Emulating Aerosol Optics with Randomly Generated Neural Networks
Abstract. Atmospheric aerosols have a substantial impact on climate and remain one of the largest sources of uncertainty in climate forecasts. Accurate representation of their direct radiative effects is a crucial component of modern climate models. Direct computation of the radiative properties of aerosols is far too computationally expensive to perform in a climate model however, so optical properties are typically approximated using a parameterization. This work develops artificial neural networks (ANNs) capable of replacing the current aerosol optics parameterization used in the Energy Exascale Earth System Model (E3SM). A large training dataset is generated by using Mie code to directly compute the optical properties of a range of atmospheric aerosol populations given a large variety of particle sizes, wavelengths, and refractive indices. Optimal neural architectures for shortwave and longwave bands are identified by evaluating ANNs with randomly generated wirings. Randomly generated deep ANNs are able to outperform conventional multi-layer perceptron style architectures with comparable parameter counts. Finally, the ANN-based parameterization is found to dramatically outperform the current parameterization. The success of this approach makes possible the future inclusion of much more sophisticated representations of aerosol optics in climate models that cannot be captured through simple expansion of the existing parameterization scheme.
Andrew Geiss et al.
Status: final response (author comments only)
- RC1: 'Comment on egusphere-2022-559', Anonymous Referee #1, 15 Jul 2022
- RC2: 'Comment on egusphere-2022-559', Anonymous Referee #2, 10 Aug 2022
CEC1: 'Comment on egusphere-2022-559', Juan Antonio Añel, 23 Aug 2022
- AC1: 'Reply on CEC1', Andrew Geiss, 06 Oct 2022
Andrew Geiss et al.
Aerosol Optics ML Datasets https://doi.org/10.5281/zenodo.6762700
Model code and software
Aerosol Optics ML Code https://doi.org/10.5281/zenodo.6767169
Andrew Geiss et al.
Viewed (geographical distribution)
This manuscript describes the development of neural networks to replace the aerosol optics in a climate model with a more detailed treatment, which is based on running the same types of codes with more detail to develop a parameterization which better represents more detailed modeling. In general the manuscript is well written and clear. There is a nice discussion of how the neural network is developed. However, my main critique is that the evaluation section (section 5) is pretty minimal. Just some error curves. What does it look like in the full model? You have demonstrated that the new parameterization represents the more detailed code better than the existing parameterization. Does it change the answers in the climate model it is designed for in any meaningful way, and does it cost anything more to run it. Also good to note in the conclusions what lessons you learn from this experience about building neural networks for parameterization replacement. This is probably suitable for publication with minor revisions, but with at least trying it in a climate model perhaps.
Detailed comments below.
Page 1, L10: Would be good to have more detail on what ‘outperform’ means specifically in another sentence or two.
Page 1, L15: Disingenuous. The direct effects of aerosols are not the largest uncertainty: only indirect effects on clouds.
Page 2, L29: Example of climate models generating training data (for replacing part of a parameterization: Gettelman et al 2021.
Gettelman, A., D. J. Gagne, C.-C. Chen, M. W. Christensen, Z. J. Lebo, H. Morrison, and G. Gantos. “Machine Learning the Warm Rain Process.” Journal of Advances in Modeling Earth Systems 13, no. 2 (2021): e2020MS002268. https://doi.org/10.1029/2020MS002268.
Page 3, L63: clarify ‘these optical properties (absorption…etc’
Page 3, L77: what is the size range here? Please be explicit.
Page 3, L90: The CESM reference should probably be Danabasoglu, et al 2020.
Danabasoglu, G., J.-F. Lamarque, J. Bacmeister, D. A. Bailey, A. K. DuVivier, J. Edwards, L. K. Emmons, et al. “The Community Earth System Model Version 2 (CESM2).” Journal of Advances in Modeling Earth Systems 12, no. 2 (2020): e2019MS001916. https://doi.org/10.1029/2019MS001916.
Page 5, L148: how much error is there in the approximations? Can you quantify it?
Page 9, L251: why would a random network do better? Is there an explanation? Isn’t that a form of overfitting?
Page 10, L289: Please describe these terms a bit. ReLU, ELU, Leaky ReLU and Parametric ReLU
Page 10, L291: what is a transfer function? Above you call them activation functions. Please clarify.
Page 11, Figure 2: is the red dot the ‘optimum’ network?
Page 12, L350: can you make the evaluation a bit more quantitative in spots? It seems a bit ‘weak’ right now, especially compared to the rest of the paper.
Page 13, L360: What does the first column (Table:) of table 1 mean? Should it say something?
Page 13, L364: Can you explain the patters in Figure 5? What do they arise from?
Page 16, L402: Other lessons learned? It would be great to share in the paper.