1. Researchers used an artificial neural network to predict slowdowns in the rate of decadal global warming by analyzing patterns in ocean heat content anomalies.
2. Explainable AI techniques showed the neural network was leveraging tropical ocean heat content to make predictions.
3. Transitions between phases of the Interdecadal Pacific Oscillation were often associated with periods of slower warming in climate model simulations, consistent with observed temperature trends.
Using artificial neural networks to predict temporary slowdowns in global warming trends
1. USING ARTIFICIAL NEURAL NETWORKS
TO PREDICT TEMPORARY SLOWDOWNS
IN GLOBAL 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
9 January 2023
22nd Conference on Artificial Intelligence for Environmental Science
103rd AMS Annual Meeting in Denver, CO
12. 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
13. Select one ensemble
member and calculate
the annual mean
global mean surface
temperature (GMST)
2-m TEMPERATURE
ANOMALY
[Labe and Barnes, 2022; GRL]
23. OCEAN HEAT CONTENT – 100 M
Start with anomalous ocean heat…
[Labe and Barnes, 2022; GRL]
24. OCEAN HEAT CONTENT – 100 M
INPUT LAYER
Start with anomalous ocean heat…
[Labe and Barnes, 2022; GRL]
25. OCEAN HEAT CONTENT – 100 M
INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
YES
SLOWDOWN
NO
SLOWDOWN
Will a slowdown begin?
[Labe and Barnes, 2022; GRL]
26. 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?
[Labe and Barnes, 2022; GRL]
29. 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
30. [Adapted from Adebayo et al., 2020]
EXPLAINABLE AI IS
NOT PERFECT
THERE ARE MANY
METHODS
31. [Adapted from Adebayo et al., 2020]
THERE ARE MANY
METHODS
EXPLAINABLE AI IS
NOT PERFECT
32. 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?
[Labe and Barnes, 2022; GRL]
33. So how well does the neural network do?
[Labe and Barnes, 2022; GRL]
40. 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