Artificial neural networks for material parameter extraction in terahertz time-domain spectroscopy
Artificial neural networks for material parameter extraction in terahertz time-domain spectroscopy
Terahertz time-domain spectroscopy (THz-TDS) is a proven technique whereby the complex refractive indices of materials can be obtained without requiring the use of the Kramers-Kronig relations, as phase and amplitude information can be extracted from the measurement. However, manual pre-processing of the data is still required and the material parameters require iterative fitting, resulting in complexity, loss of accuracy and inconsistencies between measurements. Alternatively approximations can be used to enable analytical extraction but with a considerable sacrifice of accuracy. We investigate the use of machine learning techniques for interpreting spectroscopic THz-TDS data by training with large data sets of simulated light-matter interactions, resulting in a computationally efficient artificial neural network for material parameter extraction. The trained model improves on the accuracy of analytical methods that need approximations while being easier to implement and faster to run than iterative root-finding methods. We envisage neural networks can alleviate many of the common hurdles involved in analyzing THz-TDS data such as phase unwrapping, time domain windowing, slow computation times, and extraction accuracy at the low frequency range.
15583-15595
Klokkou, Nicholas
28e68acd-c66f-495f-87f3-91235fe03503
Gorecki, Jon
6f68dd34-2d89-4063-baf6-8bb6cf8ccfe8
Wilkinson, James S.
73483cf3-d9f2-4688-9b09-1c84257884ca
Apostolopoulos, Vasilis
8a898740-4c71-4040-a577-9b9d70530b4d
25 April 2022
Klokkou, Nicholas
28e68acd-c66f-495f-87f3-91235fe03503
Gorecki, Jon
6f68dd34-2d89-4063-baf6-8bb6cf8ccfe8
Wilkinson, James S.
73483cf3-d9f2-4688-9b09-1c84257884ca
Apostolopoulos, Vasilis
8a898740-4c71-4040-a577-9b9d70530b4d
Klokkou, Nicholas, Gorecki, Jon, Wilkinson, James S. and Apostolopoulos, Vasilis
(2022)
Artificial neural networks for material parameter extraction in terahertz time-domain spectroscopy.
Optics Express, 30 (9), .
(doi:10.1364/OE.454756).
Abstract
Terahertz time-domain spectroscopy (THz-TDS) is a proven technique whereby the complex refractive indices of materials can be obtained without requiring the use of the Kramers-Kronig relations, as phase and amplitude information can be extracted from the measurement. However, manual pre-processing of the data is still required and the material parameters require iterative fitting, resulting in complexity, loss of accuracy and inconsistencies between measurements. Alternatively approximations can be used to enable analytical extraction but with a considerable sacrifice of accuracy. We investigate the use of machine learning techniques for interpreting spectroscopic THz-TDS data by training with large data sets of simulated light-matter interactions, resulting in a computationally efficient artificial neural network for material parameter extraction. The trained model improves on the accuracy of analytical methods that need approximations while being easier to implement and faster to run than iterative root-finding methods. We envisage neural networks can alleviate many of the common hurdles involved in analyzing THz-TDS data such as phase unwrapping, time domain windowing, slow computation times, and extraction accuracy at the low frequency range.
This record has no associated files available for download.
More information
Published date: 25 April 2022
Additional Information:
Funding Information:
Engineering and Physical Sciences Research Council (EP/N509747/1).
Publisher Copyright:
© 2022 OSA - The Optical Society. All rights reserved.
Identifiers
Local EPrints ID: 468133
URI: http://eprints.soton.ac.uk/id/eprint/468133
ISSN: 1094-4087
PURE UUID: 19dabd9f-d535-442f-8ba4-0e22b8a65967
Catalogue record
Date deposited: 03 Aug 2022 16:44
Last modified: 18 Mar 2024 04:05
Export record
Altmetrics
Contributors
Author:
Jon Gorecki
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics