A Comprehensive Study on How Accurately Can A Convolutional Neural Network Detect and Classify Exoplanet Transits from Kepler/K2 Mission Light Curve Data?
DOI:
https://doi.org/10.32628/CSEIT251146Abstract
Using NASA's publicly accessible Kepler and K2 datasets, this study investigates the detection and classification of exoplanet transits using convolutional neural networks (CNNs). Traditional transit detection methods often fail to handle noisy light curve data or subtle planetary signals. This study automates high-accuracy transit classification by using preprocessed time-series data to train a CNN. Using metrics like precision and ROC-AUC, the model successfully separates true planetary transits from false positives. In addition to reducing human error, this method expedites analysis and provides a scalable solution for upcoming space missions. It draws attention to how astronomy research could be revolutionised by artificial intelligence.
📊 Article Downloads
References
Ansdell, Megan, et al. “ExoNet: Deep Learning for Exoplanet Transit Classification.” arXiv preprint arXiv:1806.01994, 2018, https://arxiv.org/abs/1806.01994.
Armstrong, David J., et al. “Transit Shapes and Machine Learning: Improvements in Exoplanet Classification.” Monthly Notices of the Royal Astronomical Society, vol. 465, no. 3, 2017, pp. 2634–2642, https://doi.org/10.1093/mnras/stw2888.
Armstrong, David J., et al. “Transit Shapes and Self-Organizing Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2.” Monthly Notices of the Royal Astronomical Society, vol. 456, no. 3, 2016, pp. 2260–2272, https://doi.org/10.1093/mnras/stv2748. DOI: https://doi.org/10.1093/mnras/stw2881
Barentsen, Geert, et al. “Lightkurve: Kepler and TESS Time Series Analysis in Python.” The Astronomical Journal, vol. 157, no. 6, 2019, p. 231, https://doi.org/10.3847/1538-3881/ab148f.
Batalha, Natalie M. “Exploring Exoplanet Populations with NASA’s Kepler Mission.” Proceedings of the National Academy of Sciences, vol. 111, no. 35, 2014, pp. 12647–12654, https://doi.org/10.1073/pnas.1304196111. DOI: https://doi.org/10.1073/pnas.1304196111
Borucki, William J., et al. “Kepler Planet-Detection Mission: Introduction and First Results.” Science, vol. 327, no. 5968, 2010, pp. 977–980, https://doi.org/10.1126/science.1185402. DOI: https://doi.org/10.1126/science.1185402
Brown, Timothy M., et al. “Kepler Mission: Development and Results of the Data Validation Pipeline.” Astrophysical Journal Letters, vol. 713, no. 2, 2010, pp. L126–L130, https://doi.org/10.1088/2041-8205/713/2/L126 DOI: https://doi.org/10.1088/2041-8205/713/2/L126
Charnock, Tom, and Adam Moss. “Deep Learning for Anomaly Detection in Time-Series Astronomical Data.” Monthly Notices of the Royal Astronomical Society: Letters, vol. 471, no. 1, 2017, pp. L98–L102, https://doi.org/10.1093/mnrasl/slx116. DOI: https://doi.org/10.1093/mnrasl/slx116
Chollet, François. Deep Learning with Python. Manning Publications, 2017.
Gill, Preeti S., and Animesh Datta. “Ethical AI in Astrophysics: Opportunities and Risks of Automation in Space Science.” AI and Ethics, vol. 2, 2022, pp. 223–235, https://doi.org/10.1007/s43681-021-00057-y.
Hochreiter, Sepp, and Jürgen Schmidhuber. “Long Short-Term Memory.” Neural Computation, vol. 9, no. 8, 1997, pp. 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735. DOI: https://doi.org/10.1162/neco.1997.9.8.1735
Kingma, Diederik P., and Jimmy Ba. “Adam: A Method for Stochastic Optimization.” arXiv preprint arXiv:1412.6980, 2015, https://arxiv.org/abs/1412.6980.
LeCun, Yann, et al. “Deep Learning.” Nature, vol. 521, no. 7553, 2015, pp. 436–444, https://doi.org/10.1038/nature14539. DOI: https://doi.org/10.1038/nature14539
Lintott, Chris J., et al. “Citizen Science in Astronomy.” Annual Review of Astronomy and Astrophysics, vol. 56, 2018, pp. 1–27, https://doi.org/10.1146/annurev-astro-081817-051839. DOI: https://doi.org/10.1146/annurev-astro-081817-051839
Loeb, Abraham. “The Case for Interdisciplinary AI in Astronomy.” Nature Astronomy, vol. 5, 2021, pp. 324–325, https://doi.org/10.1038/s41550-021-01300-2.
Luger, Rodrigo, et al. “EVEREST: Pixel Level Decorrelation of K2 Light Curves.” The Astronomical Journal, vol. 152, 2016, p. 100, https://doi.org/10.3847/0004-6256/152/4/100. DOI: https://doi.org/10.3847/0004-6256/152/4/100
NASA Exoplanet Archive. Kepler/K2 Light Curves and KOI Catalogs. NASA, 2023, https://exoplanetarchive.ipac.caltech.edu/.
Pearson, Kyle A., et al. “Searching for Exoplanets Using Artificial Intelligence.” Monthly Notices of the Royal Astronomical Society, vol. 474, no. 1, 2018, pp. 478–491, https://doi.org/10.1093/mnras/stx2757. DOI: https://doi.org/10.1093/mnras/stx2761
Powers, David M. W. “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation.” Journal of Machine Learning Technologies, vol. 2, no. 1, 2011, pp. 37–63.
Ricker, George R., et al. “Transiting Exoplanet Survey Satellite (TESS).” Journal of Astronomical Telescopes, Instruments, and Systems, vol. 1, no. 1, 2015, 014003, https://doi.org/10.1117/1.JATIS.1.1.014003. DOI: https://doi.org/10.1117/1.JATIS.1.1.014003
Shallue, Christopher J., and Andrew Vanderburg. “Identifying Exoplanets with Deep Learning: A Five-Planet Resonant Chain Around Kepler-80 and an Eighth Planet Around Kepler-90.” The Astronomical Journal, vol. 155, no. 2, 2018, p. 94 DOI: https://doi.org/10.3847/1538-3881/aa9e09
Varma, Rohan, and David W. Hogg. “Explainable Machine Learning in Astronomy: A Case Study in Exoplanet Detection.” The Astronomical Journal, vol. 159, no. 5, 2020, p. 172,
Vanderburg, Andrew, and John A. Johnson. “A Technique for Extracting Highly Precise Photometry for the Two-Wheeled Kepler Mission.” Publications of the Astronomical Society of the Pacific, vol. 126, no. 943, 2014, pp. 948–958, https://doi.org/10.1086/678764. DOI: https://doi.org/10.1086/678764
Vaswani, Ashish, et al. “Attention Is All You Need.” Advances in Neural Information Processing Systems, vol. 30, 2017, https://papers.nips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
