Russian Federation
Russian Federation
Moskovskiy fiziko-tehnicheskiy institut (NIU)
Russian Federation
Institut okeanologii im. P.P. Shirshova RAN
Moskovskiy fiziko-tehnicheskiy institut (NIU)
Russian Federation
VAC 1.6 Науки о Земле и окружающей среде
UDK 551.46.0 Общие аспекты океанологии: теория, наблюдения, приборы. Прикладная океанология
GRNTI 37.25 Океанология
OKSO 05.00.00 Науки о Земле
BBK 26 Науки о Земле
BISAC SCI SCIENCE
The paper examines the impact of sensor placement on the accuracy of the Global ocean state forecasting. A comparison is made between various sensor placement methods, including the arrangement obtained by the Concrete Autoencoder method. To evaluate how sensor placement affects forecast accuracy, a simulation was conducted that emulates a scenario where the initial state of the global ocean significantly deviates from the ground truth. In the experiment, initial conditions for the ocean and ice model were altered, while atmospheric forcing was retained from the control experiment. Subsequently, the model was integrated with the assimilation of data about the ground truth state at the sensor locations. The results showed that the sensor placement obtained using deep learning methods is superior in forecast accuracy to other considered arrays with a comparable number of sensors.
operational forecast, Global ocean, optimal sensor placement, Concrete Autoencoder, data assimilation
1. Abbasi M. R., Chegini V., Sadrinasab M., et al. Correcting the Sea Surface Temperature by Data Assimilation Over the Persian Gulf // Iranian Journal of Science and Technology, Transactions A: Science. — 2018. — Vol. 43, no. 1. — P. 141–149. — DOI:https://doi.org/10.1007/s40995-017-0357-z.
2. Abid A., Balin M. F., Zou J. Concrete Autoencoders for Differentiable Feature Selection and Reconstruction // Cornell University. — 2019. — Vol. abs/1901.09346. — DOI:https://doi.org/10.48550/ARXIV.1901.09346.
3. Alonso A. A., Frouzakis C. E., Kevrekidis I. G. Optimal sensor placement for state reconstruction of distributed process systems // AIChE Journal. — 2004. — Vol. 50, no. 7. — P. 1438–1452. — DOI:https://doi.org/10.1002/aic.10121.
4. Boyer T. P., Antonov J. I., Baranova O. K., et al. World ocean database 2013. — U. S. Department of Commerce, National Oceanic, Atmospheric Administration, National Environmental Satellite, Data, Information Service, National Oceanographic Data Center, Ocean Climate Laboratory, 2013. — DOI:https://doi.org/10.7289/V5NZ85MT.
5. Clark E., Askham T., Brunton S. L., et al. Greedy Sensor Placement With Cost Constraints // IEEE Sensors Journal. — 2019. — Vol. 19, no. 7. — P. 2642–2656. — DOI:https://doi.org/10.1109/JSEN.2018.2887044.
6. Covert I., Qiu W., Lu M., et al. Learning to Maximize Mutual Information for Dynamic Feature Selection // Proceedings of the 40th International Conference on Machine Learning. — Honolulu, Hawaii, USA : PMLR 202, 2023. — DOI:https://doi.org/10.48550/arXiv.2301.00557.
7. Desai S. Jason-3 GPS based orbit and SSHA OGDR. — 2016. — DOI:https://doi.org/10.5067/J3L2G-OGDRF.
8. Fadeev R. Y., Ushakov K. V., Tolstykh M. A., et al. Design and development of the SLAV-INMIO-CICE coupled model for seasonal prediction and climate research // Russian Journal of Numerical Analysis and Mathematical Modelling. — 2018. — Vol. 33, no. 6. — P. 333–340. — DOI:https://doi.org/10.1515/rnam-2018-0028.
9. Hersbach H., Bell B., Berrisford P., et al. The ERA5 global reanalysis // Quarterly Journal of the Royal Meteorological Society. — 2020. — Vol. 146, no. 730. — P. 1999–2049. — DOI:https://doi.org/10.1002/qj.3803.
10. Huijben I. A. M., Veeling B. S., Sloun R. J. G. van. Deep probabilistic subsampling for taskadaptivecompressed sensing // International Conference on Learning Representations 2020. — ICLR, 2020.
