Articles | Volume 16, issue 9
Development and technical paper
05 May 2023
Development and technical paper |  | 05 May 2023

Emulating aerosol optics with randomly generated neural networks

Andrew Geiss, Po-Lun Ma, Balwinder Singh, and Joseph C. Hardin

Related authors

NeuralMie (v1.0): An Aerosol Optics Emulator
Andrew Geiss and Po-Lun Ma
Geosci. Model Dev. Discuss.,,, 2024
Preprint under review for GMD
Short summary
Downscaling atmospheric chemistry simulations with physically consistent deep learning
Andrew Geiss, Sam J. Silva, and Joseph C. Hardin
Geosci. Model Dev., 15, 6677–6694,,, 2022
Short summary
Inpainting radar missing data regions with deep learning
Andrew Geiss and Joseph C. Hardin
Atmos. Meas. Tech., 14, 7729–7747,,, 2021
Short summary
Cloud responses to climate variability over the extratropical oceans as observed by MISR and MODIS
Andrew Geiss and Roger Marchand
Atmos. Chem. Phys., 19, 7547–7565,,, 2019
Short summary

Related subject area

Atmospheric sciences
Efficient and stable coupling of the SuperdropNet deep-learning-based cloud microphysics (v0.1.0) with the ICON climate and weather model (v2.6.5)
Caroline Arnold, Shivani Sharma, Tobias Weigel, and David S. Greenberg
Geosci. Model Dev., 17, 4017–4029,,, 2024
Short summary
Three-dimensional variational assimilation with a multivariate background error covariance for the Model for Prediction Across Scales – Atmosphere with the Joint Effort for Data assimilation Integration (JEDI-MPAS 2.0.0-beta)
Byoung-Joo Jung, Benjamin Ménétrier, Chris Snyder, Zhiquan Liu, Jonathan J. Guerrette, Junmei Ban, Ivette Hernández Baños, Yonggang G. Yu, and William C. Skamarock
Geosci. Model Dev., 17, 3879–3895,,, 2024
Short summary
FUME 2.0 – Flexible Universal processor for Modeling Emissions
Michal Belda, Nina Benešová, Jaroslav Resler, Peter Huszár, Ondřej Vlček, Pavel Krč, Jan Karlický, Pavel Juruš, and Kryštof Eben
Geosci. Model Dev., 17, 3867–3878,,, 2024
Short summary
DEUCE v1.0: a neural network for probabilistic precipitation nowcasting with aleatoric and epistemic uncertainties
Bent Harnist, Seppo Pulkkinen, and Terhi Mäkinen
Geosci. Model Dev., 17, 3839–3866,,, 2024
Short summary
Evaluation of multi-season convection-permitting atmosphere – mixed-layer ocean simulations of the Maritime Continent
Emma Howard, Steven Woolnough, Nicholas Klingaman, Daniel Shipley, Claudio Sanchez, Simon C. Peatman, Cathryn E. Birch, and Adrian J. Matthews
Geosci. Model Dev., 17, 3815–3837,,, 2024
Short summary

Cited articles

Albrecht, B. A.: Aerosols, cloud microphysics, and fractional cloudiness, Science, 245, 1227–1230, 1989. a
Angeline, P., Saunders, G., and Pollack, J.: An evolutionary algorithm that constructs recurrent neural networks, IEEE T. Neural Networ., 5, 54–65,, 1994. a
Baker, B., Gupta, O., Naik, N., and Raskar, R.: Designing Neural Network Architectures using Reinforcement Learning, ArXiv [preprint],, 2017. a
Bellouin, N., Quaas, J., Gryspeerdt, E., Kinne, S., Stier, P., Watson-Parris, D., Boucher, O., Carslaw, K. S., Christensen, M., Daniau, A.-L., Dufresne, J.-L., Feingold, G., Fiedler, S., Forster, P., Gettelman, A., Haywood, J. M., Lohmann, U., Malavelle, F., Mauritsen, T., McCoy, D. T., Myhre, G., Mülmenstädt, J., Neubauer, D., Possner, A., Rugenstein, M., Sato, Y., Schulz, M., Schwartz, S. E., Sourdeval, O., Storelvmo, T., Toll, V., Winker, D., and Stevens, B.: Bounding global aerosol radiative forcing of climate change, Rev. Geophys., 58, e2019RG000660,, 2020. a, b
Bergstra, J., Yamins, D., and Cox, D.: Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures, in: Proceedings of the 30th International Conference on Machine Learning, edited by: Dasgupta, S. and McAllester, D., Proceedings of Machine Learning Research, Atlanta, Georgia, USA, Vol. 28, 115–123,, 2013. a
Short summary
Atmospheric aerosols play a critical role in Earth's climate, but it is too computationally expensive to directly model their interaction with radiation in climate simulations. This work develops a new neural-network-based parameterization of aerosol optical properties for use in the Energy Exascale Earth System Model that is much more accurate than the current one; it also introduces a unique model optimization method that involves randomly generating neural network architectures.