Articles | Volume 13, issue 9
Geosci. Model Dev., 13, 4399–4412, 2020
Geosci. Model Dev., 13, 4399–4412, 2020

Model description paper 21 Sep 2020

Model description paper | 21 Sep 2020

RadNet 1.0: exploring deep learning architectures for longwave radiative transfer

Ying Liu et al.

Related authors

Interaction between Atlantic cyclones and Eurasian atmospheric blocking drives wintertime warm extremes in the high Arctic
Sonja Murto, Rodrigo Caballero, Gunilla Svensson, and Lukas Papritz
Weather Clim. Dynam., 3, 21–44,,, 2022
Short summary
sympl (v. 0.4.0) and climt (v. 0.15.3) – towards a flexible framework for building model hierarchies in Python
Joy Merwin Monteiro, Jeremy McGibbon, and Rodrigo Caballero
Geosci. Model Dev., 11, 3781–3794,,, 2018
Short summary
Climate sensitivity and meridional overturning circulation in the late Eocene using GFDL CM2.1
David K. Hutchinson, Agatha M. de Boer, Helen K. Coxall, Rodrigo Caballero, Johan Nilsson, and Michiel Baatsen
Clim. Past, 14, 789–810,,, 2018
Short summary
Atmospheric circulation and hydroclimate impacts of alternative warming scenarios for the Eocene
Henrik Carlson and Rodrigo Caballero
Clim. Past, 13, 1037–1048,,, 2017
Short summary
The DeepMIP contribution to PMIP4: experimental design for model simulations of the EECO, PETM, and pre-PETM (version 1.0)
Daniel J. Lunt, Matthew Huber, Eleni Anagnostou, Michiel L. J. Baatsen, Rodrigo Caballero, Rob DeConto, Henk A. Dijkstra, Yannick Donnadieu, David Evans, Ran Feng, Gavin L. Foster, Ed Gasson, Anna S. von der Heydt, Chris J. Hollis, Gordon N. Inglis, Stephen M. Jones, Jeff Kiehl, Sandy Kirtland Turner, Robert L. Korty, Reinhardt Kozdon, Srinath Krishnan, Jean-Baptiste Ladant, Petra Langebroek, Caroline H. Lear, Allegra N. LeGrande, Kate Littler, Paul Markwick, Bette Otto-Bliesner, Paul Pearson, Christopher J. Poulsen, Ulrich Salzmann, Christine Shields, Kathryn Snell, Michael Stärz, James Super, Clay Tabor, Jessica E. Tierney, Gregory J. L. Tourte, Aradhna Tripati, Garland R. Upchurch, Bridget S. Wade, Scott L. Wing, Arne M. E. Winguth, Nicky M. Wright, James C. Zachos, and Richard E. Zeebe
Geosci. Model Dev., 10, 889–901,,, 2017
Short summary

Related subject area

Climate and Earth system modeling
ChAP 1.0: a stationary tropospheric sulfur cycle for Earth system models of intermediate complexity
Alexey V. Eliseev, Rustam D. Gizatullin, and Alexandr V. Timazhev
Geosci. Model Dev., 14, 7725–7747,,, 2021
Short summary
Non-Hydrostatic RegCM4 (RegCM4-NH): model description and case studies over multiple domains
Erika Coppola, Paolo Stocchi, Emanuela Pichelli, Jose Abraham Torres Alavez, Russell Glazer, Graziano Giuliani, Fabio Di Sante, Rita Nogherotto, and Filippo Giorgi
Geosci. Model Dev., 14, 7705–7723,,, 2021
Short summary
Robustness of neural network emulations of radiative transfer parameterizations in a state-of-the-art general circulation model
Alexei Belochitski and Vladimir Krasnopolsky
Geosci. Model Dev., 14, 7425–7437,,, 2021
Short summary
NorCPM1 and its contribution to CMIP6 DCPP
Ingo Bethke, Yiguo Wang, François Counillon, Noel Keenlyside, Madlen Kimmritz, Filippa Fransner, Annette Samuelsen, Helene Langehaug, Lea Svendsen, Ping-Gin Chiu, Leilane Passos, Mats Bentsen, Chuncheng Guo, Alok Gupta, Jerry Tjiputra, Alf Kirkevåg, Dirk Olivié, Øyvind Seland, Julie Solsvik Vågane, Yuanchao Fan, and Tor Eldevik
Geosci. Model Dev., 14, 7073–7116,,, 2021
Short summary
ENSO-ASC 1.0.0: ENSO deep learning forecast model with a multivariate air–sea coupler
Bin Mu, Bo Qin, and Shijin Yuan
Geosci. Model Dev., 14, 6977–6999,,, 2021
Short summary

Cited articles

Brenowitz, N. D. and Bretherton, C. S.: Prognostic Validation of a Neural Network Unified Physics Parameterization, Geophys. Res. Lett., 45, 6289–6298,, 2018. a
Brenowitz, N. D. and Bretherton, C. S.: Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-Graining, J. Adv. Model. Earth Sy., 11, 2728–2744,, 2019. a
Chevallier, F., Chéruy, F., Scott, N. A., and Chédin, A.: A Neural Network Approach for a Fast and Accurate Computation of a Longwave Radiative Budget, J. Appl. Meteorol., 37, 1385–1397,<1385:ANNAFA>2.0.CO;2, 1998. a
Chollet, F.: Xception: Deep Learning with Depthwise Separable Convolutions, CoRR, abs/1610.02357, 2016. a
Dee, D. P., Uppala, S. M., Simmons, A. J., Berrisford, P., Poli, P., Kobayashi, S., Andrae, U., Balmaseda, M. A., Balsamo, G., Bauer, P., Bechtold, P., Beljaars, A. C. M., van de Berg, I., Biblot, J., Bormann, N., Delsol, C., Dragani, R., Fuentes, M., Greer, A. J., Haimberger, L., Healy, S. B., Hersbach, H., Holm, E. V., Isaksen, L., Kallberg, P., Kohler, M., Matricardi, M., McNally, A. P., Mong-Sanz, B. M., Morcette, J.-J., Park, B.-K., Peubey, C., de Rosnay, P., Tavolato, C., Thepaut, J. N., and Vitart, F.: The ERA-Interim reanalysis: Configuration and performance of the data assimilation system, Q. J. Roy. Meteorol. Soc., 137, 553–597,, 2011. a, b
Short summary
The calculation of atmospheric radiative transfer is the most computationally expensive part of climate models. Reducing this computational burden could potentially improve our ability to simulate the earth's climate at finer scales. We propose using a statistical model – a deep neural network – to compute approximate radiative transfer in the earth's atmosphere. We demonstrate a significant reduction in computational burden as compared to a traditional scheme, especially when using GPUs.