簡易檢索 / 詳目顯示

回結果列表
研究生： 周厚發
Pattana Chintarungruangchai
論文名稱： 機器學習在利用凌星和直接成像法搜尋系外行星的應用
The Applications of Machine Learning on Searching Exoplanets through Transit and Direct-Imaging Methods
指導教授： 江瑛貴
Jiang, Ing-Guey
口試委員: 葉麗琴
Yeh, Li-chin
陳林文
Chen, Lin-Wen
陳怡全
Chen, Yi-chuan
吳亞霖
Wu, Ya-Lin
學位類別： 博士
Doctor
系所名稱： 理學院 - 天文研究所
Institute of Astronomy
論文出版年： 2023
畢業學年度： 111
語文別： 英文
論文頁數： 65
中文關鍵詞： 機器學習 、系外行星
外文關鍵詞： machine learning, exoplanet
相關次數： 點閱：3  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 我們試圖通過機器學習技術來改進系外行星探索方法。我們提出了二維捲機神經網路（2D-CNN），用於通過觀測到的光變曲線來進行系外行星凌日檢測。開普勒太空望遠鏡觀測到的光變曲線被使用來學習和測試新的2D-CNN模型。我們將2D-CNN的凌星檢測的標準性、可靠性和整性與1D-CNN的結果進行了比較，並展示了使用2D-CNN的優勢。此方法還可用於從其他凌星觀測的光變曲線中搜索新的凌星，例如TESS。
    此外，我們將機器學習技術應用於通過角度差分成像（ADI）技術的直接影像法的系外行星檢測。我們使用VLT/SPHERE的IRDIS所觀測到的數據來進行測試。這裡我們提出了具有殘差學習技術和批量歸一化的神經網路，MWIN5-RB。這可以將ADI方法拍攝到的低質量圖像轉換為高質量圖像，並提高圖像中的系外行星的信噪比（SNR）。

    We try to improve the methods of exoplanet detection through machine-learning techniques. We propose two-dimensional convolutional neural network (2D-CNN) for detecting exoplanet transits from observed light curves. We use light curves observed by Kepler space telescope to learn and test new 2D-CNN models. We compare accuracy, reliability, and completeness of transit detections by our 2D-CNN with the results of 1D-CNN and show the advantage of using 2D-CNN. Our method can be employed to search for possible new transits from light curves of other transit survey such as TESS.
    Furthermore, we apply machine learning techniques to the detection of exoplanets by direct imaging method with angular differential imaging (ADI) technique. We test on the image data observed by VLT/SPHERE with Infrared Dual-band Imager and Spectrograph (IRDIS). Here we proposed Modified five-layer Wide Inference Network with the Residual learning technique and Batch normalization (MWIN5-RB), which can convert low quality image taken by ADI method into high quality image and increase signal-to-noise-ratio (SNR) of exoplanet in the image.

