Iranian Journal of Geophysics

Iranian Journal of Geophysics

Application of convolutional neural network for source parameterization of inertia–gravity waves at lower stratosphere

Document Type : Research Article

Authors
Elahe Khanlari 1
Alireza Mohebalhojeh 2
Mohammad Mirzaei 3
Mozhgan Amiramjadi 4
1 M.Sc., Institute of geophysics, University of Tehran, Tehran, Iran
2 Professor, Institute of geophysics, University of Tehran, Tehran, Iran
3 Associate Professor, Department of Space Physics, Institute of Geophysics, University of Tehran
4 Researcher, Karlsruhe Institute of Technology, Karlsruhe, Germany
10.30499/ijg.2026.581841.1773
Abstract
Explicit representation of inertia–gravity waves in general circulation models is not yet feasible due to their small scale relative to the spatial resolution of the models. With enhancement of technology in recent decades, there has been a significant interest in applying machine learning (ML) to improve the performance of general circulation models (GCMs). This research investigates the performance of Convolutional Neural Network (CNN) as a non-parametric model in reconstructing nonorographic gravity waves in mid-latitude oceanic regions using the ERA5 reanalysis data. This data set with low-resolution of 2.5° × 2.5° for predictor variables and with high-resolution of 0.25° × 0.25° for predictand variables have been selected to quantify the characteristics of gravity waves. The explanatory variables employed at 15 pressure levels are representative of gravity waves sources. These variables include temperature gradient, potential vorticity, potential vorticity anomaly, relative vorticity, pressure vertical velocity, and horizontal wind velocity. On the other hand, for the gravity-wave activity in the lowermost stratosphere, the target variables have been chosen as the standard deviation of three key parameters: horizontal divergence, absolute momentum flux, and vertical velocity at the 100 hPa pressure level. Two approaches have been evaluated; the first approach examined the effect of training data volume while keeping the number of input channels constant at 150 channels, and the second one emphasizes optimizing the number of input channels while keeping the training period constant at three years. The second approach employed three distinct configurations characterized by varying numbers of input channels: 150 channels encompassing all explanatory variables, 15 channels restricted to horizontal wind velocity only, and 42 channels selected based on the most relevant explanatory variables in reconstructing gravity waves. Data from three years—2017, 2018, and 2020—were selected for the training and validation datasets, while data from 2019 were employed for the testing dataset.
The results obtained from predicting the standard deviation of three target variables show that increasing the volume of training data in first approach is able to preserve the spatial structure and intensity of variables more effectively. Examining the results of the second approach showed that the model has low performance using 15 input channels, yet has comparable results with 42 and 150 input channels in expressing the importance of horizontal wind variable to predict target variables. The relatively similar results in the 42- and 150-channel combinations indicate the inherent capability of CNN in identifying less-important variables using appropriate activation function. Despite limitations in predicting extreme events, CNN can detect periods of gravity waves activity properly and potentially reconstructs inertia–gravity waves well. Despite the advantages of using CNN in gravity wave reconstruction, conducting more comprehensive experiments could prepare CNN for operational implementation within climate models.
Keywords
Inertia&ndash
gravity waves, convolutional neural network, parameterization, lower stratosphere, nonorographic gravity waves
Subjects
Amiramjadi, M., Mohebalhojeh, A. R., Mirzaei, M., Zulicke, C., & Plougonven, R. (2020). The spatiotemporal variability of nonorographic gravity wave energy and relation to its source functions. Monthly Weather Review, 148, 4837–4857.
Amiramjadi, M., Plougonven, R., Mohebalhojeh, A. R., & Mirzaei, M. (2023). Using machine learning to estimate nonorographic gravity wave characteristics at source levels. Journal of the Atmospheric Sciences, 80, 419–440.
Bosart, L. F., & Cussen Jr., J. P. (1973). Gravity wave phenomena accompanying East Coast cyclogenesis. Monthly Weather Review, 101, 446–454.
Bosart, L. F., Bracken, W. E., & Seimon, A. (1998). A study of cyclone mesoscale structure with emphasis on a large-amplitude inertia–gravity wave. Monthly Weather Review, 126, 1497–1527.
Buss, S., Hertzog, A., Hostettler, C., Bui, T. P., Lüthi, D., & Wernli, H. (2004). Analysis of a jet stream induced gravity wave associated with an observed ice cloud over Greenland. Atmospheric Chemistry and Physics, 4, 1183–1200.
Dörnbrack, A., Leutbecher, M., Kivi, R., & Kyrö, E. (1999). Mountain-wave-induced record low stratospheric temperatures above northern Scandinavia. Tellus A: Dynamic Meteorology and Oceanography, 51, 951-963.
Eliassen, A., & Palm, E. (1961). On the transfer of energy in stationary mountain waves. Geophysics, 22, 1–23.
Espinosa, Z. I., Sheshadri, A., Cain, G. R., Gerber, E. P., & DallaSanta, K. J. (2022). Machine learning gravity wave parameterization generalizes to capture the QBO and response to increased CO2. Geophysical Research Letters, 49, e2022GL098174.
Gupta, A., Sheshadri, A., Roy, S., & Anantharaj, V. (2025). Offline performance of a nonlocal
 
     deep learning parameterization for climate model representation of atmospheric gravity waves. Journal of Advances in Modeling Earth Systems, 17, e2025MS004977.
Hardiman, S. C., Scaife, A. A., van Niekerk, A., Prudden, R., Owen, A., Adams, S. V., et al. (2023). Machine learning for nonorographic gravity waves in a climate model. Artificial Intelligence for the Earth Systems, 2, e220081.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., et al. (2020). The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146, 1999–2049.
Hitchman, M. A., Maaskant, W., van der Plas, J., Simmons, C. J., & Stratemeier, H. (1999). Cooperative Jahn− Teller interactions in dynamic Copper (II) complexes. Temperature dependence of the crystal structure and EPR spectrum of deuterated ammonium Copper (II) sulfate hexahydrate. Journal of the American Chemical Society, 121, 1488–1501.
Holton, J. (2004). An Introduction to Dynamic Meteorology, Elsevier Academic Press., 531 pp.
Holton, J., Beres, J., & Zhou, X. (2002). On the vertical scale of gravity waves excited by localized thermal forcing, Journal of the Atmospheric Sciences, 59, 2019-2023
Kim, Y. J., Eckermann, S. D., & Chun, H.-Y. (2003). An overview of the past, present and future of gravity-wave drag parametrization for numerical climate and weather prediction models. Atmosphere–Ocean, 41, 65–98.
Koch, S. E. & Dorian, P. B. (1988). A mesoscale gravity wave event observed during CCOPE. Part III: Wave environment and probable source mechanisms. Monthly Weather Review, 116, 2570–2592.
Kühl, S., Dörnbrack, A., Wilms‐Grabe, W., Sinnhuber, B.M., Platt, U., & Wagner, T. (2004). Observational evidence of rapid chlorine activation by mountain waves above northern Scandinavia. Journal of Geophysical Research: Atmospheres, 109, D22309, doi:10.1029/2004JD004797.
Matsuoka, D., Watanabe, S., Sato, K., Kawazoe, S., Yu, W., & Easterbrook, S. (2020). Application of deep learning to estimate atmospheric gravity wave parameters in reanalysis data sets. Geophysical Research Letters, 47, e2020GL089436.
Mirzaei, M., Zülicke, C., Mohebalhojeh, A. R., Ahmadi-Givi, F., & Plougonven, R. (2014). Structure, energy, and parameterization of inertia–gravity waves in dry and moist simulations of a baroclinic wave life cycle. Journal of the Atmospheric Sciences, 71, 2390–2414.
Santurkar, S., Tsipras, D., Ilyas, A., Madry, A. (2018). How does batch normalization help optimization? In: Advances in Neural Information Processing Systems, NeurIPS, 31, 2483–2493.
Sato, K., Watanabet, S., Kawatani, Y., Tomikawa, Y., Miyazaki, K., & Takahashi, M. (2009). On the origins of mesospheric gravity waves. Geophys. Res. Lett., 36, L19801.
Sato, K., Tateno, S., Watanabe, S., & Kawatani, Y. (2012). Gravity wave characteristics in the Southern Hemisphere revealed by a high-resolution middle-atmosphere general circulation model. J. Atmos. Sci., 69, 1378–1396.
Shapiro, M. A. (1981). Frontogenesis and geostrophically forced secondary circulations in the vicinity of jet stream–frontal zone systems., Atmospheric Science, 38, 954–973.
Warner, C. D., & McIntyre, M. E. (1996). On the propagation and dissipation of gravity wave spectra through a realistic middle atmosphere., Journal of the Atmospheric Sciences, 53, 3213–3235.
Warner, T. T. (2010). Numerical Weather and Climate Prediction., Cambridge University Press, 523 pp.
Williams, P. D., Read, P. L., & Haine, T. W. N. (2003). Spontaneous generation and impact of inertia–gravity waves in a stratified, two-layer shear flow. Geophysical Research Letters, 30, 2255, doi:10.1029/2003GL018498, 24.
Iranian Journal of Geophysics
Volume 20, Issue 4
September and October 2026
Pages 95-117

  • Receive Date 16 May 2026
  • Revise Date 06 June 2026
  • Accept Date 09 June 2026
  • First Publish Date 09 June 2026
  • Publish Date 23 July 2026