Climate Machine Learning Applications

Calipso Workshop 2026

Isaac Akanho

ICCS/Cambridge

Jack Atkinson

ICCS/Cambridge

2026-06-04

Teaching Material Recap

Teaching Material Recap

We have learnt the theory behind using:

• ANNs - using input features to make predictions
• CNNs - using image-like data as an input

Considerations

Image-like data

Gravity waves image from Sheridan et al. (2017).
MNIST Images from colah

NB: colah provides an excellent article trying to understand MNIST NNs.

Potential Applications

Applications in geosciences:

See review of Kashinath et al. (2021) and Burgh-Day and Leeuwenburg (2023)

• Emulation of existing parameterisations
  (Espinosa et al. 2022)
  
  
• Data-driven parameterisations
  (Yuval and O’Gorman 2020; Giglio et al. 2018)
  
  
• Downscaling/Upsampling
  (Harris et al. 2022)
  
• Climate Emulators
  (Watt-Meyer et al. 2025; Chapman et al. 2025; Dheeshjith et al. 2025)
  
  

• Time series forecasting
  (Shao et al. 2021)
  
  
• Equation discovery
  (Zanna and Bolton 2020; Ma et al. 2021)
  
  
  
• Complete forecasting
  (Pathak et al. 2022; Bi et al. 2022; Nguyen et al. 2023; Rasp et al. 2024; Kochkov et al. 2024; Nathaniel et al. 2024; Bodnar et al. 2025)
  
  
  

Climate Modelling

Climate models are large, complex, many-part systems.

Paramterisations

• Parameterisations are typically expensive
  • Microphysics and Radiation are top offenders
• Replace parameterisations with NNs
  • emulation of existing parameterisation
    e.g. Espinosa et al. (2022)
  • data-driven parameterisations
    • capture missing physics?
  • train with a high-resolution model
    access the benefits of subgrid model without the cost(?)

• data-driven may suffer from a lack of data for training?

Machine Learning

We typically think of Deep Learning as an end-to-end process;
a black box with an input and an output.

Who’s that Pokémon?

\[\begin{bmatrix}\vdots\\a_{23}\\a_{24}\\a_{25}\\a_{26}\\a_{27}\\\vdots\\\end{bmatrix}=\begin{bmatrix}\vdots\\0\\0\\1\\0\\0\\\vdots\\\end{bmatrix}\] It’s Pikachu!

Neural Net by 3Blue1Brown under fair dealing.
Pikachu © The Pokemon Company, used under fair dealing.

Machine Learning in Science

Neural Net by 3Blue1Brown under fair dealing.
Pikachu © The Pokemon Company, used under fair dealing.

Replacing physics-based components

2 approaches:

• emulation, or
• data-driven.

Additional challenges:

• Physical compatibility
  • Physics-based models have conservation laws
    Required for accuracy and stability
• Language interoperation

Downscaling

• Can we get information for ‘free’?
• Train to predict ‘image’ from coarsened version.
  • Topography?

Image by Earth Lab

Forecasting

• Time-series
  • Recurrent Neural Nets
• Complete weather
  • FourCastNet, Pangu-Weather, ClimaX
  • GraphCast, NeuralGCM, Aurora

Line plot image from Bi et al. (2023)
Global image from NVIDIA FourCastNet

Speaker notes go here.

Differentiable Models

• Online training
  • End-to-end differentiable GCMs
  • Greater stability

Images from Google NeuralGCM

Foundation Models

• Pretrained on large amount of heterogeneous climate datasets
• Aims to learn general purpose representations of dynamic
• Fine tune for specific forecasting tasks
• Examples:
  • ClimaX, Microsoft Aurora
• Limitations
  • Poor accuracy beyond short term forecasts
  • Predict unrealistic dynamics (Chattopadhyay and Hassanzadeh 2023)

Challenges

Training data - considerations

How should we prepare our training data?

• Cyclic data?
  • e.g. diurnal, annual, other
  • use time as an input
  • use a [daily] average

Training data - implications

• A NN only knows as much as its training data.
• How do you predict the 1/100 event? 1/1000 event?
• How do you train for a changing climate?
  • And tipping points?

Image by NASA

Structure/Physics-informed approach

There is a wide variety of ways to structure a Neural Net.

What is the most appropriate for our application.

What are potentiall pitfalls - don’t go in blind with an ML hammer!

Case study of Ukkonen (2022) for emulating radiative transfer:

• Recurrent Neural Network reflects physical propogation,
• and prevents spurious correlations.

Physical Compatibility

Many ML applications in climate science are more complex than other classical applications.

• our ML useage is often not end-to-end
• A stable/accurate offline model will not neccessarily be stable online (Furner et al. 2023).

Your NN is perfectly happy to have ‘negative rain’.

• Even with heavy penalties
• This is not a new problem in numerical parameterisations.
• How is it best to enforce physical constraints in NNs.

Redeployability

How easy is it to redeploy a ML model? - exactly what has it learned?

• Locked to a geographical location?
• Locked to numerical model?
  • Locked to a specific grid!?
• How do we handle inputs from different models?

