev...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2025-02-01
|
| Series: | Nanophotonics |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/nanoph-2024-0505 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850143129172180992 |
|---|---|
| author | Shin Jeong Min Kim Sanmun Menabde Sergey G. Park Sehong Lee In-Goo Kim Injue Jang Min Seok |
| author_facet | Shin Jeong Min Kim Sanmun Menabde Sergey G. Park Sehong Lee In-Goo Kim Injue Jang Min Seok |
| author_sort | Shin Jeong Min |
| collection | DOAJ |
| description | It has long been desired to enable global structural optimization of organic light-emitting diodes (OLEDs) for maximal light extraction. The most critical obstacles to achieving this goal are time-consuming optical simulations and discrepancies between simulation and experiment. In this work, by leveraging transfer learning, we demonstrate that fast and reliable prediction of OLED optical properties is possible with several times higher data efficiency compared to previously demonstrated surrogate solvers based on artificial neural networks. Once a neural network is trained for a base OLED structure, it can be transferred to predict the properties of modified structures with additional layers with a relatively small number of additional training samples. Moreover, we demonstrate that, with only a few tenths of experimental data sets, a neural network can be trained to accurately predict experimental measurements of OLEDs, which often differ from simulation results due to fabrication and measurement errors. This is enabled by transferring a pre-trained network, built with a large amount of simulated data, to a new network capable of correcting systematic errors in experiment. Our work proposes a practical approach to designing and optimizing OLED structures with a large number of design parameters to achieve high optical efficiency. |
| format | Article |
| id | doaj-art-030272ff84d247358f7a2e1914c72ffd |
| institution | OA Journals |
| issn | 2192-8614 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Nanophotonics |
| spelling | doaj-art-030272ff84d247358f7a2e1914c72ffd2025-08-20T02:28:49ZengDe GruyterNanophotonics2192-86142025-02-011481091109910.1515/nanoph-2024-0505Data-efficient prediction of OLED optical properties enabled by transfer learningShin Jeong Min0Kim Sanmun1Menabde Sergey G.2Park Sehong3Lee In-Goo4Kim Injue5Jang Min Seok6School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South KoreaSchool of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South KoreaSchool of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South KoreaCTO Division, LG Display Co., Seoul, 07796, Republic of KoreaCTO Division, LG Display Co., Seoul, 07796, Republic of KoreaCTO Division, LG Display Co., Seoul, 07796, Republic of KoreaSchool of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South KoreaIt has long been desired to enable global structural optimization of organic light-emitting diodes (OLEDs) for maximal light extraction. The most critical obstacles to achieving this goal are time-consuming optical simulations and discrepancies between simulation and experiment. In this work, by leveraging transfer learning, we demonstrate that fast and reliable prediction of OLED optical properties is possible with several times higher data efficiency compared to previously demonstrated surrogate solvers based on artificial neural networks. Once a neural network is trained for a base OLED structure, it can be transferred to predict the properties of modified structures with additional layers with a relatively small number of additional training samples. Moreover, we demonstrate that, with only a few tenths of experimental data sets, a neural network can be trained to accurately predict experimental measurements of OLEDs, which often differ from simulation results due to fabrication and measurement errors. This is enabled by transferring a pre-trained network, built with a large amount of simulated data, to a new network capable of correcting systematic errors in experiment. Our work proposes a practical approach to designing and optimizing OLED structures with a large number of design parameters to achieve high optical efficiency.https://doi.org/10.1515/nanoph-2024-0505organic light-emitting diodelight extraction efficiencytransfer learningmachine learning |
| spellingShingle | Shin Jeong Min Kim Sanmun Menabde Sergey G. Park Sehong Lee In-Goo Kim Injue Jang Min Seok Data-efficient prediction of OLED optical properties enabled by transfer learning Nanophotonics organic light-emitting diode light extraction efficiency transfer learning machine learning |
| title | Data-efficient prediction of OLED optical properties enabled by transfer learning |
| title_full | Data-efficient prediction of OLED optical properties enabled by transfer learning |
| title_fullStr | Data-efficient prediction of OLED optical properties enabled by transfer learning |
| title_full_unstemmed | Data-efficient prediction of OLED optical properties enabled by transfer learning |
| title_short | Data-efficient prediction of OLED optical properties enabled by transfer learning |
| title_sort | data efficient prediction of oled optical properties enabled by transfer learning |
| topic | organic light-emitting diode light extraction efficiency transfer learning machine learning |
| url | https://doi.org/10.1515/nanoph-2024-0505 |
| work_keys_str_mv | AT shinjeongmin dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning AT kimsanmun dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning AT menabdesergeyg dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning AT parksehong dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning AT leeingoo dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning AT kiminjue dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning AT jangminseok dataefficientpredictionofoledopticalpropertiesenabledbytransferlearning |