کاربرد روش‌های یادگیری ماشین برای بهینه‌سازی پارامترهای سنتز ذرات نقاط کوانتومی GaN قابل کاربرد در آشکارساز‌های نوری فرابنفش

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه فیزیک، دانشکده علوم پایه، دانشگاه علوم و فنون هوایی شهید ستاری، تهران، ایران.

2 گروه فیزیک،دانشکده ی علوم پایه، دانشگاه علوم و فنون هوایی شهید ستاری، تهران، ایران.

چکیده
آشکارسازی صحیح نور فرابنفش (UV) یک مسئله‌ی مهم در توسعه‌ی فناوری‌های نوری-الکترونیکی به‌شمار می‌رود. مواد نیمه‌هادی مرسوم که به‌طور معمول در ساخت آشکارسازهای نوری فرابنفش به‌کار برده می‌شوند دارای محدودیت‌هایی به‌لحاظ سرعت پاسخ، هزینه و پیچیدگی‌های ساخت می‌باشند. این در حالی است که آشکارسازهای نوری فرابنفش مبتنی‌بر ذرات نقاط کوانتومی (QDs) به‌دلیل ویژگی‌های نوری و الکترونیکی منحصر‌به‌فرد می‌توانند بر این محدودیت‌ها غلبه کنند. با این حال، سنتز این نانوذرات به‌طور معمول مبتنی‌بر رویکردهای آزمون و خطا می‌باشد. در این پژوهش، با استفاده از مدل های یادگیری ماشین و اطلاعات استخراج شده از مقالات علمی به بررسی و پیش‌بینی مهم‌ترین متغیرهای تاثیرگذار بر سنتز GaN QDs قابل کاربرد در ساخت آشکارسازهای نوری فرابنفش پرداخته شده است. نتایج بدست آمده از الگوریتم‌ AdaBoost نشان می‌دهد که متغیرهای نسبت مولی Ga/N، نسبت شار آلومینیوم به فلز، زمان و دمای رشد، مهم ترین متغیرهای موثر بر پهنای باند GaN QDs به‌شمار می روند. هم‌چنین، الگوریتم AdaBoost برای پیش بینی مقادیر بهینه‌ی متغیرهای کلیدی واکنش در دامنه های دلخواه از پهنای باندGaN QDs به‌کار برده شده است.

کلیدواژه‌ها

موضوعات


عنوان مقاله English

Application of Machine Learning Techniques for the Optimization of Synthesis Parameters of GaN Quantum Dots for Utilization in Ultraviolet Photodetectors

نویسندگان English

Bahram Abedi Ravan 1
Bahram Daalwand 2
1 Faculty of Basic Science, Shahid Sattari University of Aeronautical Sciences and Technology, Tehran, Iran.
2 Faculty of Basic Science, Shahid Sattari University of Aeronautical Sciences and Technology, Tehran, Iran.
چکیده English

Accurate ultraviolet (UV) photodetection is a critical issue in the development of optoelectronic technologies. Conventional semiconductor materials commonly used in UV photodetectors suffer from limitations in terms of response speed, cost, and fabrication complexity. In contrast, UV photodetectors based on quantum dots (QDs), owing to their unique optical and electronic properties, can potentially overcome these limitations. Nevertheless, the synthesis of these nanoparticles is typically based on trial-and-error approaches. In this study, using machine learning models and information extracted from the scientific literature, we investigate and predict the most influential variables governing the synthesis of gallium nitride (GaN) QDs applicable to UV photodetectors. The results obtained from the AdaBoost algorithm indicate that the Ga/N molar ratio, the aluminum-to-metal flux ratio, time, and growth temperature are the most important variables affecting the bandgap of GaN QDs. Moreover, the AdaBoost algorithm is employed to predict the optimal values of the key reaction variables within desired GaN QD bandgap ranges.

کلیدواژه‌ها English

Machine learning
Quantum Dots
Gallium Nitride
Ultraviolet Photodetector
[1] Kumar, D.S., B.J. Kumar, & H. Mahesh. (2018). Quantum nanostructures (QDs): an overview. Synthesis of inorganic nanomaterials, 59-88.
 [2]Li, Z., T. Yan, & X. Fang. (2023). Low-dimensional wide-bandgap semiconductors for UV photodetectors. Nature Reviews Materials. 8(9), 587-603.
[3] Braham, E.J., J. Cho, K.M. Forlano, D.F. Watson, R. Arròyave, & S. Banerjee. (2019). Machine learning-directed navigation of synthetic design space: A statistical learning approach to controlling the synthesis of perovskite halide nanoplatelets in the quantum-confined regime. Chemistry of Materials. 31(9), 3281-3292.
[4] Baum, F.b., T. Pretto, A. Köche, & M.J.L. Santos. (2020). Machine learning tools to predict hot injection syntheses outcomes for II–VI and IV–VI quantum dots. The Journal of Physical Chemistry C. 124(44), 24298-24305.
[5] Chetia, A., J. Bera, A. Betal, & S. Sahu. (2022). A brief review on photodetector performance based on zero dimensional and two dimensional materials and their hybrid structures. Materials Today Communications. 30, 103224.
[6] Dennis, P. (2012). Photodetectors: an introduction to current technology. Springer Science & Business Media.
 [7]Ding, M., Z. Guo, X. Chen, X. Ma, & L. Zhou. (2020). Surface/Interface engineering for constructing advanced nanostructured photodetectors with improved performance: A brief review. Nanomaterials. 10(2), 362.
[8] Huo, N.& G. Konstantatos. (2018). Recent progress and future prospects of 2D‐based photodetectors. Advanced Materials. 30(51), 1801164.
[9] Yadav, P.K., B. Ajitha, Y.A.K. Reddy, & A. Sreedhar. (2021). Recent advances in development of nanostructured photodetectors from ultraviolet to infrared region: A review. Chemosphere. 279, 130473.
[10] Adinolfi, V., O. Ouellette, M.I. Saidaminov, G. Walters, A.L. Abdelhady, O.M. Bakr, & E.H. Sargent. (2016). Fast and sensitive solution-processed visible-blind perovskite UV photodetectors. Adv. Mater. 28(33), 7264-7268.
 [11]Nasiri, N., D. Jin, & A. Tricoli. (2019). Nanoarchitechtonics of visible‐blind ultraviolet photodetector materials: critical features and nano‐microfabrication. Advanced Optical Materials. 7(2), 1800580.
 [12]Östling, M. (2011). High power devices in wide bandgap semiconductors. Science China Information Sciences. 54, 1087-1093.
[13] Jiawei, L., Y. Zhizhen, & N. Nasser. (2003). GaN-based quantum dots. Physica E: Low-dimensional Systems and Nanostructures. 16(2), 244-252.
[14] Qiu, H., J. Wu, M. Li, Z. Hu, S. Yang, Y. Li, Y. Gu, H. Cheng, & Y. Zheng. (2024). Oxygen-doped colloidal GaN quantum dots with blue emission. Materials Today Chemistry. 35, 101888.
[15] Kobayashi, Y., K. Kumakura, T. Akasaka, & T. Makimoto. (2012). Layered boron nitride as a release layer for mechanical transfer of GaN-based devices. Nature. 484(7393), 223-227.
[16] Daudin, B., C. Adelmann, N. Gogneau, E. Sarigiannidou, E. Monroy, F. Fossard, & J. Rouvière. (2004). GaN quantum dots by molecular beam epitaxy. Physica E: Low-dimensional Systems and Nanostructures. 21(2-4), 540-545.
[17] Zhang, R., G. Wang, Q. Zhang, S. Wang, X. Hu, L. Liu, S. Lv, W. Chen, X. Xu, & L. Zhang. (2025). Recent progress in GaN-based ultraviolet photodetectors. Journal of Materials Chemistry C. 13(22), 10972-10996.
[18] Chen, Y., J. Liu, K. Liu, J. Si, Y. Ding, L. Li, T. Lv, J. Liu, & L. Fu. (2019). GaN in different dimensionalities: Properties, synthesis, and applications. Materials Science and Engineering: R: Reports. 138, 60-84.
[19] Tchernycheva, M., A. Messanvi, A. de Luna Bugallo, G. Jacopin, P. Lavenus, L. Rigutti, H. Zhang, Y. Halioua, F. Julien, & J. Eymery. (2014). Integrated photonic platform based on InGaN/GaN nanowire emitters and detectors. Nano letters. 14(6), 3515-3520.
