Pith. sign in

REVIEW 47 references

Leveraging Transfer Learning to Overcome Data Limitations in Czochralski Crystal Growth

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.18774 v1 pith:ATEXSLAI submitted 2025-06-23 cond-mat.mtrl-sci math.OC

Milena Petkovic , Natasha Dropka , Xia Tang , Janina Zittel This is my paper
classification cond-mat.mtrl-scimath.OC
keywords datalearningtransfermaterialsczochralskigrowthacrossapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The Czochralski (Cz) method is a widely used process for growing high-quality single crystals, critical for applications in semiconductors, optics, and advanced materials. Achieving optimal growth conditions requires precise control of process and furnace design parameters. Still, data scarcity -- especially for new materials -- limits the application of machine learning (ML) in predictive modeling and optimization. This study proposes a transfer learning approach to overcome this limitation by adapting ML models trained on a higher data volume of one source material (Si) to a lower data volume of another target material (Ge and GaAs). The materials were deliberately selected to assess the robustness of the transfer learning approach in handling varying data similarity, with Cz-Ge being similar to Cz-Si, and GaAs grown via the liquid encapsulated Czochralski method (LEC), which differs from Cz-Si. We explore various transfer learning strategies, including Warm Start, Merged Training, and Hyperparameters Transfer, and evaluate multiple ML architectures across two different materials. Our results demonstrate that transfer learning significantly enhances predictive accuracy with minimal data, providing a practical framework for optimizing Cz growth parameters across diverse materials.

Discussion (0). Sign in to comment.

Reference graph

Works this paper leans on

47 extracted references · 23 canonical work pages

  1. [1]

    Rudolph, T

    P. Rudolph, T. Nishinga, Handbook of Crystal Growth: Bulk Crystal Growth, Vol. 2, Elsevier, Amsterdam, The Netherlands, 2014

    2014

  2. [2]

    M \"u ller, Review: The C zochralski method—where we are 90 years after J an C zochralski's invention, Cryst

    G. M \"u ller, Review: The C zochralski method—where we are 90 years after J an C zochralski's invention, Cryst. Res. Technol. 42 (2007) 1150--1161. https://doi.org/10.1002/crat.200711047 doi:10.1002/crat.200711047

    work page doi:10.1002/crat.200711047 2007

  3. [3]

    Noghabi, M

    O. Noghabi, M. M'Hamdi, M. Jomâa, Sensitivity analyses of furnace material properties in the C zochralski crystal, Meas. Sci. Technol. 24 (2013) 015601. https://doi.org/10.1088/0957-0233/24/1/015601 doi:10.1088/0957-0233/24/1/015601

    work page doi:10.1088/0957-0233/24/1/015601 2013

  4. [4]

    J. Ding, L. Liu, Real-time prediction of crystal/melt interface shape during C zochralski crystal growth, Cryst. Eng. Comm. 20 (2018) 6925--6931. https://doi.org/10.1039/C8CE00966A doi:10.1039/C8CE00966A

    work page doi:10.1039/c8ce00966a 2018

  5. [5]

    Mosel, A

    F. Mosel, A. Denisov, B. Klipp, N. Sennova, C. Kranert, T. Jung, M. Trempa, C. Reimann, J. Friedrich, Limitations of the growth rate of silicon mono ingots grown by the C zochralski technique, in: Proc. EU PVSEC, 2020, pp. 468--473. https://doi.org/10.4229/EUPVSEC20202020-2DV.2.18 doi:10.4229/EUPVSEC20202020-2DV.2.18

    work page doi:10.4229/eupvsec20202020-2dv.2.18 2020

  6. [6]

    Friedrich, W

    J. Friedrich, W. von Ammon, G. Müller, 2 - czochralski growth of silicon crystals, in: P. Rudolph (Ed.), Handbook of Crystal Growth (Second Edition), Elsevier, 2015, pp. 45--104

    2015

  7. [7]

    Depuydt, A

    B. Depuydt, A. Theuwis, I. Romandic, Germanium: From the first application of czochralski crystal growth to large diameter dislocation-free wafers, Materials Science in Semiconductor Processing 9 (4) (2006) 437--443, proceedings of Symposium T E-MRS 2006 Spring Meeting on Germanium based semiconductors from materials to devices. https://doi.org/https://do...

