pith. sign in

arxiv: 2605.22242 · v1 · pith:B6WC5QBVnew · submitted 2026-05-21 · 💻 cs.LG · physics.ao-ph

Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations

Birgit K\"uhbacher , Daan Crommelin , Niki Kilbertus This is my paper

Pith reviewed 2026-05-22 08:25 UTC · model grok-4.3

classification 💻 cs.LG physics.ao-ph
keywords ensemble forecastingstochastic parameterizationLorenz '96chaotic dynamicsforecast spreadmodel uncertaintyspread-error consistencyweather prediction
0
0 comments X

The pith

Ensemble perturbations regulate trajectory decorrelation rates in Lorenz '96 rather than increasing long-term variance, while persistent stochastic parameterizations improve early spread growth and spread-error consistency.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper examines how ensemble forecasts represent uncertainty in chaotic systems by decomposing contributions from initial conditions and model errors using the two-scale Lorenz '96 model. It establishes that ensemble perturbations primarily affect the rate at which different forecast trajectories diverge and cover the system's possible states, without changing the overall variance in the long run. Stochastic parameterizations that include time-persistent structures accelerate the initial growth of forecast spread and make it align better with actual forecast errors. A sympathetic reader cares because this distinction helps explain underdispersive ensembles in weather prediction and suggests better ways to incorporate model uncertainty. The work provides a controlled testbed to guide improvements in operational forecasting systems.

Core claim

Using the two-scale Lorenz 1996 system, we design a systematic approach to disentangle intrinsic variability, initial-condition perturbations, and stochastic model uncertainty. We compare multiple ensemble configurations and parameterization strategies, including existing deterministic and autoregressive as well as novel Bayesian and flow-based approaches. Our results show that ensemble perturbations do not increase the system's long-term variance; rather, they regulate how rapidly trajectories decorrelate and explore the invariant measure. Stochastic parameterizations, particularly those with temporally persistent structure, enhance early spread growth and improve spread-error consistency.

What carries the argument

Decomposition of ensemble spread into intrinsic variability, initial-condition perturbations, and stochastic model uncertainty by comparing deterministic, autoregressive, Bayesian, and flow-based parameterizations in the two-scale Lorenz '96 system.

If this is right

  • Ensemble perturbations mainly control the speed at which trajectories explore the invariant measure.
  • Temporally persistent stochastic parameterizations accelerate early spread growth.
  • Persistent structures in stochastic terms improve alignment between spread and forecast error.
  • The decomposition offers concrete guidance for designing stochastic parameterizations in operational models.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The emphasis on persistence times suggests that correlation structure of noise terms could be a high-leverage tuning knob in full-scale models.
  • Similar spread-decomposition experiments could be performed in other low-dimensional chaotic systems to test how far the decorrelation mechanism generalizes.
  • Operational ensembles might benefit from replacing white-noise stochastic schemes with ones that carry short-term memory even if total variance is unchanged.

Load-bearing premise

The two-scale Lorenz '96 system is a sufficient controlled testbed whose uncertainty interactions generalize to real weather and climate models.

What would settle it

Running the same decomposition in a higher-fidelity global climate model and finding that ensemble perturbations increase long-term variance or that non-persistent stochastic schemes match persistent ones in spread-error consistency would falsify the central claim.

Figures

Figures reproduced from arXiv: 2605.22242 by Birgit K\"uhbacher, Daan Crommelin, Niki Kilbertus.

