Review of data assimilation methods for refining the results of pollution dispersion models after accidental releases
DOI:
https://doi.org/10.34121/1028-9763-2025-1-113-123Keywords:
data assimilation, machine learning, neural networks, ensemble Kalman filterAbstract
Data assimilation (DA) is a crucial task in pollution forecasting, as it enables the integration of observations with models, improving the accuracy of pollutant dispersion predictions in the atmosphere, ocean, and land. This is particularly important for assessing the impact of accidental emissions and managing environmental risks. This paper reviews and compares four different data assimilation methods for pollution dispersion following accidental releases. The methods include ensemble-based approaches: the ensemble Kalman filter (EnKF), Ensemble Smoother (ES), and two novel approaches based on machine learning (ML). The mathematical foundations of these methods are justified, and their advantages and drawbacks are analyzed. Ensemble data assimilation methods, particularly EnKF, are computationally efficient and can provide good results even in non-linear models. They require fewer resources compared to classical methods while preserving critical information with a limited ensemble size. However, their drawback is the Gaussian approximation, which can lead to numerical instabilities and non-physical results in problems with non-Gaussian distributions. Additionally, the need for multiple reinitializations can increase computational costs. An alternative is ES, which does not require recursive updates and reduces modeling time but may produce worse results in certain cases, despite its higher computational efficiency. Two hybrid methods that combine data assimilation with machine learning have been examined: the first involves correcting tendencies or resolvents, leveraging a compositional structure that outperforms similar methods without corrections in benchmark problems; the second utilizes a neural network with a non-standard loss function. Both methods have demonstrated the ability to correct model errors and account for biases in forecasts. Hybrid approaches that integrate traditional assimilation techniques with machine learning offer high accuracy while reducing the number of DA-ML cycles.
References
1. Nychka D., Anderson, J.L. Data Assimilation. Handbook of Spatial Statistics / A. Gelfand, P. Diggle, P. Guttorp, M. Fuentes (eds.). New York, NY: Chapman & Hall/CRC, 2010. P. 477–492.
2. Katzfussa M., Stroudb J.R., Wiklec C.K. Understanding the Ensemble Kalman Filter, The american statistician, 2016. Vol. 70., P. 350–357. DOI: https://doi.org/10.1080/00031305.2016.1141709.
3. Kovalets I., Kim K.O., Shrubkovsky O., Maderich V. Ensemble Data Assimilation of Concentration Measurements Following the Accidental. Release of a Contaminant in the Ocean: Method Testing in an Idealized Setting, Pure Appl. Geophys., 2022. DOI: https://doi.org/10.1007/s00024-022-02990-5.
4. Tippett M.K., Cohn S.E., Todling R., Marchesin D. Low-dimensional representation of error covariance. Tellus, 2000. Vol. 52 (A). P. 533–553.
5. Thomas M. Hamill, Ensemble-Based Data Assimilation. NOAA-CIRES Climate Diagnostics Center, Boulder, Colorado USA, 2002. P. 83–123.
6. Sakov P., Oke P.R. A deterministic formulation of the ensemble Kalman filter: an alternative to ensemble square root filters. Tellus, 2008. Vol. 60A. Р. 361–371.
7. A comprehensive review on ensemble deep learning: Opportunities and challenges, Ammar Mohammed and Rania Kor. Journal of King Saud University – Computer and Information Sciences. 2023. P. 757–774. DOI: https://doi.org/10.1016/j.jksuci.2023.01.014.
8. Evensen G. Sequential data assimilation with a nonlinear quasi-geostrophic model using Monte Carlo methods to forecast error statistics. Journal of Geophysical Research: Oceans. 1994. N 99 (C5). Р. 10143–10162.
9. Kalman R.E. A new approach to linear filtering and prediction problems. Journal of Basic Engineering. 1960. Vol. 82 (1). P. 35–45. DOI: https://doi.org/10.1115/1.3662552.
10. Snyder C., Bengtsson T., Bickel P., Anderson J.L. Obstacles to High-dimensional Particle Filtering. MonthlyWeather Review. 2008. N 136. P. 4629–4640.
11. Liu N., Oliver D.S. Critical Evaluation of the Ensemble Kalman Filter on History Matching of Geologic Facies. SPE Journal. 2005. N 6 (3). P. 344–367.
12. Xiaoyang Xia History-matching production data using ensemble smoother with multiple data assimilation: a comparative study, 2014. P. 1–78.