11. Hunke E. C., Lipscomb W. H., Turner A. K., et al. CICE: The Los Alamos Sea Ice Model Documentation and Software User’s Manual Version 5 (Tech. Rep. LA-CC-06-012). — Los Alamos National Laboratory, 2015.
12. Jang E., Gu S., Poole B. Categorical Reparameterization with Gumbel-Softmax // Cornell University. — 2016. — Vol. abs/1611.01144. — DOI:https://doi.org/10.48550/arXiv.1611.01144.
13. Kalmykov V. V., Ibrayev R. A., Kaurkin M. N., et al. Compact Modeling Framework v3.0 for high-resolution global ocean-ice-atmosphere models // Geoscientific Model Development. — 2018. — Vol. 11, no. 10. — P. 3983–3997. — DOI:https://doi.org/10.5194/gmd-11-3983-2018.
14. Kalnitskii L. Y., Kaurkin M. N., Ushakov K. V., et al. Seasonal Variability of Water and Sea-Ice Circulation in the Arctic Ocean in a High-Resolution Model // Izvestiya, Atmospheric and Oceanic Physics. — 2020. — Vol. 56, no. 5. — P. 522–533. — DOI:https://doi.org/10.1134/S0001433820050060.
15. Kaurkin M. N., Ibrayev R. A., Belyaev K. P. Data assimilation in the ocean circulation model of high spatial resolution using the methods of parallel programming // Russian Meteorology and Hydrology. — 2016a. — Vol. 41, no. 7. — P. 479–486. — DOI:https://doi.org/10.3103/S1068373916070050.
16. Kaurkin M. N., Ibrayev R. A., Koromyslov A. EnOI-Based Data Assimilation Technology for Satellite Observations and ARGO Float Measurements in a High Resolution Global Ocean Model Using the CMF Platform // Supercomputing. — Springer International Publishing, 2016b. — P. 57–66. — DOI:https://doi.org/10.1007/978-3-319-55669-7_5.
17. Kaurkin M. N., Ibrayev R. A. Study of Sensitivity of the Algorithm for Assimilating Small Amount of Data in the Ocean Dynamics Model // Morskoy gidrofizicheskiy zhurnal. — 2019. — Vol. 35, no. 2. — DOI:https://doi.org/10.22449/0233-7584-2019-2-105-113.
18. Koshlyakov M. N., Tarakanov R. Y. Introduction to Physical Oceanography. — Moscow : MIPT, 2014. — 142 p
19. Krause A., Singh A., Guestrin C. Near-optimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies // Journal of Machine Learning Research. — 2008. — Vol. 9, no. 2.
20. Kumar P., El Sayed Y. M., Semaan R. Optimized sensor placement using stochastic estimation for a flow over a 2D airfoil with Coanda blowing // 7th AIAA Flow Control Conference. — American Institute of Aeronautics, Astronautics, 2014. — DOI:https://doi.org/10.2514/6.2014-2101.
21. Lavergne T., Sørensen A. M., Kern S., et al. Version 2 of the EUMETSAT OSI SAF and ESA CCI sea-ice concentration climate data records // The Cryosphere. — 2019. — Vol. 13, no. 1. — P. 49–78. — DOI:https://doi.org/10.5194/tc-13-49-2019.
22. Li X., Wang S., Cai Y. Tutorial: Complexity analysis of Singular Value Decomposition and its variants // Cornell University. — 2019. — Vol. abs/1906.12085. — DOI:https://doi.org/10.48550/arXiv.1906.12085.
23. Lobashev A. A., Turko N. A., Ushakov K. V., et al. Concrete Autoencoder for the Reconstruction of Sea Temperature Field from Sparse Measurements // Journal of Marine Science and Engineering. — 2023. — Vol. 11, no. 2. — P. 404. — DOI:https://doi.org/10.3390/jmse11020404.
24. Maddison C. J., Mnih A., Teh Y. W. The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables // Cornell University. — 2016. — Vol. abs/1611.00712. — DOI:https://doi.org/10.48550/arXiv.1611.00712.