Figure 1
Figure 1. Figure 1: Joint distributions of Xk and Uk. The first panel displays the truth. Deterministic and Bayesian models capture only the mean relationship, resulting in a narrow functional fit (the Bayesian posterior is visually indistinguishable from a line). The polynomial+AR(1) parameterization adds a finite-width corridor via temporally correlated noise. For flow models, Uk is sampled conditionally from test states Xk… view at source ↗
Figure 2
Figure 2. Figure 2: Predictability diagnostics of the fully resolved L96 system. Left: growth and saturation of the avg. [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Marginal PDFs of Xk from long integrations (truth in black vs. selected parameterizations in color). 5.1 Sensitivity & Predictability Baseline We first assess the intrinsic predictability of the fully resolved two-scale L96 system. To this end, we compare (a) (Ninit×Nens) integrations from perturbed initial states and (b) Ninit integrations from perfect initial states over 10 MTU. For configuration (a), we… view at source ↗
Figure 4
Figure 4. Figure 4: Invariant-measure variability σ init k (t) and climatological amplitude σclim for truth and reduced models [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Decomposition of total initial state averaged ensemble spread into perturbation-, model-, and [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: RMSE and anomaly correlation (lower RMSE and higher ANCR indicate better forecast skill). [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Spread–error consistency at selected lead times. Left: spread vs. RMSE with the consistency line [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
read the original abstract

Weather and climate forecasts are inherently uncertain due to chaotic dynamics, imperfect initial conditions, and incomplete representation of the underlying physical processes. Operational ensemble forecasts aim to represent these uncertainties through forecast spread, yet many approaches yield underdispersive estimates, with spread that grows too slowly relative to forecast error. Using the two-scale Lorenz 1996 system as a widely used, controlled testbed, we design a systematic approach to disentangle intrinsic variability, initial-condition perturbations, and stochastic model uncertainty. We compare multiple ensemble configurations and parameterization strategies, including existing deterministic and autoregressive as well as novel Bayesian and flow-based approaches. Our results show that ensemble perturbations do not increase the system's long-term variance; rather, they regulate how rapidly trajectories decorrelate and explore the invariant measure. Stochastic parameterizations, particularly those with temporally persistent structure, enhance early spread growth and improve spread-error consistency. Overall, we bring clarity to how different sources of uncertainty interact in a chaotic system and provide guidance for the design and evaluation of stochastic parameterizations in weather and climate models.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper uses the two-scale Lorenz '96 system as a testbed to decompose sources of ensemble spread arising from initial-condition perturbations and different stochastic parameterization strategies (deterministic, autoregressive, Bayesian, and flow-based). It claims that ensemble perturbations regulate the rate at which trajectories decorrelate and explore the invariant measure without increasing long-term variance, and that temporally persistent stochastic parameterizations improve early spread growth and spread-error consistency.

Significance. If the central claims hold, the work offers a controlled, systematic framework for isolating uncertainty contributions in chaotic systems and supplies concrete guidance on the design of stochastic parameterizations for weather and climate ensembles. The explicit comparison across parameterization families and the focus on spread-error diagnostics are strengths that could inform operational ensemble design.

major comments (2)
  1. [Methods and Results sections] The central claim that ensemble perturbations 'do not increase the system's long-term variance' (abstract and results) rests on the implicit assumption that the learned stochastic terms preserve the invariant measure of the reference deterministic system. The manuscript does not state whether the training objectives for the Bayesian and flow-based parameterizations enforce zero conditional mean (or moment matching) with respect to the subgrid forcing; temporally persistent noise can accumulate systematic drifts that alter climatological statistics. Without explicit verification (e.g., comparison of long-term means, variances, or attractor statistics across configurations), the reported invariance of long-term variance could be an artifact of the specific training rather than a general property.
  2. [Experimental setup] The comparison of spread-error consistency across parameterization families would be strengthened by reporting the actual ensemble size, the precise definition of 'spread' (e.g., standard deviation of the ensemble mean or of individual members), and whether error is measured against a high-resolution truth or against the deterministic reference run. These details are necessary to assess whether the reported improvement for persistent stochastic schemes is robust or sensitive to these choices.
minor comments (2)
  1. [Section 2] Notation for the two-scale Lorenz '96 variables (X, Y) and the subgrid forcing term should be introduced once with a clear equation reference and then used consistently; occasional redefinition of symbols reduces readability.
  2. [Figures 3-5] Figure captions should explicitly state the ensemble size, forecast lead time range, and whether shaded regions represent one standard deviation across multiple realizations or across ensemble members.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and positive review. The comments help clarify key aspects of our methodology and results. We address each major comment below and have revised the manuscript to incorporate additional details and verifications.

read point-by-point responses

  1. Referee: [Methods and Results sections] The central claim that ensemble perturbations 'do not increase the system's long-term variance' (abstract and results) rests on the implicit assumption that the learned stochastic terms preserve the invariant measure of the reference deterministic system. The manuscript does not state whether the training objectives for the Bayesian and flow-based parameterizations enforce zero conditional mean (or moment matching) with respect to the subgrid forcing; temporally persistent noise can accumulate systematic drifts that alter climatological statistics. Without explicit verification (e.g., comparison of long-term means, variances, or attractor statistics across configurations), the reported invariance of long-term variance could be an artifact of the specific training rather than a general property.

    Authors: We agree that explicit verification of invariant-measure preservation strengthens the central claim. Our training objectives for the Bayesian and flow-based parameterizations include explicit moment-matching terms that enforce zero conditional mean and variance matching with respect to the subgrid forcing (see Section 3). To address the concern directly, we have added a new subsection in the revised Results that compares long-term means, variances, and attractor statistics (e.g., power spectra and correlation dimensions) across all configurations, confirming that none of the stochastic schemes introduce measurable climatological drift relative to the deterministic reference. These diagnostics show that the reported invariance of long-term variance is a robust outcome rather than an artifact of training. revision: yes

  2. Referee: [Experimental setup] The comparison of spread-error consistency across parameterization families would be strengthened by reporting the actual ensemble size, the precise definition of 'spread' (e.g., standard deviation of the ensemble mean or of individual members), and whether error is measured against a high-resolution truth or against the deterministic reference run. These details are necessary to assess whether the reported improvement for persistent stochastic schemes is robust or sensitive to these choices.

    Authors: We appreciate the request for these operational details. In the revised manuscript we now explicitly state that all ensembles use 50 members, that spread is defined as the standard deviation of the individual ensemble members (not the ensemble-mean standard deviation), and that forecast error is computed against the deterministic reference integration at the same resolution (rather than a higher-resolution truth). These choices are consistent with the controlled nature of the Lorenz '96 testbed. We have also added a short sensitivity test confirming that the reported advantages of temporally persistent schemes remain qualitatively unchanged for ensemble sizes between 20 and 100 members. revision: yes

Circularity Check

0 steps flagged

No significant circularity; results from direct numerical experiments

full rationale

The paper conducts controlled numerical experiments on the two-scale Lorenz '96 system to compare ensemble configurations and learned stochastic parameterizations (deterministic, autoregressive, Bayesian, flow-based). Central claims about spread growth, decorrelation rates, and invariant measure exploration are presented as outcomes of simulation outputs rather than algebraic reductions or fitted quantities renamed as predictions. No equations or sections in the provided text reduce results to self-definitions, self-citations as load-bearing premises, or ansatzes smuggled via prior work. The derivation chain remains self-contained against the testbed benchmarks with independent empirical content.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based solely on the abstract, no explicit free parameters, axioms, or invented entities are described; the study uses the established Lorenz '96 system and learned stochastic parameterizations without detailing additional postulates.

pith-pipeline@v0.9.0 · 5719 in / 1174 out tokens · 39866 ms · 2026-05-22T08:25:19.230665+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

59 extracted references · 59 canonical work pages · 2 internal anchors

  1. [1]

    2023, PeerJ Computer Science, 9, e1516, doi: 10.7717/peerj-cs.1516

    Oriol Abril-Pla et al. “PyMC: A Modern, and Comprehensive Probabilistic Programming Framework in Python.” In:PeerJ Computer Science9 [Sept. 2023], e1516.doi:10.7717/peerj-cs.1516

    work page doi:10.7717/peerj-cs.1516 2023

  2. [2]

    ametsoc.org/wiki/climate/

    American Meteorological Society, 2026:Climate.Glossary of Meteorology.url: https://glossary. ametsoc.org/wiki/climate/

    work page 2026

  3. [3]

    American Meteorological Society, 2026:Climate Model.Glossary of Meteorology.url: https : / / glossary.ametsoc.org/wiki/climate-model/

    work page 2026

  4. [4]

    American Meteorological Society, 2026:Climate Prediction.Glossary of Meteorology.url: https: //glossary.ametsoc.org/wiki/climate-prediction/

    work page 2026

  5. [5]

    American Meteorological Society, 2026:Ensemble Forecast.Glossary of Meteorology.url: https : //glossary.ametsoc.org/wiki/ensemble-forecast/

    work page 2026

  6. [6]

    ametsoc.org/wiki/forecast/

    American Meteorological Society, 2026:Forecast.Glossary of Meteorology.url: https://glossary. ametsoc.org/wiki/forecast/

    work page 2026

  7. [7]

    ametsoc.org/wiki/grid/

    American Meteorological Society, 2026:Grid.Glossary of Meteorology.url: https : / / glossary . ametsoc.org/wiki/grid/

    work page 2026

  8. [8]

    ametsoc.org/wiki/lead-time/

    American Meteorological Society, 2026:Lead Time.Glossary of Meteorology.url: https://glossary. ametsoc.org/wiki/lead-time/

    work page 2026

  9. [9]

    American Meteorological Society, 2026:Model Resolution.Glossary of Meteorology.url: https : //glossary.ametsoc.org/wiki/model-resolution/

    work page 2026

  10. [10]

    American Meteorological Society, 2026:Numerical Forecasting.Glossary of Meteorology.url:https: //glossary.ametsoc.org/wiki/numerical-forecasting/

    work page 2026

  11. [11]

    American Meteorological Society, 2026:Parameterization.Glossary of Meteorology.url: https:// glossary.ametsoc.org/wiki/parameterization/

    work page 2026

  12. [12]

    American Meteorological Society, 2026:Subgrid-Scale Process.Glossary of Meteorology.url:https: //glossary.ametsoc.org/wiki/subgrid-scale-process/

    work page 2026

  13. [13]

    ametsoc.org/wiki/tendency/

    American Meteorological Society, 2026:Tendency.Glossary of Meteorology.url: https://glossary. ametsoc.org/wiki/tendency/

    work page 2026

  14. [14]

    American Meteorological Society, 2026:Turbulence Closure.Glossary of Meteorology.url: https: //glossary.ametsoc.org/wiki/turbulence-closure/

    work page 2026

  15. [15]

    ametsoc.org/wiki/weather/

    American Meteorological Society, 2026:Weather.Glossary of Meteorology.url: https://glossary. ametsoc.org/wiki/weather/

    work page 2026

  16. [16]

    American Meteorological Society, 2026:Weather Forecast.Glossary of Meteorology.url: https : //glossary.ametsoc.org/wiki/weather-forecast/

    work page 2026

  17. [17]

    Stochastic Parametrizations and Model Uncertainty in the Lorenz ’96 System

    H. M. Arnold, I. M. Moroz, and T. N. Palmer. “Stochastic Parametrizations and Model Uncertainty in the Lorenz ’96 System.” In:Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences371.1991 [May 2013], p. 20110479.doi:10.1098/rsta.2011.0479

    work page doi:10.1098/rsta.2011.0479 1991

  18. [18]

    Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi-Member and Stochastic Parameterizations

    Gunnar Behrens et al. “Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi-Member and Stochastic Parameterizations.” In:Journal of Advances in Modeling Earth Systems17.4 [2025], e2024MS004272.doi:10.1029/2024MS004272

    work page doi:10.1029/2024ms004272 2025

  19. [19]