    1 Introduction 1 2 Machine-Learning 5 2.1 Overview of Machine-Learning and Artificial Intelegence . . . . . . . 5 2.2 Logistic Regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.3 Deep-Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.4 Convolutional Neural Network . . . . . . . . . . . . . . . . . . . . . . 9 2.5 Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3 Transit Method 14 3.1 Overview of Transit Method . . . . . . . . . . . . . . . . . . . . . . . 14 3.2 The Data of Kepler Space Telescope . . . . . . . . . . . . . . . . . . . 15 3.3 Injected Planet Signal in Light Curve . . . . . . . . . . . . . . . . . . 17 4 Convolutional Neural Network for Detecting Exoplanet Transit 19 4.1 The Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4.2 Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.2.1 Training, Validation, and Testing Processes . . . . . . . . . . . 23 4.2.2 Signal-to-Noise Ratios . . . . . . . . . . . . . . . . . . . . . . 25 4.2.3 Transit Phase Positions . . . . . . . . . . . . . . . . . . . . . . 26 4.2.4 Folding Periods . . . . . . . . . . . . . . . . . . . . . . . . . . 27 4.3 Demonstration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 5 Direct Imaging Method 35 5.1 Overview of Angular Differenrial Imaging . . . . . . . . . . . . . . . . 35 5.2 VLT SPHERE Data . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 5.3 Injected Planet Image . . . . . . . . . . . . . . . . . . . . . . . . . . 39 5.4 Signal-to-Noise Ratio . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 6 Convolutional Neural Network for Denoising Exoplanet Image 43 6.1 The Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 6.2 The Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 6.2.1 The Input . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 6.2.2 The Operation of Layers . . . . . . . . . . . . . . . . . . . . . 47 6.2.3 The Residual . . . . . . . . . . . . . . . . . . . . . . . . . . . 50 6.2.4 The Optimization . . . . . . . . . . . . . . . . . . . . . . . . . 51 6.3 Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 6.4 Demonstration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 7 Conclusions 59 7.1 The Conclusion of Convolutional Neural Network for Exoplanet Transit 59 7.2 The Conclusion of Convolutional Neural Network for Direct Imaging Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60

