Deep-learning approach for predicting crystalline phase distribution of femtosecond laser-processed silicon
Source abstract
Abstract
In this study, two deep-learning models are presented to predict the crystalline phases of femtosecond laser-processed silicon. To obtain the datasets, single-crystal silicon was processed by a femtosecond laser using 49 different combinations of laser fluence and scanning speed, and for each specimen, Raman spectra were measured at 22,500 locations inside a square domain. The first model was trained to classify the Raman spectra of silicon into six silicon phases. By applying the model to the entire surface of a silicon specimen in batches, the silicon phase distribution was visualized in RGB color values, with each color representing a particular silicon phase. Using the classification results of the 49 specimens obtained by the first model, the second model was developed to predict the silicon phase distribution image from the inputs of the laser fluence and scanning speed. The average prediction accuracy of the second model was 86.60%.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Laser Material Processing Techniques · Thermography and Photoacoustic Techniques · Advanced Surface Polishing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Ultrafast laser-induced crystallization of amorphous silicon films10.1117/1.1617312 ↗
2. Near-infrared femtosecond laser crystallized poly-Si thin film transistors10.1364/OE.15.006982 ↗
3. Ultra fast melting process in femtosecond laser crystallization of thin a-Si layer10.1016/j.apsusc.2009.04.067 ↗
4. Femtosecond laser ablation of silicon-modification thresholds and morphology10.1007/s003390100893 ↗
5. Modifying single-crystalline silicon by femtosecond laser pulses: an analysis by micro Raman spectroscopy, scanning laser microscopy and atomic force microscopy10.1016/S0169-4332(03)00881-X ↗
6. Sub-damage-threshold femtosecond laser ablation from crystalline Si: surface nanostructures and phase transformation10.1007/s00339-004-2803-y ↗
7. Thermal melting and ablation of silicon by femtosecond laser radiation10.1134/S106377611302012X ↗
8. Femtosecond laser-induced damage morphologies of crystalline silicon by sub-threshold pulses10.1016/j.optlaseng.2004.10.006 ↗
9. Polarization effects in femtosecond laser induced amorphization of monocrystalline silicon10.1016/j.cplett.2016.08.080 ↗
10. Numerical simulation of femtosecond laser interaction with silicon10.2351/1.1848529 ↗
11. Effect of ionization on the femtosecond laser pulse interaction with silicon10.1063/1.2388853 ↗
12. Topic Review: Application of Raman Spectroscopy Characterization in Micro/Nano-Machining
13. Deep learning-based component identification for the Raman spectra of mixtures10.1039/C8AN02212G ↗
14. Deep convolutional neural networks for Raman spectrum recognition: a unified solution10.1039/C7AN01371J ↗
15. Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning10.1038/s41467-019-12898-9 ↗
16. Rapid diagnosis of lung cancer and glioma based on serum Raman spectroscopy combined with deep learning10.1002/jrs.6224 ↗
17. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
18. M. Mirza, S. Osindero, Conditional generative adversarial nets, arXiv preprint arXiv:1411.1784 (2014).
19. A. Radford, L. Metz, S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv preprint arXiv:1511.06434 (2015).
20. Experimental determination of the nanocrystalline volume fraction in silicon thin films from Raman spectroscopy10.1063/1.99054 ↗
21. Raman scattering of light in silicon nanostructures: First-and second-order spectra10.1134/1.1999895 ↗
22. Raman scattering study of ion implanted and CW-Laser annealed polycrystalline silicon10.1016/0038-1098(81)90825-5 ↗
23. Crystallization processes of amorphous Si by thermal annealing and pulsed laser processing
24. Denoising of spectra with no user input: a spline-smoothing algorithm10.1002/jrs.2692 ↗
25. Smoothing Raman spectra with contiguous single-channel fitting of Voigt distributions: an automated, high-quality procedure
26. Schubert · 2006
27. Micro-Raman spectroscopy characterization of silicon with different structures irradiated with energetic Bi-ions10.1016/j.nimb.2015.08.041 ↗
28. In situ plasma monitoring of PECVD nc-Si: H films and the influence of dilution ratio on structural evolution10.3390/coatings8070238 ↗
29. A. Jadhavar, A. Pawbake, R. Waykar, V. Jadkar, R. Kulkarni, A. Bhorde, S. Rondiya, A. Funde, D. Patil, A. Date, Growth of hydrogenated nano-crystalline silicon (nc-Si: H) films by plasma enhanced chemical vapor deposition (PE-CVD), Energy Procedia 110 (2017) 45-52.10.1016/j.egypro.2017.03.104 ↗
30. T. Deschaines, J. Hodkiewicz, P. Henson, Characterization of amorphous and microcrystalline silicon using Raman spectroscopy, (2009).
31. Nondestructive measurement of machining-induced amorphous layers in single-crystal silicon by laser micro-Raman spectroscopy10.1016/j.precisioneng.2007.08.006 ↗
32. Y. Xu, X. Qiu, L. Zhou, X. Huang, Improving bert fine-tuning via self-ensemble and self-distillation, arXiv preprint arXiv:2002.10345 (2020).
33. W. Tang, G. Long, L. Liu, T. Zhou, J. Jiang, M. Blumenstein, Rethinking 1d-cnn for time series classification: A stronger baseline, arXiv preprint arXiv:2002.10061 (2020).
34. W. Tang, G. Long, L. Liu, T. Zhou, M. Blumenstein, J. Jiang, Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification, International Conference on Learning Representations, 2021.
35. S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, International conference on machine learning, PMLR, 2015, pp. 448-456.
36. A.L. Maas, A.Y. Hannun, A.Y. Ng, Rectifier nonlinearities improve neural network acoustic models, Proc. icml, Citeseer, 2013, p. 3.
37. M.D. Zeiler, D. Krishnan, G.W. Taylor, R. Fergus, Deconvolutional networks, 2010 IEEE Computer Society Conference on computer vision and pattern recognition, IEEE, 2010, pp. 2528-2535.10.1109/CVPR.2010.5539957 ↗
38. K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.10.1109/CVPR.2016.90 ↗
39. T. Miyato, T. Kataoka, M. Koyama, Y. Yoshida, Spectral normalization for generative adversarial networks, arXiv preprint arXiv:1802.05957 (2018).
40. Sparse feature learning for deep belief networks
41. S. Dutta, Z. Bai, H. Jeong, T.M. Low, P. Grover, A unified coded deep neural network training strategy based on generalized polydot codes, 2018 IEEE International Symposium on Information Theory (ISIT), IEEE, 2018, pp. 1585-1589.10.1109/ISIT.2018.8437852 ↗
42. T.-C. Wang, M.-Y. Liu, J.-Y. Zhu, A. Tao, J. Kautz, B. Catanzaro, High-resolution image synthesis and semantic manipulation with conditional gans, Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8798-8807.10.1109/CVPR.2018.00917 ↗
43. P. Isola, J.-Y. Zhu, T. Zhou, A.A. Efros, Image-to-image translation with conditional adversarial networks, Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1125-1134.10.1109/CVPR.2017.632 ↗
44. Determining the material structure of microcrystalline silicon from Raman spectra10.1063/1.1596364 ↗
45. A. Rode, L. Rapp, T. Matsuoka, K. Firestein, D. Sagae, H. Habara, K. Mukai, K. Tanaka, E. Gamaly, R. Kodama, Y. Seto, T. Shobu, A. Tominaga, L. Smillie, T. Pikuz, B. Haberl, T. Yabuuchi, T.T.T. Togashi, Y. Inubushi, M. Yabashi, S. Juodkazis, D. Golberg, N. Ozaki, High-pressure polymorphs in bulk silicon formed at relativistic laser intensity, (2022).10.21203/rs.3.rs-2060424/v1 ↗