Next Article in Journal
Global Structural Behavior and Leg Strength for Jack-Up Rigs with Varying Environmental Parameters
Previous Article in Journal
Differing Responses of Three Scleractinian Corals from Phuket Coast in the Andaman Sea to Experimental Warming and Hypoxia
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JMSE
Volume 11
Issue 2
10.3390/jmse11020404
jmse-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Concrete Autoencoder for the Reconstruction of Sea Temperature Field from Sparse Measurements †

by
Alexander A. Lobashev
1,
Nikita A. Turko
2,*,
Konstantin V. Ushakov
2,3,
Maxim N. Kaurkin
3 and
Rashit A. Ibrayev
2,3,4
1
Skolkovo Institute of Science and Technology, 30 Bolshoy Boulevard, Moscow 121205, Russia
2
Moscow Institute of Physics and Technology, 9 Institutskiy Per., Dolgoprudny 141701, Russia
3
Shirshov Institute of Oceanology, Russian Academy of Sciences, 36 Nakhimovsky Prospekt, Moscow 117997, Russia
4
Marchuk Institute of Numerical Mathematics, Russian Academy of Sciences, 8 Gubkin Str., Moscow 119333, Russia
*
Author to whom correspondence should be addressed.
†
This paper is an extended version of paper published in the International Scientific Conference “Russian Supercomputing Days”, Moscow, Russia, 26–27 September 2022.
J. Mar. Sci. Eng. 2023, 11(2), 404; https://doi.org/10.3390/jmse11020404
Submission received: 10 December 2022 / Revised: 4 February 2023 / Accepted: 7 February 2023 / Published: 12 February 2023
Browse Figures
Review Reports Versions Notes

Abstract

This paper presents a new method for finding the optimal positions for sensors used to reconstruct geophysical fields from sparse measurements. The method is composed of two stages. In the first stage, we estimate the spatial variability of the physical field by approximating its information entropy using the Conditional Pixel CNN network. In the second stage, the entropy is used to initialize the distribution of optimal sensor locations, which is then optimized using the Concrete Autoencoder architecture with the straight-through gradient estimator for the binary mask and with adversarial loss. This allows us to simultaneously minimize the number of sensors and maximize reconstruction accuracy. We apply our method to the global ocean under-surface temperature field and demonstrate its effectiveness on fields with up to a million grid cells. Additionally, we find that the information entropy field has a clear physical interpretation related to the mixing between cold and warm currents.
Keywords: concrete autoencoder; optimal sensor placement; information entropy; ocean state reconstruction; mutual information; sensitivity concrete autoencoder; optimal sensor placement; information entropy; ocean state reconstruction; mutual information; sensitivity

Share and Cite

MDPI and ACS Style

Lobashev, A.A.; Turko, N.A.; Ushakov, K.V.; Kaurkin, M.N.; Ibrayev, R.A. Concrete Autoencoder for the Reconstruction of Sea Temperature Field from Sparse Measurements. J. Mar. Sci. Eng. 2023, 11, 404. https://doi.org/10.3390/jmse11020404

AMA Style

Lobashev AA, Turko NA, Ushakov KV, Kaurkin MN, Ibrayev RA. Concrete Autoencoder for the Reconstruction of Sea Temperature Field from Sparse Measurements. Journal of Marine Science and Engineering. 2023; 11(2):404. https://doi.org/10.3390/jmse11020404

Chicago/Turabian Style

Lobashev, Alexander A., Nikita A. Turko, Konstantin V. Ushakov, Maxim N. Kaurkin, and Rashit A. Ibrayev. 2023. "Concrete Autoencoder for the Reconstruction of Sea Temperature Field from Sparse Measurements" Journal of Marine Science and Engineering 11, no. 2: 404. https://doi.org/10.3390/jmse11020404

APA Style

Lobashev, A. A., Turko, N. A., Ushakov, K. V., Kaurkin, M. N., & Ibrayev, R. A. (2023). Concrete Autoencoder for the Reconstruction of Sea Temperature Field from Sparse Measurements. Journal of Marine Science and Engineering, 11(2), 404. https://doi.org/10.3390/jmse11020404

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop