Literature

Some Literature that might be useful

CNRS
MEOM

Research Questions

This is inspired by the talk by Steve Penny - Recording | Slides

Reanalysis vs Simulations vs Observations

Observations and Reanalysis are inherently imperfect data sources with often uncharacterized uncertainties.

  • Q1: Are reanalysis datasets an adequate source of training data for ML?
  • Q2: Are pure simulation datasets more effective data for ML?
  • Q3: How will biases & systematic errors be handled?
  • Q4: Can we learn directly from observations plus basic physics constraints?

Reanalysis-Based

Simulation-Based

PINNS in the Wild

[Agarwal et al., 2022]

Hybrid Models

As numerical Forecasts are modernized (e.g. written in new languages that support differentiation, and designed to take advantage of GPUs), can AI/ML solutions maintain a competitive edge (in terms of computational cost) over conventional modeling.

[Belochitski & Krasnopolsky (2021)Dresdner et al. (2022)Frerix et al. (2021)Kochkov et al. (2021)]

Model Error Estimation

How much State Dependent (Conventional) Model error can we learn from comparison with observations? How do we separate system observation errors from systematic model forecast errors?

[Bonavita & Laloyaux (2022)Laloyaux et al. (2022)Pathak et al. (2018)Arcomano et al. (2022)]

Subgrid Parameterization

This is an instance of

[Frezat et al., 2022]

Better Metrics

[Frezat et al., 2021]


Operational Center

Observation Datasets

AlongTack

In-Situ

Extrapolation Datasets

Forecast

HindCast

Reanalysis Datasets


Applications

Plants n Things

Water n Things


Data Assimilation

Algorithms

Back-and-Forth Nudging

References
  1. Agarwal, A., Meijer, V. R., Eastham, S. D., Speth, R. L., & Barrett, S. R. H. (2022). Reanalysis-driven simulations may overestimate persistent contrail formation by 100%–250%. Environmental Research Letters, 17(1), 014045. 10.1088/1748-9326/ac38d9
  2. Belochitski, A., & Krasnopolsky, V. (2021). Robustness of neural network emulations of radiative transfer parameterizations in a state-of-the-art general circulation model. Geoscientific Model Development, 14(12), 7425–7437. 10.5194/gmd-14-7425-2021
  3. Dresdner, G., Kochkov, D., Norgaard, P., Zepeda-Núñez, L., Smith, J. A., Brenner, M. P., & Hoyer, S. (2022). Learning to correct spectral methods for simulating turbulent flows. arXiv. 10.48550/ARXIV.2207.00556
  4. Frerix, T., Kochkov, D., Smith, J. A., Cremers, D., Brenner, M. P., & Hoyer, S. (2021). Variational Data Assimilation with a Learned Inverse Observation Operator. arXiv. 10.48550/ARXIV.2102.11192
  5. Kochkov, D., Smith, J. A., Alieva, A., Wang, Q., Brenner, M. P., & Hoyer, S. (2021). Machine learning–accelerated computational fluid dynamics. Proceedings of the National Academy of Sciences, 118(21). 10.1073/pnas.2101784118