EXTRACTING A MUCH WIDER ABSORPTION SPECTRAL RANGE FROM A NARROWER RANGE USING TRANSFORMER MODEL

Abstract

Obtaining a wide absorption spectral range rapidly at high resolution plays a crucial role in scientific research and practical applications. The main motivation of this work is to investigate the rapid acquisition of a very wide spectral range at high resolution by using a much narrower absorption spectral range. To accomplish this, we proposed a novel transformer-based approach that produces a wider absorption spectral range (100 cm−1 ) with high resolution in milliseconds from a narrow absorption spectral range (2 cm−1 ). A distributed feedback quantum cascade laser (DFB QCL) together with a multi-pass cell was used to obtain the absorption lines. To evaluate the performance of the sensor, N2O was selected as the target molecule.

Keywords

• Machine Learning
• Deep Learning
• Transformer
• Lasers
• Absorption

References

1. Y. Matsuoka, et al., "External-cavity quantum cascade laser using intra-cavity out-coupling," Optics Letters 43, 3726-3729 (2018).
2. I. Bayrakli, "A portable N2O sensor based on quartz-enhanced photoacoustic spectroscopy with adistributed-feedback quantum cascade laser for medical and atmospheric applications," Optical and Quantum Electronics 53, 642 (2021).
3. I. Bayrakli, and H. Akman, "Ultrasensitive, real-time analysis of biomarkers in breath using tunable external cavity laser and off-axis cavity-enhanced absorption spectroscopy," Journal of Biomedical Optics 20, 037001 (2015).
4. I. Bayrakli, "External cavity quantum cascade lasers without anti-reflection coating with intracavity and extracavityacoustic-optic frequency shifter for fast standoff detection," Optics and Laser Technology 148, 107747 (2022).
5. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems 25 (2012).
6. J. Redmon, "You only look once: Unified, real-time object detection," In Proceedings of the IEEE conference on computer vision and pattern recognition (2016).
7. F. Hosein, and H. Abbasimehr, "A novel combined approach based on deep Autoencoder and deep classifiers for credit card fraud detection," Expert Systems with Applications 217, 119562 (2023).
8. I. Bayrakli, and E. Eken, "Compact laser spectroscopy-based sensor using a transformer-based model for analysis of multiple molecules," Applied Optics 63, 6941-6947 (2024).

9. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE 86, 2278-2324 (1998).
10. A. Vaswani, "Attention is all you need," Advances in Neural Information Processing Systems (2017).
11. D.P. Kingma, and B. Jimmy "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980 (2014).
12. T. Tieleman, "Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA:Neural networks for machine learning," 4, 2 (2012).
13. J. L. Elman, "Finding structure in time. Cognitive science," 14, 2 (1990).
14. S. Hochreiter, "Long Short-term Memory," Neural Computation MIT-Press (1997).
15. S. Hochreiter, "Long Short-term Memory," Neural Computation MIT-Press (1997).
16. J. Chung, C. Gulcehre, K. Cho, and Y. Bengio. "Empirical evaluation of gated recurrent neural networks on sequence modeling," arXiv preprint arXiv:1412.3555 (2014).
17. L. Ze, et al., "Swin transformer: Hierarchical vision transformer using shifted windows," In Proceedings of the IEEE/CVF international conference on computer vision, 10012-10022. (2021).
18. C. Nicolas, et al., "End-to-end object detection with transformers," In European conference on computer vision," Cham: Springer International Publishing, 213-229 (2020).
19. J. L. Ba, "Layer normalization," arXiv preprint arXiv:1607.06450 (2016).
20. H. Kaiming, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," In Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778 (2016).
21. Bayrakli, and E. Eken, "Compact laser spectroscopy-based sensor using a transformer-based model for analysis of multiple molecules," Applied Optics, 63, 6941-6947 (2024).
22. I. Bayrakli, and E. Eken. "A novel breath molecule sensing system based on deep neural network employing multiple-line direct absorption spectroscopy," Optics and Laser Technology 158 108918 (2023).