| ELECTROMAGNETISM, OPTICS, ACOUSTICS, HEAT TRANSFER, CLASSICAL MECHANICS, AND FLUID DYNAMICS |
Prev
Next
|
|
|
Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks |
| Jian Zhang(张健), Yiming Liu(刘一鸣), and Zhanchun Tu(涂展春)† |
| Department of Physics, Beijing Normal University, Beijing 100875, China |
|
|
|
|
Abstract Neural networks have provided powerful approaches to solve various scientific problems. Many of them are even difficult for human experts who are good at accessing the physical laws from experimental data. We investigate whether neural networks can assist us in exploring the fundamental laws of classical mechanics from data of planetary motion. Firstly, we predict the orbits of planets in the geocentric system using the gate recurrent unit, one of the common neural networks. We find that the precision of the prediction is obviously improved when the information of the Sun is included in the training set. This result implies that the Sun is particularly important in the geocentric system without any prior knowledge, which inspires us to gain Copernicus' heliocentric theory. Secondly, we turn to the heliocentric system and make successfully mutual predictions between the position and velocity of planets. We hold that the successful prediction is due to the existence of enough conserved quantities (such as conservations of mechanical energy and angular momentum) in the system. Our research provides a new way to explore the existence of conserved quantities in mechanics system based on neural networks.
|
Received: 26 April 2022
Revised: 22 May 2022
Accepted manuscript online: 30 August 2022
|
|
PACS:
|
45.20.D-
|
(Newtonian mechanics)
|
| |
45.20.dh
|
(Energy conservation)
|
| |
95.10.Ce
|
(Celestial mechanics (including n-body problems))
|
| |
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant No. 11975050). |
Corresponding Authors:
Zhanchun Tu
E-mail: tuzc@bnu.edu.cn
|
Cite this article:
Jian Zhang(张健), Yiming Liu(刘一鸣), and Zhanchun Tu(涂展春) Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks 2022 Chin. Phys. B 31 094502
|
[1] Jones H S 1943 Nature 151 573
[2] Lecun Y, Bengio Y and Hinton G 2015 Nature 521 436
[3] Goodfellow I, Bengio Y and Courville A 2016 Deep Learning (Cambridge:MIT Press)
[4] Caldeira J, Wu W L K, Nord B, Avestruz C, Trivedi S and Story K T 2019 Astronomy and Computing 28 100307
[5] Yu H, Adhikari R X, Magee R, Sachdev S and Chen Y 2021 Phys. Rev. D 104 062004
[6] Pfeil T, Jordan J, Tetzlaff T, Grübl A, Schemmel J, Diesmann M and ¨ Meier K 2016 Phys. Rev. X 6 021023
[7] Petrovici M A, Bill J, Bytschok I, Schemmel J and Meier K 2016 Phys. Rev. E 94 042312
[8] Zhang P, Shen H and Zhai H 2018 Phys. Rev. Lett. 120 066401
[9] Ma X R, Tu Z C and Ran S J 2021 Chin. Phys. Lett. 38 110301
[10] Kaubruegger R, Pastori L and Budich J C 2018 Phys. Rev. B 97 195136
[11] Sturm E J, Carbone M R, Lu D, Weichselbaum A and Konik R M 2021 Phys. Rev. B 103 245118
[12] Huang Y and Moore J E 2021 Phys. Rev. Lett. 127 170601
[13] Zhao R, Xing B, Mu H, Fu Y and Zhang L 2022 Chin. Phys. B 31 056302
[14] Ma X R, He X F and Tu Z C 2021 Engineering Fracture Mechanics 241 107402
[15] Baldi P, Cranmer K, Faucett T, Sadowski P and Whiteson D 2016 Eur. Phys. J. C 76 235
[16] Beentjes S V and Khamseh A 2020 Phys. Rev. E 102 053314
[17] Giri S K and Goswami H P 2019 Phys. Rev. E 99 022104
[18] Rotondo P, Pastore M and Gherardi M 2020 Phys. Rev. Lett. 125 120601
[19] Huang H and Goudarzi A 2018 Phys. Rev. E 98 042311
[20] Casert C, Vieijra T, Whitelam S and Tamblyn I 2021 Phys. Rev. Lett. 127 120602
[21] Liu J G, Mao L, Zhang P and Wang L 2021 Mach. Learn.:Sci. Technol. 2 025011
[22] Zhao H 2021 Sci. China-Phys. Mech. Astron 64 270511
[23] Iten R, Metger T, Wilming H, del Rio L and Renne R 2020 Phys. Rev. Lett. 124 010508
[24] Qin H 2020 Sci. Rep. 10 13929
[25] Cho K, van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H and Bengio Y 2014 arXiv:1406.1078[cs.CL]
[26] Chung J, Gulcehre C, Cho K and Bengio Y 2014 arXiv:1412.3555[cs.NE]
[27] Cho K, van Merriënboer B, Bahdanau D, Bougares F and Bengio Y 2014 arXiv:1409.1259[cs.CL]
[28] https://pypi.org/project/de421/
[29] Elman J L 1990 Cognitive Science 14 179
[30] Schäfer A M and Zimmermann H G 2007 International Journal of Neural Systems 1 253
[31] Chollet F et al. 2015 Keras
[32] Abadi M et al. 2015 TensorFlow:Large-scale machine learning on heterogeneous systems software available from tensorflow.org
[33] Duchi J, Hazan E and Singer Y 2011 Journal of Machine Learning Research 12 2121
[34] Cybenko G 1989 Math. Control Signals Systems 2 303
[35] Hornik K, Stinchcombe M and White H 1989 Neural Networks 2 359
[36] Goldstein H 1980 Classical Mechanics, 2nd edn. (Massachusetts:Addison Wesley) pp. 419
[37] Liu Y 2021 Planetary Orbit Prediction Based on Machine Learning and Exploration of Classical Physics, M.S. Dissertation (Beijing:Beijing Normal University) (in Chinese)
[38] Wu T and Tegmark M 2019 Phys. Rev. E 100 033311 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