    Amara, A., Quanz, S. P. 2012, MNRAS, 427, 948A
    Armstrong, D. J., Pollacco, D., Santerne, A. 2017, MNRAS, 465, 2634
    Batalha, N. M., Rowe, J. F., Bryson, S. T., et al. 2013, ApJS, 204, 24
    Beuzit, J. L., et al., 2019, A&A, 631, A155
    Borucki, W. J., Koch, D., Jenkins, J., et al. 2009, Sci, 325, 709
    Camporeale, E., 2020, Journal of Geophysical Research, 125, 2, e27502
    Charbonneau, D., Brown, T., Latham, D., Mayor, M. 2003, ApJ, 529, L45
    Chauvin, G., Desidera, S., Lagrange, A. et al. 2017, A&A, 605, L9, 9 pp.
    Cheng, T.-Y., Conselice, C. J., Arag´on-Salamanca, A., et al. 2021, MNRAS, 507, 4425
    Chintarungruangchai, P., Jiang I.-G. 2019, PASP, 131, 064502
    Christiansen, J. L., Clarke, B. D., Burke, C. J., et al. 2013, ApJS, 207, 35
    Christiansen, J. L., Clarke, B. D., Burke, C. J., et al. 2015, ApJ, 810, 95
    Christiansen, J. L., Clarke, B. D., Burke, C. J., et al. 2016, ApJ, 828, 99
    Coughlin, J. L., Mullally, F., Thompson, S. E. 2016, ApJS, 224, 12
    Cuevas-Tello, J. C., Tino, P., Raychaudhury, S. 2006, A&A, 454, 695
    de la Calleja, J., Fuentes, O., 2004, MNRAS, 349, 87
    Ding, X., Ji, K.-F., Li, X.-Z., 2021, PASJ, 73, 786
    Dohlen, K., Langlois, M., Saisse, M. et al. 2008, in Ground-based and Airborne Instrumentation for Astronomy II, Proc. SPIE, 7014,70143L
    Felipe, T., Asensio Ramos, A. 2019, A&A 632, A82
    Gao, X.-H., 2018, ApJ, 869, 9
    Gomez Gonzalez, C. A., Absil, O., Absil, P. -A., et al. 2016, A&A 589, A54
    Hahnloser, R, Sarpeshkar, R., Mahowald, M. A. et al. 2000 Nature, 405, 6789, pp. 947-951
    Hinners, T., Tat, K., Thorp, R. 2017, AJ, 156, 7
    Ioffe, S., Szegedy, C. 2015, arXiv. 1502, 03167
    Jenkins, J. M., Caldwell, D. A., Chandrasekaran, H., et al. 2010, ApJL, 713, L87
    Jovanovic, N., Martinache, F., Guyon, O., et al., 2015, PASP, 127, 890,
    Karas, P., Graham, J., Chiang, E. 2008, Science, Volume 322, Issue 5906, pp. 1345-
    Kelley, J. M., Gray, M. R., Givens, J. A., IEEE Trans. Syst. Man Cybern. SMC-15, 580.
    Kiku, D., Monno, Y., Tanaka, M., Okutomi M. 2013, IEEE International Conference on Image Processing, pages 2304–2308. IEEE
    Kim, D.-W., Protopapas, P., Byun, Y.-I., et al. 2011, ApJ, 735, 68
    Kingma, D., Ba, J. 2014, arXiv:1412.6980
    Koch, D. G., Borucki, W. J., Rowe, J. F., et al. 2010, ApJL, 713, L131
    Kovacs, G., Zucker, S., & Mazeh, T. 2002, A&A, 391, 369
    Liao, S., Li, X., Yang, Y. 2022, New Astronomy, 96, 101850
    Lin, H.-W., Chen, Y.-T., Wang, J.-H., et al., 2018, PASJ, 70, S39
    Liu, P., Fang, R. 2017, arXiv, 1707, 05414
    Lv, X., Ming, D., Chen, Y., et al., 2019, International Journal of Remote Sensing, 40, 506
    Macintosh, B., et al., 2006, SPIE, 62720L
    Mandel, K., Agol, E. 2002, ApJ, 580, L171
    Marois, C., Lafreni`ere, D., Doyon, R. et al. 2006, ApJ, 641, 556M
    Mawet, D., Milli, J., Wahhaj, Z. et al. 2016, arXiv. 1606, 08921
    McCauliff, S. D., Jenkins, J. M., Catanzarite, J. et al. 2015, ApJ, 806, 6
    Miettinen, O., 2018, Astrophysics and Space Science, 363, 197
    Mullally, F., Coughlin, J. L., Thompson, S. E., et al. 2015, ApJS, 217, 31
    Mullally, F., Coughlin, J. L., Thompson, S. E., et al. 2016, PASP, 128, 074502
    Nair, V., Hinton, G. E. 2010, in Proc. 27th Int. Conf. Machine Learning, ed. J. Fürnkranz & T. Joachims (Madison, WI: Omnipress), 807
    Paszke, A., Gross, S., Chintala, S., et al. 2017, in Advances in Neural Information
    Processing Systems 31, ed. S. Bengio et al. (Red Hook, NY: Curran Associates, Inc.)
    Pearson, K. A., Palafox, L., Griffith, C. A. 2018, MNRAS, 474, 478
    Ronneberger, O., Fischer, P., Brox, T. 2015 arXiv. 1505, 04597
    Schawinski, K., Zhang, C., Zhang, H. et al. 2017 MNRAS, 467, 110
    Shallue, C. J., Vanderburg, A. 2018, AJ, 155, 94
    Smith, J. C., Stumpe, M. C., Van Cleve, J. E. et al. 2012, PASP., 124.1000
    Soummer, R., Pueyo, L., Larkin, J. 2012, ApJ, 755L, 28S
    Stone M. 1974, Journal of the Royal Statistical Society, Series B, 36, 111-147
    Thompson, S. E., Mullally, F., Coughlin, J. et al. 2015, ApJ, 812, 46
    Thompson, S. E., Coughlin, J. L., Hoffman, K. et al. 2018, ApJS, 235, 38
    Vigan, A., Moutou, C., Langlois, M. et al. 2010, MNRAS, 407, 71
    Vigan, A., 2020, ASCL, ascl:2009.002 https://github.com/avigan/SPHERE
    Yeh, L.-C., Jiang, I.-G. 2021, PASP, 133, 014401
    Zhang, K., Zuo, W., Chen, Y. et al. 2017, IEEE Transactions on Image Processing, 26, 7, pp. 3142-3155
    Zucker, S., Giryes, R. 2017, AJ, 155, 147

    QR CODE