A Machine Learning Specklegram Wavemeter (MaSWave) Based on a Short Section of Multimode Fiber as the Dispersive Element

Aug 5, 2026

Wavemeters are essential for precise measurements of optical pulses and continuous-wave sources, traditionally relying on gratings, prisms, or other wavelength-sensitive optics. This work presents a low-cost wavemeter using a short section of multimode fiber (MMF) as the dispersive element. Multimodal interference at the MMF end face produces specklegrams that are captured by a CCD camera and analyzed with a convolutional neural network (CNN) to map wavelength changes with up to 1 pm resolution, trained across multiple image categories and MMF types. It also examines robustness trade-offs against vibration and temperature effects.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Optical sensing and wavelength measurement needs

Conventional wavemeter technologies and limitations

Proposed approach (MaSWave)

Multimode fiber specklegram generation and sensing setup

CNN-based wavelength mapping

Experimental setup and results

Resolution with different MMF lengths

Training across wavelength shifts and MMF types

Discussion

Environmental robustness vs. resolution trade-off

Conclusion

Missouri University of Science and Technology Scholars' Mine | Electrical and Computer Engineering Faculty Research & Creative Works | Electrical and Computer Engineering | | --- | --- | | 01 May 2023
A Machine Learning Specklegram Wavemeter (MaSWave) Based On A Short Section Of Multimode Fiber As The Dispersive Element Ogbole C. Inalegwu
Rex E. Gerald
Missouri University of Science and Technology, [geraldr@mst.edu](geraldr@mst.edu)
Jie Huang
Missouri University of Science and Technology, [jieh@mst.edu](jieh@mst.edu)
Follow this and additional works at: [https://scholarsmine.mst.edu/ele_comeng_facwork](https://scholarsmine.mst.edu/ele_comeng_facwork)
Part of the Electrical and Computer Engineering Commons | | Recommended Citation O. C. Inalegwu et al., "A Machine Learning Specklegram Wavemeter (MaSWave) Based On A Short Section Of Multimode Fiber As The Dispersive Element," Sensors, vol. 23, no. 10, article no. 4574, MDPI, May 2023. The definitive version is available at [https://doi.org/10.3390/s23104574](https://doi.org/10.3390/s23104574) This work is licensed under a Creative Commons Attribution 4.0 License. This Article-Journal is brought to you for free and open access by Scholars' Mine. It has been accepted for inclusion in Electrical and Computer Engineering Faculty Research & Creative Works by an authorized administrator of Scholars' Mine. This work is protected by U. S. Copyright Law. Unauthorized use including reproduction for redistribution requires the permission of the copyright holder. For more information, please contact [scholarsmine@mst.edu](scholarsmine@mst.edu). sensors Article A Machine Learning Specklegram Wavemeter (MaSWave) Based on a Short Section of Multimode Fiber as the Dispersive Element Ogbole C. Inalegwu *, Rex E. Gerald II and Jie Huang * Citation: Inalegwu, O.C.; II, R.E.G.; Huang, J. A Machine Learning Specklegram Wavemeter (MaSWave) Based on a Short Section of Multimode Fiber as the Dispersive Element. Sensors 2023, 23, 4574 . [https://doi.org/10.3390/s23104574](https://doi.org/10.3390/s23104574) Academic Editor: Jesper Skottfelt Received: 6 March 2023 Revised: 25 April 2023 Accepted: 3 May 2023 Published: 9 May 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409-0040, USA * Correspondence: [ocigwk@mst.edu](ocigwk@mst.edu) (O.C.I.); [jieh@mst.edu](jieh@mst.edu) (J.H.) Abstract: Wavemeters are very important for precise and accurate measurements of both pulses and continuous-wave optical sources. Conventional wavemeters employ gratings, prisms, and other wavelength-sensitive devices in their design. Here, we report a simple and low-cost wavemeter based on a section of multimode ﬁber (MMF) . The concept is to correlate the multimodal interference pattern (i.e., speckle patterns or specklegrams) at the end face of an MMF with the wavelength of the input light source. Through a series of experiments, specklegrams from the end face of an MMF as captured by a CCD camera (acting as a low-cost interrogation unit) were analyzed using a convolutional neural network (CNN) model. The developed machine learning specklegram wavemeter (MaSWave) can accurately map specklegrams of wavelengths up to 1 pm resolution when employing a 0.1 m long MMF. Moreover, the CNN was trained with several categories of image datasets (from 10 nm to 1 pm wavelength shifts) . In addition, analysis for different step-index and graded-index MMF types was carried out. The work shows how further robustness to the effects of environmental changes (mainl

FAQs

What is the MaSWave concept for measuring wavelength?

MaSWave uses the multimodal interference pattern (specklegrams) formed at the end face of a short multimode fiber. A CCD camera captures the specklegram, and a CNN maps it to the input light wavelength.

How accurate is the machine learning specklegram wavemeter?

The system can map specklegrams to wavelength with up to 1 pm resolution when using a 0.1 m long MMF section.

How do vibrations and temperature changes affect the system?

Robustness to environmental changes can be improved by using a shorter MMF length (e.g., 0.02 m). This increases robustness but reduces the wavelength shift resolution.

Aug 5, 2026

Upload by Lucas Martin