mlsanityData to 7 Oct 2026

Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: a case study with the Lorenz 96 model

arXiv 2203.14814 ↗First posted 28 Mar 2022cs.LG physics.ao-phcited by 5

Not on the map. Why?

Abstract (arXiv)

The modelling of small-scale processes is a major source of error in climate models, hindering the accuracy of low-cost models which must approximate such processes through parameterization. Red noise is essential to many operational parameterization schemes, helping model temporal correlations. We show how to build on the successes of red noise by combining the known benefits of stochasticity with machine learning. This is done using a physically-informed recurrent neural network within a probabilistic framework. Our model is competitive and often superior to both a bespoke baseline and an existing probabilistic machine learning approach (GAN) when applied to the Lorenz 96 atmospheric simulation. This is due to its superior ability to model temporal patterns compared to standard first-order autoregressive schemes. It also generalises to unseen scenarios. We evaluate across a number of metrics from the literature, and also discuss the benefits of using the probabilistic metric of hold-out likelihood.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 87 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

22 of 87 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  9. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  10. 2015A note on the evaluation of generative modelscited by 291
  11. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  12. 2018Deep learning to represent sub-grid processes in climate modelscited by 156
10 more
  1. 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
  2. 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
  3. 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 132
  4. 2016Hierarchical Multiscale Recurrent Neural Networkscited by 102
  5. 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
  6. 2019Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Modelcited by 45
  7. 2020Hierarchical Deep Learning of Multiscale Differential Equation Time-Stepperscited by 37
  8. 2020Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learningcited by 17
  9. 2020Towards Physically-consistent, Data-driven Models of Convectioncited by 13
  10. 2020Bridging Maximum Likelihood and Adversarial Learning via α-Divergencecited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 2.

5 papers.

  1. 2024Defining error accumulation in ML atmospheric simulatorscited by 5
  2. 2023Taylorformer: Probabilistic Modelling for Random Processes including Time Seriescited by 2
  3. 2024Machine Learning for Stochastic Parametrisationcited by 0
  4. 2026Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizationscited by 0
  5. 2026Learning Prognostic Variables for AI Convective Parameterizations via Symbolic Distillationcited by 0