[20] Gyger, F., P. Bockstaller, H. Gröger, D. Gerthsen, & C. Feldmann. (2014). Quantum-confined GaN nanoparticles synthesized via liquid-ammonia-in-oil-microemulsions. Chemical Communications. 50(22), 2939-2942.
[21] Yue, Y., Z. Hu, J. Guo, B. Sensale-Rodriguez, G. Li, R. Wang, F. Faria, T. Fang, B. Song, & X. Gao. (2012). InAlN/AlN/GaN HEMTs with regrown ohmic contacts and $ f_ {T} $ of 370 GHz. IEEE Electron Device Letters. 33(7), 988-990.
[22] Tanaka, A., W. Choi, R. Chen, & S.A. Dayeh. (2017). Si complies with GaN to overcome thermal mismatches for the heteroepitaxy of thick GaN on Si. Advanced Materials. 29(38), 1702557.
[23] Goswami, L., N. Aggarwal, P. Vashishtha, S.K. Jain, S. Nirantar, J. Ahmed, M.M. Khan, R. Pandey, & G. Gupta. (2021). Fabrication of GaN nano-towers based self-powered UV photodetector. Scientific Reports. 11(1), 10859.
[24] Wu, H., J. Pan, J. Wang, C. Guo, S. Du, D. Xiao, D. Guo, & J. Hu. (2025). Pyro-phototronic-enhanced self-powered broadband UV photodetector based on GaNQDs/GaN homojunction for deep-UV imaging applications. Materials Today Physics, 101876.
[25] Jordan, M.I.& T.M. Mitchell. (2015). Machine learning: Trends, perspectives, and prospects. Science. 349(6245), 255-260.
[26] Janiesch, C., P. Zschech, & K. Heinrich. (2021). Machine learning and deep learning. Electronic Markets. 31(3), 685-695.
[27] Günnemann, S. (2017). Machine learning meets databases. Datenbank-Spektrum. 17(1), 77-83.
[28] Zhou, Z., X. Li, & R.N. Zare. (2017). Optimizing chemical reactions with deep reinforcement learning. ACS central science. 3(12), 1337-1344.
[29] Voznyy, O., L. Levina, J.Z. Fan, M. Askerka, A. Jain, M.-J. Choi, O. Ouellette, P. Todorovic, L.K. Sagar, & E.H. Sargent. (2019). Machine learning accelerates discovery of optimal colloidal quantum dot synthesis. Acs Nano. 13(10), 11122-11128.
[30] Vajire, S.L., A.P. Singh, D.K. Saini, A.K. Mukhopadhyay, K. Singh, & D. Mishra. (2022). Novel machine learning-based prediction approach for nanoindentation load-deformation in a thin film: Applications to electronic industries. Computers & Industrial Engineering. 174, 108824.
[31] Simeonov, D., E. Feltin, J.-F. Carlin, R. Butté, M. Ilegems, & N. Grandjean. (2006). Stranski-Krastanov GaN∕ AlN quantum dots grown by metal organic vapor phase epitaxy. Journal of applied physics. 99(8).
[32] Pelekanos, N., G. Dialynas, J. Simon, H. Mariette, & B. Daudin. GaN quantum dots: from basic understanding to unique applications. in Journal of Physics: Conference Series. 2005. IOP Publishing.
[33] Ghobadi, N., Daqiq, R. & Moradi, S.A.H. Layer-resolved berry curvature and Rashba spin–orbit control of quantum transport in magnetic tunnel junctions. Sci Rep 16, 9066 (2026). https://doi.org/10.1038/s41598-026-39901-w
[34] Seyed Ali Hosseini Moradi, Nader Ghobadi, Sajad Esfandyari, Reza Daqiq,Enhanced spin-transfer torque in asymmetric uperlattice magnetic tunnel junctions with engineered barrier profiles,Journal of Magnetism and Magnetic Materials, Volume 29,
2025,173276,ISSN 0304-8853, https://doi.org/10.1016/j.jmmm.2025.173276
[35] Chen, H., K. Chen, D. Drabold, & M. Kordesch. (2000). Band gap engineering in amorphous Al x Ga 1− x N: Experiment and ab initio calculations. Applied Physics Letters. 77(8), 1117-1119.
[36] Rouf, P., N.J. O’Brien, S.C. Buttera, I. Martinovic, B. Bakhit, E. Martinsson, J. Palisaitis, C.-W. Hsu, & H. Pedersen. (2020). Epitaxial GaN using Ga (NMe 2) 3 and NH 3 plasma by atomic layer deposition. Journal of Materials Chemistry C. 8(25), 8457-8465.
 [37]Freund, Y.& R.E. Schapire. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences. 55(1), 119-139.
 
 
دوره 4، شماره 4
زمستان 1404
صفحه 74-97

  • تاریخ دریافت 10 دی 1404
  • تاریخ بازنگری 20 اسفند 1404
  • تاریخ پذیرش 10 اردیبهشت 1405