A General Neural Network Model for Complex Refractive Index Extraction of Low-Loss Materials in the Transmission-Mode THz-TDS
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
The complex refractive index for low-loss materials is conventionally extracted by either approximate analytical formula or numerical iterative algorithm (such as Nelder-Mead and Newton-Raphson) based on the transmission-mode terahertz time domain spectroscopy (THz-TDS). A novel 4-layer neural network model is proposed to obtain optical parameters of low-loss materials with high accuracy in a wide range of parameters (frequency and thickness). Three materials (TPX, z-cut crystal quartz and 6H SiC) with different dispersions and thicknesses are used to validate the robustness of the general model. Without problems of proper initial values and non-convergence, the neural network method shows even smaller errors than the iterative algorithm. Once trained and tested, the proposed method owns both high accuracy and wide generality, which will find application in the multi-class object detection and high-precision characterization of THz materials.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898
Convergence Properties of the Nelder--Mead Simplex Method in Low Dimensions
Lagarias, J. C., Reeds, J. A., Wright, M. H., & Wright, P. E. (1998) · SIAM Journal on Optimization · doi:10.1137/s1052623496303470 · Cited by 7,447
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
A reliable method for extraction of material parameters in terahertz time-domain spectroscopy
Duvillaret, L., Garet, F., & Coutaz, J.-L. (1996) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/2944.571775 · Cited by 994 · cited 1×
“Based on the Fresnel formula for materials under plane wave excitation, the simple analytical method produces approximate results of complex refractive index with fast speed, although the accuracy is low especially for the refractive index n of high-loss and high-dispersion materials [11,12].”
MethodMaterial parameter estimation with terahertz time-domain spectroscopy
Dorney, T. D., Baraniuk, R. G., & Mittleman, D. M. (2001) · Journal of the Optical Society of America A · doi:10.1364/josaa.18.001562 · Cited by 807
Terahertz Time-Domain Spectroscopy for Material Characterization
Naftaly, M., & Miles, R. E. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2007.898835 · Cited by 544
Duvillaret, L., Garet, F., & Coutaz, J.-L. (1999) · Applied Optics · doi:10.1364/ao.38.000409 · Cited by 505 · cited 1×
“Based on the Fresnel formula for materials under plane wave excitation, the simple analytical method produces approximate results of complex refractive index with fast speed, although the accuracy is low especially for the refractive index n of high-loss and high-dispersion materials [11,12].”
MethodHighly accurate optical material parameter determination with THz time-domain spectroscopy
Pupeza, I., Wilk, R., & Koch, M. (2007) · Optics Express · doi:10.1364/oe.15.004335 · Cited by 351
Fundamentals of Measurement in Terahertz Time-Domain Spectroscopy