25. Manohar K., Brunton B. W., Kutz J. N., et al. Data-Driven Sparse Sensor Placement for Reconstruction: Demonstrating the Benefits of Exploiting Known Patterns // IEEE Control Systems. — 2018. — Vol. 38, no. 3. — P. 63–86. — DOI:https://doi.org/10.1109/MCS.2018.2810460.
26. Murray R. J. Explicit Generation of Orthogonal Grids for Ocean Models // Journal of Computational Physics. — 1996. — Vol. 126, no. 2. — P. 251–273. — DOI:https://doi.org/10.1006/jcph.1996.0136.
27. Nagata T., Nonomura T., Nakai K., et al. Data-Driven Sparse Sensor Selection Based on A-Optimal Design of Experiment with ADMM // IEEE Sensors Journal. — 2021. — Vol. 21, no. 13. — P. 15248–15257. — DOI:https://doi.org/10.1109/JSEN.2021.3073978.
28. Nakai K., Yamada K., Nagata T., et al. Effect of Objective Function on Data-Driven Greedy Sparse Sensor Optimization // IEEE Access. — 2021. — Vol. 9. — P. 46731–46743. — DOI:https://doi.org/10.1109/ACCESS.2021.3067712.
29. Nguyen L., Hu G., Spanos C. J. Efficient Sensor Deployments for Spatio-Temporal Environmental Monitoring // IEEE Transactions on Systems, Man, and Cybernetics: Systems. — 2020. — Vol. 50, no. 12. — P. 5306–5316. — DOI:https://doi.org/10.1109/TSMC.2018.2872041.
30. Pathak J., Subramanian S., Harrington P., et al. FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators // Cornell University. — 2022. — Vol. abs/2202.11214. — DOI:https://doi.org/10.48550/arXiv.2202.11214.
31. Ryan A. G., Regnier C., Divakaran P., et al. GODAE OceanView Class 4 forecast verification framework: global ocean inter-comparison // Journal of Operational Oceanography. — 2015. — Vol. 8, sup1. — s98–s111. — DOI:https://doi.org/10.1080/1755876X.2015.1022330.
32. Saito Y., Nonomura T., Yamada K., et al. Determinant-Based Fast Greedy Sensor Selection Algorithm // IEEE Access. — 2021. — Vol. 9. — P. 68535–68551. — DOI:https://doi.org/10.1109/ACCESS.2021.3076186.
33. Sallée J.-B., Pellichero V., Akhoudas C., et al. Summertime increases in upper-ocean stratification and mixed-layer depth // Nature. — 2021. — Vol. 591, no. 7851. — P. 592–598. — DOI:https://doi.org/10.1038/s41586-021-03303-x.
34. Sun S., Liu S., Liu J., et al. Wind Field Reconstruction Using Inverse Process With Optimal Sensor Placement // IEEE Transactions on Sustainable Energy. — 2019. — Vol. 10, no. 3. — P. 1290–1299. — DOI:https://doi.org/10.1109/TSTE.2018.2865512.
35. Turko N., Lobashev A., Ushakov K., et al. Information Entropy Initialized Concrete Autoencoder for Optimal Sensor Placement and Reconstruction of Geophysical Fields // Supercomputing. — Springer International Publishing, 2022. — P. 167–184. — DOI:https://doi.org/10.1007/978-3-031-22941-1_12.
36. Turpin V., Remy E., Traon P. Y. L. How essential are Argo observations to constrain a global ocean data assimilation system? // Ocean Science. — 2016. — Vol. 12, no. 1. — P. 257–274. — DOI:https://doi.org/10.5194/os-12-257-2016.
37. Ushakov K. V., Ibrayev R. A. Assessment of mean world ocean meridional heat transport characteristics by a high-resolution model // Russian Journal of Earth Sciences. — 2018. — Vol. 18, no. 1. — DOI:https://doi.org/10.2205/2018ES000616.
38. Wong A. P. S., Wijffels S. E., Riser S. C., et al. Argo Data 1999–2019: Two Million Temperature-Salinity Profiles and Subsurface Velocity Observations From a Global Array of Profiling Floats // Frontiers in Marine Science. — 2020. — Vol. 7. — DOI:https://doi.org/10.3389/fmars.2020.00700.
