Feature Engineering for False Positive Exoplanet Prediction: A Deep Learning Approach
Keywords:
: Artificial Neural Networks, Deep Learning, Exoplanet, Stellar Parameters, Transit PropertiesAbstract
The growing number of satellites has improved our understanding of exoplanets, but it has also increased false positive detections. These errors can mislead research and allocation of resources. To address this, we introduce ArtAe, an AI model that employs Artificial Neural Networks and AutoEncoders to validate exoplanet data. ArtAe processes Kepler and TESS datasets, achieving 93.67% and 92.10% accuracy respectively in distinguishing genuine exoplanets from false positives. Moreover, this model has unique algorithm that reduces overfitting of the model. It also lowers dataset dimensionality, saving time and resources. This accuracy aids in informed resource allocation for future studies and enables automated, accurate data validation and analysis.
Downloads
References
MacDonald, R. J. (2023, January 13). POSEIDON: A Multidimensional Atmospheric Retrieval Code for Exoplanet Spectra. Journal of Open-Source Software, 8(81), 4873. https://doi.org/10.21105/joss.04873
Dimitrov, N., & Natarajan, A. (2019, May 1). From SCADA to lifetime assessment and performance optimization: how to use models and machine learning to extract useful insights from limited data. Journal of Physics: Conference Series, 1222(1), 012032. https://doi.org/10.1088/1742-6596/1222/1/012032
Martin, S. R., Szwaykowski, P., & Loya, F. M. (2005, October). TPF-I Planet Detection Testbed: Progress in Testing Exo-planet Signal Detection. Proceedings of the International Astronomical Union, 1(C200), 279–284. https://doi.org/10.1017/s1743921306009458
Lin, Wu, Fu, Wang, Zhang, & Kong. (2019, October 28). Dual-NMS: A Method for Autonomously Removing False Detection Boxes from Aerial Image Object Detection Results. Sensors, 19(21), 4691. https://doi.org/10.3390/s19214691
Baluev, R. (2018, October). PlanetPack3: A radial-velocity and transit analysis tool for exoplanets. Astronomy and Computing, 25, 221–229. https://doi.org/10.1016/j.ascom.2018.10.005
Espinoza, N. (2018, November 12). Efficient Joint Sampling of Impact Parameters and Transit Depths in Transiting Exoplanet Light Curves. Research Notes of the AAS, 2(4), 209. https://doi.org/10.3847/2515-5172/aaef38
Alpaydin, E. (2010). Introduction to machine learning (2nd ed.). Cambridge, MA: MIT Press.
Bengio, Y., Goodfellow, I. J., & Courville, A. (2015). Deep learning. Cambridge, MA: MIT Press.
Brownlee, J. (2020). Neural networks for computer vision: A gentle introduction. Machine Learning Mastery. https://machinelearningmastery.com/neural-networks-for-computer-vision/
Haykin, S. (2009). Neural networks and learning machines (3rd ed.). Upper Saddle River, NJ: Pearson Education.
Hsu, S., Zhang, H., & Xing, E. P. (2019). Neural network models for joint dimensionality reduction and clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 517-524.
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., & Frey, B. (2015). Adversarial autoencoders. arXiv preprint arXiv:1511.05644.
Zhou, Y., Wen, D., & Fan, Y. (2017). Auto-encoder based anomaly detection for temporal data. IEEE Transactions on Cybernetics, 47(12), 4109-4121.
Shallue, C. J., & Vanderburg, A. (2018). Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90. The Astronomical Journal, 155(2), 94.
Malik, A., Moster, B. P., Obermeier, C., Exoplanet detection using machine learning, Monthly Notices of the Royal Astronomical Society, 513(4), 5505-5516. https://doi.org/10.1093/mnras/stab3692.
Liu, L., & Deng, J. (2018, April 29). Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-Offs by Selective Execution. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11630.
Sturrock, G. C., Manry, B., & Rafiqi, S. (2019). Machine Learning Pipeline for Exoplanet Classification. SMU Data Science Review, 2(1), 9.
Catanzarite, J. H. (2015). Autovetter Planet Candidate Catalog for Q1-Q17 Data Release 24, (K
SCI-19090-001). NASA Ames Research Center.
Ansdell, M., Ioannou, Y., Osborn, H. P., Sasdelli, M., Smith, JC., Caldwell, D., et al. (2018). Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning. The Astrophysical Journal, 869(1), L7.
Yu, L., Vanderburg, A., Huang, C., Shallue, CJ., Crossfield, IJM., Gaudi, BS., et al. (2019). Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates. The Astronomical Journal, 158(1), 25.
Chintarungruangchai, P., & Jiang, IG. (2019). Detecting Exoplanet Transits through Machine-learning Techniques with Convolutional Neural Networks. Publications of the Astronomical Society of the Pacific, 131(1000), 064502.
Fiscale, S., et al. (2023). Identifying Exoplanets in TESS Data by Deep Learning. In: Esposito, A., Faundez-Zanuy, M., Morabito, F.C., Pasero, E. (eds) Applications of Artificial Intelligence and Neural Systems to Data Science. Smart Innovation, Systems and Technologies, vol 360. Springer, Singapore.
Valizadegan, H., et al. (2022). ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier That Validates 301 New Exoplanets. The Astrophysical Journal, 926(2), 120.
Gupta, T. K., & Kumar, C. (2015, June 25). Deep Autoencoders for Non-Linear Dimensionality Reduction. Journal of Bioinformatics and Intelligent Control.
Liang Yu, Andrew Vanderburg, Chelsea Huang, Christopher J. Shallue, Ian J. M. Crossfield, B. Scott Gaudi, Tansu Daylan, Anne Dattilo, David J. Armstrong, George R. Ricker 2019, "Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates," The Astronomical Journal, Volume 158, Number 1.
Anne Dattilo, Andrew Vanderburg, Christopher J. Shallue, Andrew W. Mayo, Perry Berlind, Allyson Bieryla, Michael L. Calkins, Gilbert A. Esquerdo, Mark E. Everett, Steve B. Howell 2019, "Identifying Exoplanets with Deep Learning. II. Two New Super-Earths Uncovered by a Neural Network in K2 Data," The Astronomical Journal, Volume 157, Number 5.
Tey, E., Moldovan, D., Kunimoto, M., Huang, C. X., Shporer, A., Daylan, T., Muthukrishna, D., Vanderburg, A., Dattilo, A., Ricker, G. R., & Seager, S. 2023, “Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations.” Retrieved from https://doi.org/10.48550/arXiv.2301.01371
Chatterjee, Supratik & Keprate, Arvind. (2021). Predicting Remaining Fatigue Life of Topside Piping Using Deep Learning. 10.1109/ICAPAI49758.2021.9462055.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Nidhi Shakhapur, Ravin D., Chetan Shiraguppi, Sathya K.
![Creative Commons License](http://i.creativecommons.org/l/by-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.