Withayachumnankul, W., & Naftaly, M. (2014) · Journal of Infrared, Millimeter, and Terahertz Waves · doi:10.1007/s10762-013-0042-z · Cited by 288
Beard, M. C., Turner, G. M., & Schmuttenmaer, C. A. (2001) · Journal of Applied Physics · doi:10.1063/1.1416140 · Cited by 230
Low-loss polymers for terahertz applications
Podzorov, A., & Gallot, G. (2008) · Applied Optics · doi:10.1364/ao.47.003254 · Cited by 168
Dielectric constant measurement of thin films by differential time-domain spectroscopy
Jiang, Z., Li, M., & Zhang, X.-C. (2000) · Applied Physics Letters · doi:10.1063/1.126587 · Cited by 139
Optical Materials for the THz Range
Rogalin, V. E., Каплунов, И. А., & Kropotov, G. I. (2018) · Optics and Spectroscopy · doi:10.1134/s0030400x18120172 · Cited by 126
Temperature-Dependent Refractive Index of Quartz at Terahertz Frequencies
Davies, C. L., Patel, J. B., Xia, C. Q., Herz, L. M., & Johnston, M. B. (2018) · Journal of Infrared Millimeter and Terahertz Waves · doi:10.1007/s10762-018-0538-7 · Cited by 117
Phase Retrieval in Terahertz Time-Domain Measurements: a 'how to' Tutorial
Jepsen, P. U. (2019) · Journal of Infrared, Millimeter and Terahertz Waves · doi:10.1007/s10762-019-00578-0 · Cited by 114
Machine Learning Techniques for THz Imaging and Time-Domain Spectroscopy
Park, H., & Son, J.-H. (2021) · Sensors · doi:10.3390/s21041186 · Cited by 89
THz-TDS Time-Trace Analysis for the Extraction of Material and Metamaterial Parameters
Peretti, R., Mitryukovskiy, S., Froberger, K., Mebarki, M. A., Eliet, S., Vanwolleghem, M., & Lampin, J.-F. (2019) · IEEE Transactions on Terahertz Science and Technology · doi:10.1109/tthz.2018.2889227 · Cited by 78
Qualitative and Quantitative Identification of Components in Mixture by Terahertz Spectroscopy
Peng, Y., Shi, C., Xu, M., Kou, T., Wu, X., Song, B., Ma, H., Guo, S., Liu, L., & Zhu, Y. (2018) · IEEE Transactions on Terahertz Science and Technology · doi:10.1109/tthz.2018.2867816 · Cited by 61
Liu, W., Zhang, R., Ling, Y., Tang, H., She, R., Wei, G., Gong, X., & Lu, Y. (2020) · Biomedical Optics Express · doi:10.1364/boe.381623 · Cited by 47
Terahertz tag identifiable through shielding materials using machine learning
Mitsuhashi, R., Murate, K., Niijima, S., Horiuchi, T., & Kawase, K. (2020) · Optics Express · doi:10.1364/oe.384195 · Cited by 43
Tayvah, U., Spies, J. A., Neu, J., & Schmuttenmaer, C. A. (2021) · Analytical Chemistry · doi:10.1021/acs.analchem.1c02132 · Cited by 41
Tabet, M. F., & McGahan, W. A. (2000) · Thin Solid Films · doi:10.1016/s0040-6090(00)00952-4 · Cited by 40
Terahertz time-domain spectroscopy of zone-folded acoustic phonons in 4H and 6H silicon carbide
Tarekegne, A. T., Zhou, B., Kaltenecker, K., Iwaszczuk, K., Clark, S., & Jepsen, P. U. (2019) · Optics Express · doi:10.1364/oe.27.003618 · Cited by 39
Artificial neural networks for material parameter extraction in terahertz time-domain spectroscopy
Klokkou, N., Gorecki, J., Wilkinson, J. S., & Apostolopoulos, V. (2022) · Optics Express · doi:10.1364/oe.454756 · Cited by 34 · cited 2×
“than 5 and the extinction coefficient k for low-loss THz materials is normally hundreds of times smaller than n [34].”
BackgroundMethodBernier, M., Garet, F., Coutaz, J.-L., Minamide, H., & Sato, A. (2016) · IEEE Transactions on Terahertz Science and Technology · doi:10.1109/tthz.2016.2535244 · Cited by 29
Decoupling substrate thickness and refractive index measurement in THz time-domain spectroscopy
Vandrevala, F., & Einarsson, E. (2018) · Optics Express · doi:10.1364/oe.26.001697 · Cited by 24
Wu, B. Y., Cao, L., Zhang, Z., Fu, Q., & Xiong, Y. (2018) · IEEE Transactions on Terahertz Science and Technology · doi:10.1109/tthz.2018.2810018 · Cited by 23
Self-citationSoriano, A. N., Ramos, K. F. P. O., Muriel, C. A. M., Adornado, A. P., Bungay, V. C., & Li, M. (2016) · Journal of the Taiwan Institute of Chemical Engineers · doi:10.1016/j.jtice.2016.05.031 · Cited by 17
Lee, J., & Jin, J. (2022) · Scientific Reports · doi:10.1038/s41598-022-06247-y · Cited by 15
Joshi, S., & Kiani, A. (2021) · Opto-Electronic Advances · doi:10.29026/oea.2021.210039 · Cited by 14
Machine learning analysis of broadband optical reflectivity of semiconductor thin film
Lee, B., Yu, K., Jeon, J., & Choi, E. (2022) · Journal of the Korean Physical Society · doi:10.1007/s40042-022-00436-8 · Cited by 11
Şimşek, E. (2020) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ab6d5f · Cited by 10
Estimation of optical constants of thin film by the use of artificial neural networks
Ma, Y., Liu, X., Gu, P., & Tang, J. (1996) · Applied Optics · doi:10.1364/ao.35.005035 · Cited by 9
Accelerating silicon photonic parameter extraction using artificial neural networks
Hammond, A. M., Potokar, E. R., & Camacho, R. M. (2019) · OSA Continuum · doi:10.1364/osac.2.001964 · Cited by 9
Neural network approach to rapid thin film characterization
Jakatdar, N. H., Niu, X., & Spanos, C. J. (1998) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.304402 · Cited by 8
Determination of optical properties of Al80Mn20 quasi-crystalline alloy using neural networks
Bourouis, C., Meddour, A., & Moussaoui, A. (2006) · Journal of Molecular Structure THEOCHEM · doi:10.1016/j.theochem.2006.08.010 · Cited by 5
Toward estimation of refractivity index of ionic liquids and alcohols by developing an MLP-ANN
Wang, N., Yang, Z., & Li, Y. (2019) · Energy Sources Part A Recovery Utilization and Environmental Effects · doi:10.1080/15567036.2019.1648605 · Cited by 5
Cao, L., Yin, Z., & Xia, H. (2020) · Journal of the Optical Society of America B · doi:10.1364/josab.414151 · Cited by 4
Self-citationGorecki, J., & Apostolopoulos, V. (2021) · Applied Optics · doi:10.1364/ao.420987 · Cited by 3
Research works printed but not linked: 1
- Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative Adversarial Nets. Proceedings of the 28th Conference on Neural Information Processing Systems, Montreal, QC, Canada.
Cited by
Unlocking Terahertz technology with machine learning: A comprehensive review
Cacciari, I., & Ranfagni, A. (2025) · Journal of Applied Physics · doi:10.1063/5.0272428 · Cited by 20
Liao, J., Wang, B., Wang, Z., & Zhu, L. (2023) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2023.133806 · Cited by 16
Klokkou, N., Gorecki, J., Beddoes, B., & Apostolopoulos, V. (2023) · Optics Express · doi:10.1364/oe.507439 · Cited by 6
“Similarly, networks for parameter extraction have been extended to higher frequencies [22], but there has yet to be progress on creating networks that can compensate for error and variability between spectroscopists.”
Zeki Güngördü, M., Kung, P., & Kim, S. M. (2023) · Optics Express · doi:10.1364/oe.481094 · Cited by 5
Al-Ibadi, A. (2026) · Discover Applied Sciences · doi:10.1007/s42452-026-08317-6 · Cited by 1
Metadata
- Authors
- Zhou, Z., Jia, S., & Cao, L.
- Affiliations
- State Key Laboratory of Advanced Electromagnetic Engineering and Technology (CN)
- Corresponding author
- Cao, Lei
- ORCID
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2022-10-17
- Volume
- 22
- Issue
- 20
- Pages
- 7877
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9611207
- OpenAlex
- W4306403081
- Semantic Scholar
- 23d618ae660cf6eb5e862f467c68750dbaf44488
- Cited by
- 11
- References
- 41
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 2 · 2023: 3
- FWCI
- 0.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Interdisciplinary Program of Wuhan National High Magnetic Field Center (WHMFC202136)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Terahertz technology and applications
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Microwave and Dielectric Measurement Techniques
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Keywords
- low-loss materials, neural network model, TPX, Z-cut quartz, 6H-SiC, material characterization, multi-class object detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.