    work page doi:10.1016/j.mssp.2006.08.002 2006

  8. [8]

    Sarukura, T

    N. Sarukura, T. Nawata, H. Ishibashi, M. Ishii, T. Fukuda, 4 - czochralski growth of oxides and fluorides, in: P. Rudolph (Ed.), Handbook of Crystal Growth (Second Edition), Elsevier, 2015, pp. 131--168

    2015

Show all 47 references
  1. [9]

    Böttcher, P

    K. Böttcher, P. Rudolph, M. Neubert, M. Kurz, A. Pusztai, G. Müller, Global temperature field simulation of the vapour pressure controlled C zochralski (vcz) growth of 3”–4” gallium arsenide crystals, J. Cryst. Growth 198 (1999) 349--354. https://doi.org/10.1016/S0022-0248(98)...

    1999 doi

  2. [10]

    X. Qi, W. Ma, Y. Dang, W. Su, L. Liu, Optimization of the melt/crystal interface shape and oxygen concentration during the Czochralski silicon crystal growth process using an artificial neural network and a genetic algorithm, J. Cryst. Growth 548 (2020) 125828. https://doi.org...

    2020

  3. [11]

    Kutsukake, Y

    K. Kutsukake, Y. Nagai, T. Horikawa, H. Banba, Real-time prediction of interstitial oxygen concentration in Czochralski silicon using machine learning, Appl. Phys. Express 13 (2020) 125502. https://doi.org/10.35848/1882-0786/aba4d3 doi:10.35848/1882-0786/aba4d3

    2020 doi

  4. [12]

    Dropka, K

    N. Dropka, K. Böttcher, M. Holena, Development and optimization of VGF-GaAs crystal growth process using data mining and machine learning techniques, Crystals 11 (2021) 1218. https://doi.org/10.3390/cryst11101218 doi:10.3390/cryst11101218

    2021 doi

  5. [13]

    W. Yu, C. Zhu, Y. Tsunooka, W. Huang, Y. Dang, K. Kutsukake, S. Harada, M. Tagawa, T. Ujihara, Geometrical design of a crystal growth system guided by a machine learning algorithm, Cryst. Eng. Comm. 23 (2021) 2695--2702. https://doi.org/10.1039/D1CE00089E doi:10.1039/D1CE00089E

    2021 doi

  6. [14]

    Dropka, X

    N. Dropka, X. Tang, G. K. Chappa, M. Holena, Smart design of cz-ge crystal growth furnace and process, Crystals 12 (12) (2022). https://doi.org/10.3390/cryst12121764 doi:10.3390/cryst12121764

    2022 doi

  7. [15]

    Vieira, R

    L. Vieira, R. Menzel, M. Holena, N. Dropka, An analysis of elusive relationships in floating zone growth using data mining techniques, Advanced Theory and Simulations (2025) 2400781 https://doi.org/https://doi.org/10.1002/adts.202400781 doi:https://doi.org/10.1002/adts.202400781

    2025 doi

  8. [16]

    Y. Dang, K. Kutsukake, X. Liu, Y. Inoue, X. Liu, S. Seki, C. Zhu, S. Harada, M. Tagawa, T. Ujihara, A transfer learning-based method for facilitating the prediction of unsteady crystal growth, Advanced Theory and Simulations 5 (9) (2022) 2200204. https://doi.org/https://doi.or...

    2022 doi

  9. [17]

    Frank-Rotsch, N

    C. Frank-Rotsch, N. Dropka, P. Rotsch, Chapter 6: Iii-arsenides, in: R. Fornari (Ed.), Single Crystals of Electronic Materials: Growth and Properties, Woodhead Publishing, Elsevier, 2018, pp. 181--240. https://doi.org/https://doi.org/10.1016/B978-0-08-102096-8.00006-9 doi:http...

