27th Annual CESM Workshop - Earth System Prediction Working Group (ESPWG)
To explore the predictability of temporary slowdowns in future climate warming, we apply an artificial neural network (ANN) to data from CESM2-LE and observations. Here, an ANN is tasked with predicting the onset of a slowdown in the rate of the global mean surface temperature trend by using maps of upper ocean heat content anomalies. Through a machine learning explainability method, we identify key regional patterns the ANN is learning to make its slowdown predictions.
Using neural networks to predict temporary slowdowns in decadal climate warming trends
1. USING NEURAL NETWORKS TO PREDICT
TEMPORARY SLOWDOWNS IN DECADAL
CLIMATE WARMING TRENDS
@ZLabe
Zachary M. Labe1
with Elizabeth A. Barnes2
1NOAA GFDL and Princeton University; Atmospheric and Oceanic Sciences
2
Colorado State University; Department of Atmospheric Science
16 June 2022
27th Annual CESM Workshop
Earth System Prediction Working Group (ESPWG)
11. Are slowdowns (“hiatus”) in decadal
warming predictable?
• Statistical construct?
• Lack of surface temperature observations in the Arctic?
• Phase transition of the Interdecadal Pacific Oscillation (IPO)?
• Influence of volcanoes and other aerosol forcing?
• Weaker solar forcing?
• Lower equilibrium climate sensitivity (ECS)?
• Other combinations of internal variability?
FUTURE
WARMING
12. Select one ensemble
member and calculate
the annual mean
global mean surface
temperature (GMST)
2-m TEMPERATURE
ANOMALY
24. OCEAN HEAT CONTENT – 100 M
INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
YES
SLOWDOWN
NO
SLOWDOWN
Will a slowdown begin?
25. OCEAN HEAT CONTENT – 100 M
INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
YES
SLOWDOWN
NO
SLOWDOWN
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
LAYER-WISE RELEVANCE PROPAGATION
Will a slowdown begin?
28. Visualizing something we already know…
Input maps of sea surface
temperatures to identify
El Niño or La Niña
Use ‘LRP’ to see how the
neural network is making
its decision
[Toms et al. 2020, JAMES]
Layer-wise Relevance Propagation
Composite Observations
LRP [Relevance]
SST Anomaly [°C]
0.00 0.75
0.0 1.5
-1.5
29. [Adapted from Adebayo et al., 2020]
EXPLAINABLE AI IS
NOT PERFECT
THERE ARE MANY
METHODS
30. [Adapted from Adebayo et al., 2020]
THERE ARE MANY
METHODS
EXPLAINABLE AI IS
NOT PERFECT
31. OCEAN HEAT CONTENT – 100 M
INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
YES
SLOWDOWN
NO
SLOWDOWN
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
LAYER-WISE RELEVANCE PROPAGATION
Will a slowdown begin?
39. KEY POINTS
1. An artificial neural network predicts the onset of slowdowns in decadal warming trends of
global mean surface temperature
2. Explainable AI reveals the neural network is leveraging tropical patterns of ocean heat content
anomalies to make its predictions
3. Transitions in the phase of the Interdecadal Pacific Oscillation are frequently associated with
warming slowdown trends in CESM2-LE
Zachary Labe
zachary.labe@noaa.gov
@ZLabe
Labe, Z.M. and E.A. Barnes (2022), Predicting slowdowns in decadal climate warming trends with
explainable neural networks. Geophysical Research Letters, DOI:10.1029/2022GL098173