簡易檢索 / 詳目顯示
| 研究生： |
林佑宣 Lin, Yu-Hsuan |
|---|---|
| 論文名稱： |
以機器學習法尋找SuperWASP資料庫之凌星事件 Searching for Transit Events from SuperWASP Data through Machine Learning |
| 指導教授： |
葉麗琴
Yeh, Li-Chin |
| 口試委員: |
江瑛貴
Jiang, Ing-Guey 陳賢修 Chen, Shyan Shiou |
| 學位類別： |
碩士 Master |
| 系所名稱： |
理學院 - 計算與建模科學研究所 Institute of Computational and Modeling Science |
| 論文出版年： | 2021 |
| 畢業學年度： | 109 |
| 語文別： | 中文 |
| 論文頁數： | 50 |
| 中文關鍵詞： | 機器學習 、系外行星 |
| 相關次數： | 點閱：2 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 |
在本論文中，我們使用SuperWASP資料庫中的光曲線作為背景訊號，再加上人工建構的凌星光曲線形成資料庫，利用機器學習法訓練，也進行交叉驗證，尋找出可能的凌星週期後，目測挑選出較明顯的凌星光曲線，再以Mandel & Agol [6]的方法建構理論光曲線，計算理論光曲線與凌星光曲線的誤差，並從中選取候選行星，若同一條光曲線選取了不只一個凌星週期，將以誤差值最小的光曲線作為候選行星。
在此論文中，我們找到48個候選行星，其週期介於1天與2天之間，要判斷是否為系外行星，可能需要更多望遠鏡資料，再來做最後的確認。
In this thesis, we used the light curves from SuperWASP data for backgroung noise and added artificial transit light curves for our data set. We used a machine learning method to train our models. From the cross-validation method the stability of our machine learning model will be presented. After all, we selected the more obvious transit light curves for some transit periods. Then, we constructed the theoretical transit light curves by Mandel & Agol [6]. After that, calculated the errors between the theoretical transit light curves and the observational transit light curves. If one light curve had more than one possible transit period, we chose the period which had the smallest error to be our planet candidate.
In this thesis, we found there are 48 planet candidates with their periods between one day and two days. We need more data from large telescopes to confirm whether these planet candidates are exoplanets or not.
[1] Armstrong D. J, et al. (2020). T Exoplanet Validation with Machine Learning: 50 new validated Kepler planets. Monthly Notices of the Royal Astronomical Society, Volume 504, Issue 4, July 2021, Pages 5327–5344
[2] Collier Cameron, et al. (2007). WASP-1b and WASP-2b: two new transiting exoplanets detected with SuperWASP and SOPHIE, Monthly Notices of the Royal Astronomical Society, Volume 375, Issue 3, March 2007, Pages 951–957,
[3] Ketkar N. (2017). Convolutional Neural Networks. In: Deep Learning with Python. Apress, Berkeley, CA.
[4] Kuo, C.-C. (2020). Searching Exoplanets through Machine Learning Techniques. Unpublished master’s thesis, Nation Tsing Hua University.
[5] Kohavi, R. (1995). A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. Int Jt Conf Artif Intell. 1995;14:1137–1145.
[6] Mandel, K., & Agol, E. (2002). Analytic Lightcurves for Planetary Transit Searches. The Astrophysical Journal, Volume 580, Issue 2, pp. L171-L175.
[7] https://github.com/PetarV-/TikZ/tree/master/Dropout