Augmented Bayesian Data Selection: Improving Machine Learning Predictions of Bragg Grating Spectra
Open Access
Abstract
Bragg gratings are fundamental components in a wide range of sensing applications due to their high sensitivity and tunability. In this work, we present an augmented Bayesian approach for efficiently acquiring limited but highly informative training data for machine learning models in the design and simulation of Bragg grating sensors. Our method integrates a distance-based diversity criterion with Bayesian optimization to identify and prioritize the most informative design points. Specifically, when multiple candidates exhibit similar acquisition values, the algorithm selects the point that is farthest from the existing dataset to enhance diversity and coverage. We apply this strategy to the Bragg grating design space, where various analytical functions are fitted to the optical response. To assess the influence of output complexity on model performance, we compare different fit functions, including polynomial models of varying orders and Gaussian functions. Results demonstrate that emphasizing output diversity during the initial stages of data acquisition significantly improves performance, especially for complex optical responses. This approach offers a scalable and efficient framework for generating high-quality simulation data in data-scarce scenarios, with direct implications for the design and optimization of next-generation Bragg grating-based sensors.Keywords
Funding Information
- Bundesministerium für Forschung, Technologie und Raumfahrt (13N14906, 50WM2152, 50WK2272)
- Bundesministerium für Wirtschaft und Energie (13N14906, 50WM2152, 50WK2272)
This publication has 58 references indexed in Scilit:
- Frequency-stabilized and high-efficiency Brillouin random fiber laser based on a fiber Bragg grating ringInfrared Physics & Technology, 2025
- Inverse Design of Photonic SystemsLaser & Photonics Reviews, 2024
- Feature selection techniques for machine learning: a survey of more than two decades of researchKnowledge and Information Systems, 2023
- Demonstration of a fast-training feed-forward machine learning algorithm for studying key optical properties of FBG and predicting precisely the output spectrumOptical and Quantum Electronics, 2022
- Tackling Photonic Inverse Design with Machine LearningAdvanced Science, 2021
- Generative Deep Learning Model for Inverse Design of Integrated Nanophotonic DevicesLaser & Photonics Reviews, 2020
- Predicting Missing Values in Medical Data Via XGBoost RegressionJournal of Healthcare Informatics Research, 2020
- Diode Lasers and Photonic Integrated Circuits2012
- Chirped Fiber Bragg Gratings2010
- Nonlinear Fiber Optics2007