    Stochastic Parameterization: Toward a New View of Weather and Climate Models

    Judith Berner et al. “Stochastic Parameterization: Toward a New View of Weather and Climate Models.” In:Bulletin of the American Meteorological Society98.3 [Mar. 2017], pp. 565–588.doi: 10.1175/BAMS-D-15-00268.1

    work page doi:10.1175/bams-d-15-00268.1 2017

  20. [20]

    Simulating Weather Regimes: Impact of Stochastic and Perturbed Parameter Schemes in a Simple Atmospheric Model

    H. M. Christensen, I. M. Moroz, and T. N. Palmer. “Simulating Weather Regimes: Impact of Stochastic and Perturbed Parameter Schemes in a Simple Atmospheric Model.” In:Climate Dynamics44.7 [Apr. 2015], pp. 2195–2214.doi:10.1007/s00382-014-2239-9

    work page doi:10.1007/s00382-014-2239-9 2015

  21. [21]

    Machine Learning for Stochastic Parametrization

    Hannah M. Christensen et al. “Machine Learning for Stochastic Parametrization.” In:Environmental Data Science3 [Jan. 2024], e38.doi:10.1017/eds.2024.45. 12

    work page doi:10.1017/eds.2024.45 2024

  22. [22]

    Resampling with Neural Networks for Stochastic Parameteri- zation in Multiscale Systems

    Daan Crommelin and Wouter Edeling. “Resampling with Neural Networks for Stochastic Parameteri- zation in Multiscale Systems.” In:Physica D: Nonlinear Phenomena422 [Aug. 2021], p. 132894.doi: 10.1016/j.physd.2021.132894

    work page doi:10.1016/j.physd.2021.132894 2021

  23. [23]

    Subgrid-Scale Parameterization with Conditional Markov Chains

    Daan Crommelin and Eric Vanden-Eijnden. “Subgrid-Scale Parameterization with Conditional Markov Chains.” In:Journal of the Atmospheric Sciences65.8 [Aug. 2008], pp. 2661–2675.doi:10.1175/ 2008JAS2566.1

    work page 2008

  24. [24]

    “Certain Uncertainty: The Role of Internal Climate Variability in Projections of Regional Climate Change and Risk Management

    Clara Deser. ““Certain Uncertainty: The Role of Internal Climate Variability in Projections of Regional Climate Change and Risk Management”.” In:Earth’s Future8.12 [2020], e2020EF001854.doi:10. 1029/2020EF001854

    work page 2020

  25. [25]

    Density Estimation Using Real NVP

    Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. “Density Estimation Using Real NVP.” In: International Conference on Learning Representations. Feb. 2017

    work page 2017

  26. [26]

    Stochastic Parameterization of Shallow Cumulus Convection Estimated from High-Resolution Model Data

    Jesse Dorrestijn et al. “Stochastic Parameterization of Shallow Cumulus Convection Estimated from High-Resolution Model Data.” In:Theoretical and Computational Fluid Dynamics27.1 [Feb. 2013], pp. 133–148.doi:10.1007/s00162-012-0281-y

    work page doi:10.1007/s00162-012-0281-y 2013

  27. [27]

    Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz ’96 Model

    David John Gagne II et al. “Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz ’96 Model.” In:Journal of Advances in Modeling Earth Systems12.3 [2020], e2019MS001896.doi:10.1029/2019MS001896

    work page doi:10.1029/2019ms001896 2020

  28. [28]

    Rood.Demystifying Climate Models

    Andrew Gettelman and Richard B. Rood.Demystifying Climate Models. Vol. 2. Earth Systems Data and Models. Berlin, Heidelberg: Springer Berlin Heidelberg, 2016.doi:10.1007/978-3-662-48959-8

    work page doi:10.1007/978-3-662-48959-8 2016

  29. [29]

