journal article·2025-06-01Open access

Data-driven insight into propagation and bend losses in silicon nitride waveguides using classification and regression trees and design of experiments

Jakob Wilhelm Hinum-Wagner, Peter Scheibelhofer, Samuel Marko Hörmann, Christoph Schmidt, Gandolf Feigl, Jochen Kraft, Alexander Bergmann

Optical Materials Express· Volume 15· Issue 6

Abstract

Photonic integrated circuits play a pivotal role in high-speed telecommunications and sensing, yet minimizing optical losses in scalable fabrication remains a persistent challenge. This study focuses on silicon nitride waveguides and applies a full-factorial design of experiments combined with regression trees to identify the layer-specific origins of propagation and bend excess losses. Regression tree modeling revealed that waveguide width is the dominant predictor of propagation loss, followed by material composition—particularly the upper cladding at lower widths and the waveguide core material at higher widths—highlighting the confinement-dependent interplay of scattering and absorption. Bend excess loss analysis indicated a shift in dominant predictors from bend radius and width to waveguide material at smaller radii. Although these dependencies have been previously established through physical modeling and experimental studies, most prior work covers smaller datasets or relies on idealized fabrication assumptions. The results of this work establish a statistically grounded and interpretable framework for waveguide loss analysis and underscore classification and regression trees’ utility in photonic process optimization. Our approach complements existing physical frameworks by providing a statistically grounded, data-driven method to optimize SiN photonic platforms, offering predictive insight into complex layer—geometry interactions and fabrication-induced variations that are difficult to model physically. By enabling predictive insight into layer—geometry interactions, this approach paves the way for more robust photonic integrated-circuit design in sensing and next-generation optical systems.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Photonic and Optical Devices · Microwave Engineering and Waveguides · Advanced Fiber Optic Sensors

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

ams OSRAM Group

References (36)

Show source-provided references
1. Xing · ACS Photonics · 2023 · 10 · 226410.1021/acsphotonics.2c01375 ↗
2. Rizzo · Opt. Lett. · 2023 · 48 · 21510.1364/OL.476873 ↗
3. Laplatine · Sensors and Actuators B: Chemical · 2018 · 273 · 161010.1016/j.snb.2018.07.025 ↗
4. Roberts · Adv. Opt. Mater. · 2022 · 10 · 210207310.1002/adom.202102073 ↗
5. Corato-Zanarella · Opt. Express · 2024 · 32 · 571810.1364/OE.505892 ↗
6. Gao · Nat. Commun. · 2022 · 13 · 332310.1038/s41467-022-30966-5 ↗
7. Marcuse · The Bell Syst. Tech. J. · 1969 · 48 · 318710.1002/j.1538-7305.1969.tb01742.x ↗
8. Snyder · IEEE Trans. Microwave Theory Tech. · 1969 · 17 · 113010.1109/TMTT.1969.1127112 ↗
9. Payne · Opt. Quantum Electron. · 1994 · 26 · 97710.1007/BF00708339 ↗
10. Hörmann · J. Lightwave Technol. · 2023 · 41 · 150310.1109/JLT.2022.3224777 ↗
11. Pfeiffer · Optica · 2018 · 5 · 88410.1364/OPTICA.5.000884 ↗
12. Xuan · Optica · 2016 · 3 · 117110.1364/OPTICA.3.001171 ↗
13. Ji · Laser & Photonics Reviews · 2023 · 17 · 220054410.1002/lpor.202200544 ↗
14. Nevlacsil · Opt. Express · 2020 · 28 · 3246810.1364/OE.404588 ↗
15. Buchberger · IEEE Sens. J. · 2021 · 21 · 1882910.1109/JSEN.2021.3087633 ↗
16. Montgomery · 2017
17. Hammond · Opt. Express · 2019 · 27 · 2962010.1364/OE.27.029620 ↗
18. Bauters · Opt. Express · 2011 · 19 · 316310.1364/OE.19.003163 ↗
19. Liu · Nat. Commun. · 2021 · 12 · 223610.1038/s41467-021-21973-z ↗
20. Ji · Optica · 2017 · 4 · 61910.1364/OPTICA.4.000619 ↗
21. Ji · APL Photonics · 2021 · 6 · 07110110.1063/5.0057881 ↗
22. Breiman · 1984
23. Berk · 2016
24. Random forest modelling as a tool for propagation and bend excess loss minimization on silicon nitride waveguide platforms
25. Bahcecitapar · Istatistikciler Dergisi: Istatistik ve Aktuerya · 2016 · 9 · 79
26. Selvaraja · IEEE J. Select. Topics Quantum Electron. · 2010 · 16 · 31610.1109/JSTQE.2009.2026550 ↗
27. Constantoudis · J. Micro/Nanolith. MEMS MOEMS · 2009 · 8 · 04300410.1117/1.3268365 ↗
28. Fouchier · J. Micro/Nanolithogr., MEMS, MOEMS · 2013 · 12 · 04130810.1117/1.JMM.12.4.041308 ↗
29. Shapiro · Biometrika · 1965 · 52 · 59110.1093/biomet/52.3-4.591 ↗
30. Lehmann · 1998
31. Scheibelhofer · Austrian Journal of Statistics · 2012 · 41 · 161
32. 4 - sputter processing
33. Chuang · IEEE J. Quantum Electron. · 1987 · 23 · 49910.1109/JQE.1987.1073397 ↗
34. Marcuse · The Bell Syst. Tech. J. · 1970 · 49 · 27310.1002/j.1538-7305.1970.tb01769.x ↗
35. Eleftheriades · IEEE Trans. Microwave Theory Tech. · 1994 · 42 · 189610.1109/22.320771 ↗
36. CART-based optimization of core and cladding layers in silicon nitride photonic integrated circuits towards propagation and bend loss minimization