Interfacing

Replacing physics-based components of larger models (emulation or data-driven) requires care.

• Language interoperation
• Physical compatibility

Mathematical Bridge by cmglee used under CC BY-SA 3.0

Emulation and data-driven is a focus of several of out projects.

Models typically in Fortran ML typically in Python Challenge of interoperation

Interfacing - Possible solutions

Ideally need to:

• Not generate excess additional work for user
  • Not require excess knowledge of computing
  • Minimal learning curve
• Not add excess dependencies
• Be easy to maintain
• Maximise performance

1. No re-writing net after you have already done and trained
2. For scientists doing science, not compsci
3. Run on HPC environments so minimal additional
4. Easily keep up to date
5. Simple to learn and deploy
6. Needs to be as efficient as possible

Interfacing - Possible solutions

• Implement a NN in Fortran
• Forpy/CFFI
• SmartSim/Pipes
• Fortran-Keras Bridge

Interfacing - Our Solution

Python
env

Python
runtime

xkcd #1987 by Randall Munroe, used under CC BY-NC 2.5

Interfacing - Our Solution

Ftorch and TF-lib

• Use Fortran’s intrinsic C-bindings to access the C/C++ APIs provided by ML frameworks
• Performance
• Ease of use
• Use frameworks’ implementations directly

MOTIVATION Driven by disadvantages of the above. Make it quick and easy for researchers to correctly deploy their models.

• intrinsic => readily available
• highly functional

Interfacing - Our Solution

Ftorch and TF-lib

• Use Fortran’s intrinsic C-bindings to access the C/C++ APIs provided by ML frameworks
• Performance
  • avoids python runtime
  • no-copy transfer (shared memory)
• Ease of use
• Use frameworks’ implementations directly

Copying is one of the most expensive operations you can do. Avoid this!

Interfacing - Our Solution

Ftorch and TF-lib

• Use Fortran’s intrinsic C-bindings to access the C/C++ APIs provided by ML frameworks
• Performance
• Ease of use
  • pleasant API (see next slides)
  • utilities for generating TorchScript/TF module provided
  • examples provided
• Use frameworks’ implementations directly

Interfacing - Our Solution

Ftorch and TF-lib

• Use Fortran’s intrinsic C-bindings to access the C/C++ APIs provided by ML frameworks
• Performance
• Ease of use
• Use frameworks’ implementations directly
  • feature support
  • future support
  • direct translation of python models ¹

• NB Currently inference only - build and train in python

1. Caveats exist if using exotic non-Torch features.

Code Example - PyTorch

• Take model file
• Save as torchscript

import torch
import my_ml_model

trained_model = my_ml_model.initialize()
scripted_model = torch.jit.script(model)
scripted_model.save("my_torchscript_model.pt")

Code Example - PyTorch

Neccessary imports:

use, intrinsic :: iso_c_binding, only: c_int64_t, c_float, c_char, &
                                       c_null_char, c_ptr, c_loc
use ftorch

Loading a pytorch model:

model = torch_module_load('/path/to/saved/model.pt'//c_null_char)

Code Example - PyTorch

Tensor creation from Fortran arrays:

! Fortran variables
real, dimension(:,:), target  :: SST, model_output
! C/Torch variables
integer(c_int), parameter :: dims_T = 2
integer(c_int64_t) :: shape_T(dims_T)
integer(c_int), parameter :: n_inputs = 1
type(torch_tensor), dimension(n_inputs), target :: model_inputs
type(torch_tensor) :: model_output_T

shape_T = shape(SST)

model_inputs(1) = torch_tensor_from_blob(c_loc(SST), dims_T, shape_T &
                                         torch_kFloat64, torch_kCPU)

model_output = torch_tensor_from_blob(c_loc(output), dims_T, shape_T, &
                                      torch_kFloat64, torch_kCPU)

Code Example - PyTorch

Running the model

call torch_module_forward(model, model_inputs, n_inputs, model_output_T)

Cleaning up:

call torch_tensor_delete(model_inputs(1))
call torch_module_delete(model)

We recommend PT TF has a weakness that prior knowledge of model structure is required.

Further information

References

Bi, Kaifeng, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, and Qi Tian. 2022. “Pangu-Weather: A 3d High-Resolution Model for Fast and Accurate Global Weather Forecast.” arXiv Preprint arXiv:2211.02556.

Bi, Kaifeng, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, and Qi Tian. 2023. “Accurate Medium-Range Global Weather Forecasting with 3D Neural Networks.” Nature, 1–6.

Bodnar, Cristian, Wessel P Bruinsma, Ana Lucic, et al. 2025. “A Foundation Model for the Earth System.” Nature, 1–8.

Burgh-Day, C. O. de, and T. Leeuwenburg. 2023. “Machine Learning for Numerical Weather and Climate Modelling: A Review.” Geoscientific Model Development 16 (22): 6433–77. https://doi.org/10.5194/gmd-16-6433-2023.

Chapman, William E, John S Schreck, Yingkai Sha, et al. 2025. “CAMulator: Fast Emulation of the Community Atmosphere Model.” arXiv Preprint arXiv:2504.06007.