    Stochastic Climate Theory

    Georg A. Gottwald, Daan T. Crommelin, and Christian L. E. Franzke. “Stochastic Climate Theory.” In: Nonlinear and Stochastic Climate Dynamics. Ed. by Christian L. E. Franzke and Terence J. O’Kane. Cambridge: Cambridge University Press, 2017, pp. 209–240.doi:10.1017/9781316339251.009

    work page doi:10.1017/9781316339251.009 2017

  30. [30]

    Deep Learning Based Cloud Cover Parameterization for ICON

    Arthur Grundner et al. “Deep Learning Based Cloud Cover Parameterization for ICON.” In:Journal of Advances in Modeling Earth Systems14.12 [2022].doi:10/gs5rbs

    work page 2022

  31. [31]

    Flexible Tails for Normalizing Flows

    Tennessee Hickling and Dennis Prangle. “Flexible Tails for Normalizing Flows.” In:Forty-Second International Conference on Machine Learning. June 2025

    work page 2025

  32. [32]

    The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo

    Matthew D. Hoffman and Andrew Gelman. “The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo.” In:Journal of Machine Learning Research15.47 [2014], pp. 1593–1623

    work page 2014

  33. [33]

    Tails of Lipschitz Triangular Flows

    Priyank Jaini et al. “Tails of Lipschitz Triangular Flows.” In:Proceedings of the 37th International Conference on Machine Learning. PMLR, Nov. 2020, pp. 4673–4681

    work page 2020

  34. [34]

    Adam: A Method for Stochastic Optimization

    Diederik P. Kingma and Jimmy Ba, 2017:Adam: A Method for Stochastic Optimization.url:http: //arxiv.org/abs/1412.6980

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  35. [35]

    Chapter 11 - Near-term Climate Change: Projections and Predictability

    B. Kirtman et al. “Chapter 11 - Near-term Climate Change: Projections and Predictability.” In: ed. by IPCC. Cambridge: Cambridge University Press, 2013

    work page 2013

  36. [36]

    The Importance of Internal Variability for the Uncertainty in Climate Change Projections and Decision-Making

    Flavio Lehner and Clara Deser. “The Importance of Internal Variability for the Uncertainty in Climate Change Projections and Decision-Making.” In:Uncertainty in Climate Change Research: An Integrated Approach. Ed. by Linda O. Mearns et al. Cham: Springer Nature Switzerland, 2025, pp. 177–183.doi: 10.1007/978-3-031-85542-9_17

    work page doi:10.1007/978-3-031-85542-9_17 2025

  37. [37]

    Partitioning Climate Projection Uncertainty with Multiple Large Ensembles and CMIP5/6

    Flavio Lehner et al. “Partitioning Climate Projection Uncertainty with Multiple Large Ensembles and CMIP5/6.” In:Earth System Dynamics11.2 [May 2020], pp. 491–508.doi:10.5194/esd-11-491-2020

    work page doi:10.5194/esd-11-491-2020 2020

  38. [38]

    Masset, R

    M. Leutbecher and T. N. Palmer. “Ensemble Forecasting.” In:Journal of Computational Physics. Predicting Weather, Climate and Extreme Events 227.7 [Mar. 2008], pp. 3515–3539.doi:10.1016/j. jcp.2007.02.014

    work page doi:10.1016/j 2008

  39. [39]

    Stochastic Representations of Model Uncertainties at ECMWF: State of the Art and Future Vision

    Martin Leutbecher et al. “Stochastic Representations of Model Uncertainties at ECMWF: State of the Art and Future Vision.” In:Quarterly Journal of the Royal Meteorological Society143.707 [2017], pp. 2315–2339.doi:10.1002/qj.3094

    work page doi:10.1002/qj.3094 2017

  40. [40]

    Navigating the Noise: Bringing Clarity to ML Parameterization Design With \boldsym- bol\mathcalO\(100) Ensembles