    2018 doi

  10. [18]

    J. B. Mullin, 3 - liquid encapsulation and related technologies for the czochralski growth of semiconductor compounds, in: P. Rudolph (Ed.), Handbook of Crystal Growth (Second Edition), Elsevier, 2015, pp. 105--130

    2015

  11. [19]

    Dropka, K

    N. Dropka, K. Böttcher, G. K. Chappa, M. Holena, Data-driven cz–si scale-up under conditions of partial similarity, Crystal Research and Technology 59 (6) (2024) 2300342. https://doi.org/https://doi.org/10.1002/crat.202300342 doi:https://doi.org/10.1002/crat.202300342

    2024 doi

  12. [20]

    Petkovic, N

    M. Petkovic, N. Dropka, Symo: A hybrid approach for multi-objective optimization of crystal growth processes, Advanced Theory and Simulations (2025) 2401361 https://doi.org/https://doi.org/10.1002/adts.202401361 doi:https://doi.org/10.1002/adts.202401361

    2025 doi

  13. [21]

    V. V. Voronkov, The mechanism of swirl defects formation in silicon, J. Cryst. Growth 59 (1982) 625--643. https://doi.org/10.1016/0022-0248(82)90370-3 doi:10.1016/0022-0248(82)90370-3

    1982 doi

  14. [22]

    V. V. Voronkov, R. Falster, Vacancy and self-interstitial concentration incorporated into growing silicon crystals , Journal of Applied Physics 86 (11) (1999) 5975--5982. https://doi.org/10.1063/1.371642 doi:10.1063/1.371642

    1999 doi

  15. [23]

    Kakimoto, B

    K. Kakimoto, B. Gao, Fluid dynamics: Modeling and analysis, in: P. Rudolph (Ed.), Handbook of Crystal Growth, Elsevier, Amsterdam, The Netherlands, 2015, pp. 845--870

    2015

  16. [24]

    Rudolph, Transport phenomena of crystal growth—heat and mass transfer, AIP Conference Proceedings 1270 (1) (2010) 107--132

    P. Rudolph, Transport phenomena of crystal growth—heat and mass transfer, AIP Conference Proceedings 1270 (1) (2010) 107--132. https://doi.org/10.1063/1.3476222 doi:10.1063/1.3476222

    2010 doi

  17. [25]

    ://str-soft.com/software/cgsim/

    STR Group , https://str-soft.com/software/cgsim/ SGSim (2024). ://str-soft.com/software/cgsim/

    2024

  18. [26]

    T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16, Association for Computing Machinery, New York, NY, USA, 2016, p. 785–794. https://doi.org/10.1145/29...

    2016

  19. [27]

    G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, T.-Y. Liu, Lightgbm: A highly efficient gradient boosting decision tree, in: Neural Information Processing Systems, 2017

    2017

  20. [28]

    Haykin, Neural networks: a comprehensive foundation, Prentice Hall PTR, 1994

    S. Haykin, Neural networks: a comprehensive foundation, Prentice Hall PTR, 1994

    1994

  21. [29]

    Deng, X.-Q

    Y.-H. Deng, X.-Q. Luo, P. Yan, N.-Y. Zhang, Y. Liu, S.-B. Duan, Outcome prediction for acute kidney injury among hospitalized children via extreme gradient boosting algorithm, Scientific Reports (2022). https://doi.org/10.1038/s41598-022-13152-x doi:10.1038/s41598-022-13152-x

    2022 doi

  22. [30]

    H. Zeng, Y. Chen, H. Zhang, Z. Wu, J. Zhang, G. Dai, F. Babiloni, W. Kong, A lightgbm-based eeg analysis method for driver mental states classification, Computational Intelligence and Neuroscience (2019). https://doi.org/10.1155/2019/3761203 doi:10.1155/2019/3761203

    2019 doi

  23. [31]

    López-Zorrilla, X

    J. López-Zorrilla, X. M. Aretxabaleta, H. Manzano, Exploring the polymorphism of dicalcium silicates using transfer learning enhanced machine learning atomic potentials, Journal of Chemical Theory and Computation (2024). https://doi.org/10.1021/acs.jctc.4c00479 doi:10.1021/acs...

    2024 doi

  24. [32]

    Shahriari, A

    B. Shahriari, A. Bouchard-Cote, N. Freitas, Unbounded bayesian optimization via regularization, in: A. Gretton, C. C. Robert (Eds.), Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, Vol. 51 of Proceedings of Machine Learning Research,...