Chattopadhyay, Ashesh, and Pedram Hassanzadeh. 2023. “Long-Term Instabilities of Deep Learning-Based Digital Twins of the Climate System: The Cause and a Solution.” arXiv Preprint arXiv:2304.07029.

Dheeshjith, Surya, Adam Subel, Alistair Adcroft, et al. 2025. “Samudra: An AI Global Ocean Emulator for Climate.” Geophysical Research Letters 52 (10). https://doi.org/10.1029/2024gl114318.

Espinosa, Zachary I, Aditi Sheshadri, Gerald R Cain, Edwin P Gerber, and Kevin J DallaSanta. 2022. “Machine Learning Gravity Wave Parameterization Generalizes to Capture the QBO and Response to Increased CO2.” Geophysical Research Letters 49 (8): e2022GL098174.

Furner, Rachel, Peter Haynes, Dave Munday, Brooks Paige, Emily Shuckburgh, et al. 2023. “An Iterative Data-Driven Emulator of an Ocean General Circulation Model.” Unpublished manuscript.

Giglio, Donata, Vyacheslav Lyubchich, and Matthew R Mazloff. 2018. “Estimating Oxygen in the Southern Ocean Using Argo Temperature and Salinity.” Journal of Geophysical Research: Oceans 123 (6): 4280–97.

Harris, Lucy, Andrew TT McRae, Matthew Chantry, Peter D Dueben, and Tim N Palmer. 2022. “A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts.” Journal of Advances in Modeling Earth Systems 14 (10): e2022MS003120.

Kashinath, Karthik, M Mustafa, Adrian Albert, et al. 2021. “Physics-Informed Machine Learning: Case Studies for Weather and Climate Modelling.” Philosophical Transactions of the Royal Society A 379 (2194): 20200093.

Kochkov, Dmitrii, Janni Yuval, Ian Langmore, et al. 2024. “Neural General Circulation Models for Weather and Climate.” Nature 632 (8027): 1060–66. https://doi.org/10.1038/s41586-024-07744-y.

Ma, Donglai, Jacob Bortnik, Edurado Alves, Enrico Camporeale, Xiangning Chu, and Adam Kellerman. 2021. “Data-Driven Discovery of the Governing Equations Describing Radiation Belt Dynamics.” AGU Fall Meeting Abstracts 2021: SA15B–1928.

Nathaniel, Juan, Yongquan Qu, Tung Nguyen, et al. 2024. “Chaosbench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction.” Advances in Neural Information Processing Systems 37: 43715–29.

Nguyen, Tung, Johannes Brandstetter, Ashish Kapoor, Jayesh K Gupta, and Aditya Grover. 2023. “Climax: A Foundation Model for Weather and Climate.” arXiv Preprint arXiv:2301.10343.

Pathak, Jaideep, Shashank Subramanian, Peter Harrington, et al. 2022. “Fourcastnet: A Global Data-Driven High-Resolution Weather Model Using Adaptive Fourier Neural Operators.” arXiv Preprint arXiv:2202.11214.

Rasp, Stephan, Stephan Hoyer, Alexander Merose, et al. 2024. “WeatherBench 2: A Benchmark for the Next Generation of Data-Driven Global Weather Models.” Journal of Advances in Modeling Earth Systems 16 (6): e2023MS004019.

Shao, Qi, Wei Li, Guijun Han, et al. 2021. “A Deep Learning Model for Forecasting Sea Surface Height Anomalies and Temperatures in the South China Sea.” Journal of Geophysical Research: Oceans 126 (7): e2021JC017515.

Sheridan, Peter, Simon Vosper, and Philip Brown. 2017. “Mountain Waves in High Resolution Forecast Models: Automated Diagnostics of Wave Severity and Impact on Surface Winds.” Atmosphere 8 (1): 24.

Ukkonen, Peter. 2022. “Exploring Pathways to More Accurate Machine Learning Emulation of Atmospheric Radiative Transfer.” Journal of Advances in Modeling Earth Systems 14 (4): e2021MS002875.

Watt-Meyer, Oliver, Brian Henn, Jeremy McGibbon, et al. 2025. “ACE2: Accurately Learning Subseasonal to Decadal Atmospheric Variability and Forced Responses.” Npj Climate and Atmospheric Science 8 (1): 205.

Yuval, Janni, and Paul A O’Gorman. 2020. “Stable Machine-Learning Parameterization of Subgrid Processes for Climate Modeling at a Range of Resolutions.” Nature Communications 11 (1): 3295.

Zanna, Laure, and Thomas Bolton. 2020. “Data-Driven Equation Discovery of Ocean Mesoscale Closures.” Geophysical Research Letters 47 (17): e2020GL088376.

Slides

These slides can be viewed at:
https://cambridge-iccs.github.io/practical-ml-with-pytorch

The html and source can be found on GitHub.

Contact

For more information we can be reached at:

 Isaac Akanho

 ICCS/UoCambridge

 ia464[AT]cam.ac.uk

 Jack Atkinson

 ICCS/UoCambridge

 jwa34[AT]cam.ac.uk