13. Daley R. Atmospheric data analysis. Cambridge University Press, 1991. P. 98–180.
14. Evensen G. Data Assimilation. The Ensemble Kalman Filter. Springer-Verlag, 2009. P. 71–92.
15. Stommel H. The westward intensification of wind-driven ocean currents. Transactions American Geophysical Union. 1948. Vol. 29 (2). P. 202–206.
16. Lawson C.R., Hanson R.J. Solving least squares problems. SIAM. 1995. P. 100–103.
17. Peter Jan Van Leeuwen, Data assimilation and inverse methods in terms of a probabilistic formulation. Monthly Weather Review. 1996. Vol. 124. P. 2898–2913.
18. Skjervheim J., Evensen G. An Ensemble Smoother for Assisted History Matching. SPE Journal. 2011. Vol. 5 (2). P. 412–423.
19. Pathak J., Subramanian S., Harrington P., Raja S., Chattopadhyay A., Mardani M., Kurth T., Hall D., Li Z., Azizzadenesheli K., Hassanzadeh P., Kashinath K., Anandkumar A. FourCastNet: A global datadriven high-resolution weather model using adaptive Fourier neural operators. 2022. URL: https://arxiv.org/abs/2202.11214.
20. Fan Z., Ghaddar B., Wang X., Xing L., Zhang Y., Zhou Z. Artificial intelligence for operations research: Revolutionizing the operations research process, 2024. P. 1–47. DOI: https://doi.org/ 10.48550/arXiv.2401.03244.
21. Jia X., Willard J., Karpatne A., Read J., Zwart J., Steinbach M., Kumar V. Physics guided RNNs for modeling dynamical systems: A case study in simulating lake temperature profiles. Proc. of the 2019 SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics. Philadelphia, PA, 2019. P. 558, 566. DOI: http://dx.doi.org/10.1137/1.9781611975673.
22. Watson P.A.G. Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction. Journal of Advances in Modeling Earth Systems. 2019. Vol. 11 (5). P. 1402–1417. DOI: https://doi.org/10.1029/2018MS001597.
23. Hsieh W.W., Tang B. Applying neural network models to prediction and data analysis in meteorology and oceanography. Bulletin of the American Meteorological Society. 1998. Vol. 79 (9). P. 1855–1870. DOI: https://doi.org/10.1175/1520-0477(1998)079<1855:ANNMTP>2.0.CO;2.
ISSN 1028-9763. Математичні машини і системи. 2025. № 1 123
24. Abarbanel H.D.I., Rozdeba P.J., Shirman S. Machine learning: Deepest learning as statistical data assimilation problems. Neural Computation. 2018. Vol. 30 (8). P. 2025–2055. DOI: https://doi.org/10.1162/neco_a_01094.
25. Bocquet M., Brajard J., Carrassi A., Bertino L. Data assimilation as a learning tool to infer ordinary differential equation representations of dynamical models. Nonlinear Processes in Geophysics. 2019. Vol. 26 (3). P. 143–162. DOI: https://doi.org/10.5194/npg-26-143-2019.
26. Bocquet M., Brajard J., Carrassi A., Bertino L. Bayesian inference of chaotic dynamics by merging data assimilation, machine learning. arXiv:2001.06270, 2020. P. 1–27. DOI: https://doi.org/10.48550/arXiv.2001.06270.
27. Farchi A., Bocquet M., Laloyaux P., Bonavita M., Malartic Q. A comparison of combined data assimilation and machine learning methods for offline and online model error correction. Journal of Computational Science. 2021. Vol. 55. P. 101468. URL: https://doi.org/10.1016/j.jocs.2021.101468.
28. Farchi A., Laloyaux P., Bonavita M., Bocquet M. Using machine learning to correct model error in data assimilation and forecast applications. Quarterly Journal of the Royal Meteorological Society. 2021. Vol. 147 (739). P. 3067–3084. ISSN 1477-870X. DOI: https://doi.org/10.1002/qj.4116. URL: http://dx.doi.org/10.1002/qj.4116.
29. Keller J.D., Potthast R. AI-based data assimilation: Learning the functional of analysis estimation. arXiv:2406.00390 [physics.ao-ph], 2024. Р. 1–16. DOI: https://doi.org/10.48550/arXiv.2406.00390.
30. Bollmeyer C., Keller J.D., Ohlwein C., Wahl S., Crewell S., Friederichs P., Hense A., Keune J., Kneifel S., Pscheidt I., Redl S., Steinke S. Towards a high-resolution regional reanalysis for the European CORDEX domain. Quarterly Journal of the Royal Meteorological Society. 2015. Vol. 141 (686). P. 1–15. DOI: https://doi.org/10.1002/qj.2486.
49
16