    2016

  25. [33]

    Snoek, H

    J. Snoek, H. Larochelle, R. P. Adams, Practical bayesian optimization of machine learning algorithms, in: F. Pereira, C. Burges, L. Bottou, K. Weinberger (Eds.), Advances in Neural Information Processing Systems, Vol. 25, Curran Associates, Inc., 2012

    2012

  26. [34]

    Prechelt, Early Stopping - But When?, Springer Berlin Heidelberg, Berlin, Heidelberg, 1998, pp

    L. Prechelt, Early Stopping - But When?, Springer Berlin Heidelberg, Berlin, Heidelberg, 1998, pp. 55--69. https://doi.org/10.1007/3-540-49430-8_3 doi:10.1007/3-540-49430-8_3

    1998 doi

  27. [35]

    S. J. Pan, Q. Yang, A survey on transfer learning https://api.semanticscholar.org/CorpusID:740063, IEEE Transactions on Knowledge and Data Engineering 22 (2010) 1345--1359. ://api.semanticscholar.org/CorpusID:740063

    2010

  28. [36]

    Weiss, T

    K. Weiss, T. M. Khoshgoftaar, D. Wang, A survey of transfer learning https://doi.org/10.1186/s40537-016-0043-6, Journal of Big Data 3 (9) (2016). https://doi.org/10.1186/s40537-016-0043-6 doi:10.1186/s40537-016-0043-6 . ://doi.org/10.1186/s40537-016-0043-6

    2016 doi

  29. [37]

    Kornblith, J

    S. Kornblith, J. Shlens, Q. V. Le, https://doi.ieeecomputersociety.org/10.1109/CVPR.2019.00277 Do Better ImageNet Models Transfer Better? , in: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2019, pp. 2...

    2019

  30. [38]

    M. Gao, U. Bağcı, L. Lü, A. Wu, M. Buty, H.-C. Shin, H. R. Roth, G. Z. Papadakis, A. Depeursinge, R. M. Summers, Z. Xu, D. J. Mollura, Holistic classification of ct attenuation patterns for interstitial lung diseases via deep convolutional neural networks, Computer Methods in ...

    2016

  31. [39]

    Y. Guo, H. Shi, A. Kumar, K. Grauman, T. Rosing, R. Feris, Spottune: Transfer learning through adaptive fine-tuning (2019). https://doi.org/10.1109/cvpr.2019.00494 doi:10.1109/cvpr.2019.00494

    2019

  32. [40]

    Y. Guo, Y. Li, L. Wang, T. Rosing, Adafilter: Adaptive filter fine-tuning for deep transfer learning, Proceedings of the Aaai Conference on Artificial Intelligence (2020). https://doi.org/10.1609/aaai.v34i04.5824 doi:10.1609/aaai.v34i04.5824

    2020 doi

  33. [41]

    Z. Hong, Z. Fan, X. Tong, R. Zhou, H. Pan, Y. Zhang, Y. Han, J. Wang, S. Yang, H. Wu, J. Li, Prediction of covid-19 epidemic situation via fine-tuned indrnn, Peerj Computer Science (2021). https://doi.org/10.7717/peerj-cs.770 doi:10.7717/peerj-cs.770

    2021 doi

  34. [42]

    X. Dong, A. T. Luu, M. Lin, S. Yan, H. Zhang, How should pre-trained language models be fine-tuned towards adversarial robustness? (2021). https://doi.org/10.48550/arxiv.2112.11668 doi:10.48550/arxiv.2112.11668

    2021 doi arXiv

  35. [43]

    Tajbakhsh, J

    N. Tajbakhsh, J. Y. Shin, S. R. Gurudu, R. T. Hurst, C. B. Kendall, M. B. Gotway, J. Liang, Convolutional neural networks for medical image analysis: Full training or fine tuning?, Ieee Transactions on Medical Imaging (2016). https://doi.org/10.1109/tmi.2016.2535302 doi:10.110...

    2016

  36. [44]

    Goodfellow, Y

    I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016, http://www.deeplearningbook.org

    2016

  37. [45]

    Hofmann, B

    T. Hofmann, B. Sch \"o lkopf, A. J. Smola, Kernel methods in machine learning , The Annals of Statistics 36 (3) (2008) 1171 -- 1220. https://doi.org/10.1214/009053607000000677 doi:10.1214/009053607000000677

    2008 doi

  38. [46]

    , " * write output.state after.block =

    ENTRY address author booktitle chapter edition editor eid howpublished institution isbn issn journal key month note number organization pages publisher school series title type url volume year label INTEGERS output.state before.all mid.sentence after.sentence after.block FUNCT...

  39. [47]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 gl...

Pith tools