Using Simple, Explainable Neural Networks to Predict the Madden‐Julian Oscillation

Martin, Zane; Barnes, Elizabeth A.; Maloney, Eric D.

doi:10.1029/2021ms002774

Cited by 13 publications

(7 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interestingly, we find that ANN classification accuracy is more sensitive to the choice of L 2 , rather than the complexity of the network itself (i.e., number of hidden layers and nodes). In general, our networks here are relatively shallow (one to three layers) and similar to recent studies applying feed-forward neural networks to climate science applications (e.g., Toms et al, 2021;Martin et al, 2022;.…”

Section: Conflict Of Interestsupporting

confidence: 57%

Exploring a data-driven approach to identify regions of change associated with future climate scenarios

Labe,

Delworth,

Johnson

et al. 2024

Preprint

View full text Add to dashboard Cite

A key consideration for evaluating climate projections is uncertainty in radiative forcing scenarios. Although it is straightforward to monitor greenhouse gas concentrations and compare those observations with specified climate scenarios, it remains less obvious on how to connect regional climate patterns with these scenarios in real time. Here we introduce a machine learning approach for linking patterns of climate change with radiative forcing scenarios and use an attribution method to understand how these linkages are made. We train a neural network using output from the SPEAR Large Ensemble to classify whether temperature or precipitation maps are most likely to originate from one of several potential radiative forcing scenarios. The neural network learns to identify “fingerprint” patterns that associate signals of climate change with the scenarios. We illustrate this using output from additional mitigation experiments and highlight regions that are critical for associating the new simulations with likely radiative forcing scenarios.

show abstract

Section: Conflict Of Interestsupporting

confidence: 57%

Exploring a data-driven approach to identify regions of change associated with future climate scenarios

Labe,

Delworth,

Johnson

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, neural networks have been shown to be a powerful statistical tool for the atmospheric sciences due to their ability to identify non-linear, physical relationships within large amounts of data (Davenport & Diffenbaugh, 2021;Gordon et al, 2021;Labe & Barnes, 2022;Martin et al, 2022;Toms et al, 2020Toms et al, , 2021. For example, on subseasonal timescales, explainable neural networks were demonstrated to identify subseasonal forecasts of opportunity using the network's "confidence" in a given prediction as well as the associated tropical sources of predictability through explainability techniques (Mayer & Barnes, 2021).…”

Section: Introductionmentioning

confidence: 99%

Exploring the Relative Importance of the MJO and ENSO to North Pacific Subseasonal Predictability

Mayer,

Chapman,

Manriquez

2024

Geophysical Research Letters

View full text Add to dashboard Cite

Here we explore the relative contribution of the Madden‐Julian Oscillation (MJO) and El Niño Southern Oscillation (ENSO) to midlatitude subseasonal predictive skill of upper atmospheric circulation over the North Pacific, using an inherently interpretable neural network applied to pre‐industrial control runs of the Community Earth System Model version 2. We find that this interpretable network generally favors the state of ENSO, rather than the MJO, to make correct predictions on a range of subseasonal lead times and predictand averaging windows. Moreover, the predictability of positive circulation anomalies over the North Pacific is comparatively lower than that of their negative counterparts, especially evident when the ENSO state is important. However, when ENSO is in a neutral state, our findings indicate that the MJO provides some predictive information, particularly for positive anomalies. We identify three distinct evolutions of these MJO states, offering fresh insights into opportune forecasting windows for MJO teleconnections.

show abstract

“…The neural network approach allows us to make subseasonal predictions without the need for a forecast model. The fields of weather and climate science have benefitted from applications of neural networks to learn physical relationships within the Earth system via explainability techniques (Ham et al 2019, McGovern et al 2019, Toms et al 2020, Antonios et al 2021, Gordon et al 2021, Martin et al 2022, Mayer and Barnes 2022, Straaten et al 2023. Here, we use shallow artificial neural networks (ANNs) to quantify U.S. West Coast subseasonal precipitation skill and identify forecasts of opportunity provided by the tropics within CESM2.…”

Section: Introductionmentioning

confidence: 99%

Assessing decadal variability of subseasonal forecasts of opportunity using explainable AI

Arcodia

Barnes

Mayer

et al. 2023

Environ. Res.: Climate

Self Cite

View full text Add to dashboard Cite

Identifying predictable states of the climate system allows for enhanced prediction skill on the generally low-skill subseasonal timescale via forecasts with higher confidence and accuracy, known as forecasts of opportunity. This study takes a neural network approach to explore decadal variability of subseasonal predictability, particularly during forecasts of opportunity. Specifically, this work quantifies subseasonal prediction skill provided by the tropics within the CESM2 Large Ensemble and assesses how this skill evolves on decadal timescales. Utilizing the networks’ confidence and explainable artificial intelligence (XAI), physically meaningful sources of predictability associated with periods of enhanced skill are identified. Using these networks, we find that tropically-driven subseasonal predictability varies on decadal timescales during forecasts of opportunity. Analysis is extended to ECMWF Reanalysis v5 data, revealing that the relationships learned within the CESM2-LE holds in modern reanalysis data. These results indicate that the neural networks are capable of identifying predictable decadal states of the climate system within CESM2 that are useful for making confident, accurate subseasonal precipitation predictions in the real world.

show abstract

Using Simple, Explainable Neural Networks to Predict the Madden‐Julian Oscillation

Cited by 13 publications

References 58 publications

Exploring a data-driven approach to identify regions of change associated with future climate scenarios

Exploring a data-driven approach to identify regions of change associated with future climate scenarios

Exploring the Relative Importance of the MJO and ENSO to North Pacific Subseasonal Predictability

Assessing decadal variability of subseasonal forecasts of opportunity using explainable AI

Contact Info

Product

Resources

About