Abstract
Accurate estimation and prediction of the thermospheric density is crucial for accurate low Earth orbit prediction. Recently, Reduced-Order Models (ROMs) were developed to obtain accurate quasi-physical dynamic models for the thermospheric density. In this paper we explore the use of deep neural networks and autoencoders to improve the reduced-order models. Through the development of deep and convolutional autoencoders, we obtain improved low-dimension representations of a high-dimensional density state. In addition, we improve the prediction accuracy of the ROM using a deep neural network.
H. Turner and M. Zhang—These authors contributed equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bergstra, J., Yamins, D., Cox, D.D.: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In: Proceedings of the 30th International Conference on Machine Learning, vol. 28, p. I-115-I-123. JMLR (2013)
Bernstein, D., Ridley, A., Cutler, J., Cohn, A.: Transformative advances in DDDAS with application to space weather monitoring. University of Michigan (2015)
Blasch, E.: DDDAS advantages from high-dimensional simulation. In: 2018 Winter Simulation Conference (WSC), pp. 1418–1429. IEEE (2018)
Gondelach, D.J., Linares, R.: Real-time thermospheric density estimation viatwo-line element data assimilation. Space Weather 18(2), e2019SW002356 (2020)
Gonzalez, F.J., Balajewicz, M.: Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems (2018). arXiv preprint arXiv:1808.01346
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980
Lee, K., Carlberg, K.T.: Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders. J. Comput. Phys. 404, 108973 (2020)
Licata, R.J., Mehta, P.M.: Physics-informed machine learning with autoencoders and LSTM for probabilistic space weather modeling and forecasting. In: 100th American Meteorological Society Annual Meeting (2020)
Linares, R., Mehta, P.M., Godinez, H.C., Gondelach, D.J.: Koopman operator theory for thermospheric density modeling. In: Proceedings of the 29th AAS/AIAA Space Flight Mechanics Meeting, Ka’anapali, HI (2019)
Mehta, P.M., Linares, R.: A methodology for reduced order modeling and calibration of the upper atmosphere. Space Weather 15(10), 1270–1287 (2017)
Mehta, P.M., Linares, R., Sutton, E.K.: A quasi-physical dynamic reduced order model for thermospheric mass density via hermitian space-dynamic mode decomposition. Space Weather 16(5), 569–588 (2018)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929–1958 (2014)
Szegedy, C., et al.: Going deeper with convolutions (2014). arXiv preprint arXiv:1409.4842
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Turner, H., Zhang, M., Gondelach, D., Linares, R. (2020). Machine Learning Algorithms for Improved Thermospheric Density Modeling. In: Darema, F., Blasch, E., Ravela, S., Aved, A. (eds) Dynamic Data Driven Applications Systems. DDDAS 2020. Lecture Notes in Computer Science(), vol 12312. Springer, Cham. https://doi.org/10.1007/978-3-030-61725-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-61725-7_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61724-0
Online ISBN: 978-3-030-61725-7
eBook Packages: Computer ScienceComputer Science (R0)