    Jerry Lin et al. “Navigating the Noise: Bringing Clarity to ML Parameterization Design With \boldsym- bol\mathcalO\(100) Ensembles.” In:Journal of Advances in Modeling Earth Systems17.4 [2025], e2024MS004551.doi:10.1029/2024MS004551

    work page doi:10.1029/2024ms004551 2025

  41. [41]

    Christopher Bishop.Pattern Recognition and Machine Learning

    Edward N. Lorenz. “Deterministic Nonperiodic Flow.” In:Journal of the Atmospheric Sciences20.2 [Mar. 1963], pp. 130–141.doi:10.1175/1520-0469(1963)020<0130:DNF>2.0.CO;2

    work page doi:10.1175/1520-0469(1963)020 1963

  42. [42]

    Predictability – a Problem Partly Solved

    Edward N. Lorenz. “Predictability – a Problem Partly Solved.” In:Predictability of Weather and Climate. Ed. by Renate Hagedorn and Tim Palmer. Cambridge: Cambridge University Press, 2006, pp. 40–58. doi:10.1017/CBO9780511617652.004. 13

    work page doi:10.1017/cbo9780511617652.004 2006

  43. [43]

    Characterizing Uncertainty in Deep Convection Triggering Using Explainable Machine Learning

    Greta A. Miller, Philip Stier, and Hannah M. Christensen. “Characterizing Uncertainty in Deep Convection Triggering Using Explainable Machine Learning.” In:Journal of the Atmospheric Sciences 82.6 [May 2025], pp. 1093–1111.doi:10.1175/JAS-D-24-0085.1

    work page doi:10.1175/jas-d-24-0085.1 2025

  44. [44]

    Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events

    Paul A. O’Gorman and John G. Dwyer. “Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events.” In:Journal of Advances in Modeling Earth Systems10.10 [2018], pp. 2548–2563.doi:10/gfdc2j

    work page 2018

  45. [45]

    Stochastic Parametrization and Model Uncertainty

    T. N. Palmer et al. “Stochastic Parametrization and Model Uncertainty.” In:ECMWF Technical Memorandum598 [2009]

    work page 2009

  46. [46]

    The ECMWF Ensemble Prediction System: Looking Back (More than) 25 Years and Projecting Forward 25 Years

    Tim Palmer. “The ECMWF Ensemble Prediction System: Looking Back (More than) 25 Years and Projecting Forward 25 Years.” In:Quarterly Journal of the Royal Meteorological Society145.S1 [2019], pp. 12–24.doi:10.1002/qj.3383

    work page doi:10.1002/qj.3383 2019

  47. [47]

    Masked Autoregressive Flow for Density Estimation

    George Papamakarios, Theo Pavlakou, and Iain Murray. “Masked Autoregressive Flow for Density Estimation.” In:Advances in Neural Information Processing Systems. Vol. 30. Curran Associates, Inc., 2017

    work page 2017

  48. [48]

    Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: A Case Study with the Lorenz 96 Model

    Raghul Parthipan et al. “Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: A Case Study with the Lorenz 96 Model.” In:Geoscientific Model Development 16.15 [Aug. 2023], pp. 4501–4519.doi:10.5194/gmd-16-4501-2023

    work page doi:10.5194/gmd-16-4501-2023 2023

  49. [49]

    Coupled Online Learning as a Way to Tackle Instabilities and Biases in Neural Network Parameterizations: General Algorithms and Lorenz 96 Case Study (v1.0)

    Stephan Rasp. “Coupled Online Learning as a Way to Tackle Instabilities and Biases in Neural Network Parameterizations: General Algorithms and Lorenz 96 Case Study (v1.0).” In:Geoscientific Model Development13.5 [May 2020], pp. 2185–2196.doi:10.5194/gmd-13-2185-2020

    work page doi:10.5194/gmd-13-2185-2020 2020

  50. [50]

    Deep Learning to Represent Subgrid Processes in Climate Models

    Stephan Rasp, Michael S. Pritchard, and Pierre Gentine. “Deep Learning to Represent Subgrid Processes in Climate Models.” In:Proceedings of the National Academy of Sciences115.39 [Sept. 2018], pp. 9684– 9689.doi:10/gfcpxb

    work page 2018

  51. [51]

    Climate Goals and Computing the Future of Clouds

    Tapio Schneider et al. “Climate Goals and Computing the Future of Clouds.” In:Nature Climate Change 7.1 [Jan. 2017], pp. 3–5.doi:10/gf9pkz

    work page 2017

  52. [52]

    Smith.Uncertainty Quantification: Theory, Implementation, and Applications

    Ralph C. Smith.Uncertainty Quantification: Theory, Implementation, and Applications. Computational Science & Engineering. Philadelphia: Society for Industrial and Applied Mathematics, 2014

    work page 2014

  53. [53]

    Climate Model Projections from the Scenario Model Intercomparison Project (ScenarioMIP) of CMIP6

    Claudia Tebaldi et al. “Climate Model Projections from the Scenario Model Intercomparison Project (ScenarioMIP) of CMIP6.” In:Earth System Dynamics12.1 [Mar. 2021], pp. 253–293.doi:10/gh6k9m

    work page 2021

  54. [54]

    Conditional Density Estimation with Bayesian Normalising Flows

    Brian L. Trippe and Richard E. Turner, 2018:Conditional Density Estimation with Bayesian Normalising Flows.url:http://arxiv.org/abs/1802.04908

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  55. [55]

    Effects of Stochastic Parametrizations in the Lorenz ’96 System

    Daniel S. Wilks. “Effects of Stochastic Parametrizations in the Lorenz ’96 System.” In:Quarterly Journal of the Royal Meteorological Society131.606 [Jan. 2005], pp. 389–407.doi:10.1256/qj.04.03

    work page doi:10.1256/qj.04.03 2005

  56. [56]

    Forced Component Estimation Statistical Method Intercomparison Project (ForceSMIP)

    Robert C. J. Wills et al. “Forced Component Estimation Statistical Method Intercomparison Project (ForceSMIP).” In:Journal of Climate39.8 [Apr. 2026], pp. 1927–1953.doi:10.1175/JCLI- D- 25- 0326.1

    work page doi:10.1175/jcli- 2026

  57. [57]

    Quantifying the Uncertainty Sources of Future Climate Projections and Narrowing Uncertainties With Bias Correction Techniques

    Yi Wu et al. “Quantifying the Uncertainty Sources of Future Climate Projections and Narrowing Uncertainties With Bias Correction Techniques.” In:Earth’s Future10.11 [2022], e2022EF002963.doi: 10.1029/2022EF002963

    work page doi:10.1029/2022ef002963 2022

  58. [58]

    Stable Machine-Learning Parameterization of Subgrid Processes for Climate Modeling at a Range of Resolutions

    Janni Yuval and Paul A. O’Gorman. “Stable Machine-Learning Parameterization of Subgrid Processes for Climate Modeling at a Range of Resolutions.” In:Nature Communications11.1 [July 2020].doi: 10/gngc7t

    work page 2020

  59. [59]

    Uncertainty in Projection of Climate Extremes: A Comparison of CMIP5 and CMIP6

    Shaobo Zhang and Jie Chen. “Uncertainty in Projection of Climate Extremes: A Comparison of CMIP5 and CMIP6.” In:Journal of Meteorological Research35.4 [Aug. 2021], pp. 646–662.doi: 10.1007/s13351-021-1012-3. 14 Decomposing Ensemble Spread in Lorenz ’96 With Learned Stochastic Parameterizations Appendix A Glossary B Flow Variations Tail flow.As an addition...

    work page doi:10.1007/s13351-021-1012-3 2021