1. REVEALING CLIMATE CHANGE SIGNALS
WITH EXPLAINABLE AI
@ZLabe
Zachary M. Labe
with Elizabeth A. Barnes
Department of Atmospheric Science
30 March 2021
Spring Postdoctoral Research Symposium
CSU PASS
3. What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
Anomaly is relative to 1951-1980
4. What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
Let’s run a
climate model
5. What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
Let’s run a
climate model
again
6. What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
Let’s run a
climate model
again & again
7. What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
CLIMATE MODEL
ENSEMBLES
8. What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
Range of ensembles
= natural variability (noise)
Mean of ensembles
= forced response (climate change)
CLIMATE MODEL
ENSEMBLES
9. What is the annual mean temperature of Earth?
• Increasing greenhouse gases (CO2, CH4, N2O)
• Changes in industrial aerosols (SO4, BC, OC)
• Changes in biomass burning (aerosols)
• Changes in land-use & land-cover (albedo)
10. What is the annual mean temperature of Earth?
• Increasing greenhouse gases (CO2, CH4, N2O)
• Changes in industrial aerosols (SO4, BC, OC)
• Changes in biomass burning (aerosols)
• Changes in land-use & land-cover (albedo)
Plus everything else…
(Natural/internal variability)
12. Greenhouse gases fixed to 1920 levels
All forcings (CESM-LE)
Industrial aerosols fixed to 1920 levels
[Deser et al. 2020, JCLI]
Fully-coupled CESM1.1
20 Ensemble Members
Run from 1920-2080
Observations
13. So what?
Greenhouse gases = warming
Aerosols = ?? (though mostly cooling)
What are the relative responses
between greenhouse gas
and aerosol forcing?
16. INPUT LAYER
Surface Temperature Map
ARTIFICIAL NEURAL NETWORK (ANN)
Collection of nodes (neurons)
that adjust their weights and
biases across layers in order to
learn signals for making
predictions
Learns nonlinear processes
through selected parameters
in the model
17. INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
Surface Temperature Map
“2000-2009”
DECADE CLASS
“2070-2079”
“1920-1929”
ARTIFICIAL NEURAL NETWORK (ANN)
18. INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
Surface Temperature Map
“2000-2009”
DECADE CLASS
“2070-2079”
“1920-1929”
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
ARTIFICIAL NEURAL NETWORK (ANN)
19. INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
Layer-wise Relevance Propagation
Surface Temperature Map
“2000-2009”
DECADE CLASS
“2070-2079”
“1920-1929”
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
ARTIFICIAL NEURAL NETWORK (ANN)
[Barnes et al. 2020, JAMES]
[Labe and Barnes 2021, in revision]
20. OUTPUT LAYER
Layer-wise Relevance Propagation
“2000-2009”
DECADE CLASS
“2070-2079”
“1920-1929”
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
WHY?
= LRP HEAT MAPS
[Labe and Barnes 2021, in revision]
21. Layer-wise Relevance Propagation
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
[Labe and Barnes 2021, in revision]
WHY?
= LRP HEAT MAPS
Find regions of “relevance”
that contribute to the
neural network’s
decision-making process
22. 1960-1999: ANNUAL MEAN TEMPERATURE TRENDS
Greenhouse gases fixed
to 1920 levels
[AEROSOLS PREVAIL]
Industrial aerosols fixed
to 1920 levels
[GREENHOUSE GASES PREVAIL]
All forcings
[STANDARD CESM-LE]
DATA
23. 1960-1999: ANNUAL MEAN TEMPERATURE TRENDS
Greenhouse gases fixed
to 1920 levels
[AEROSOLS PREVAIL]
Industrial aerosols fixed
to 1920 levels
[GREENHOUSE GASES PREVAIL]
All forcings
[STANDARD CESM-LE]
DATA
24. 1960-1999: ANNUAL MEAN TEMPERATURE TRENDS
Greenhouse gases fixed
to 1920 levels
[AEROSOLS PREVAIL]
Industrial aerosols fixed
to 1920 levels
[GREENHOUSE GASES PREVAIL]
All forcings
[STANDARD CESM-LE]
DATA
25. 1960-1999: ANNUAL MEAN TEMPERATURE TRENDS
Greenhouse gases fixed
to 1920 levels
[AEROSOLS PREVAIL]
Industrial aerosols fixed
to 1920 levels
[GREENHOUSE GASES PREVAIL]
All forcings
[STANDARD CESM-LE]
DATA
26. CLIMATE MODEL DATA PREDICT THE YEAR FROM MAPS OF TEMPERATURE
[Labe and Barnes 2021, in revision]
AEROSOLS
PREVAIL
GREENHOUSE GASES
PREVAIL
STANDARD
CLIMATE MODEL
27. OBSERVATIONS PREDICT THE YEAR FROM MAPS OF TEMPERATURE
[Labe and Barnes 2021, in revision]
AEROSOLS
PREVAIL
GREENHOUSE GASES
PREVAIL
STANDARD
CLIMATE MODEL
28. OBSERVATIONS
SLOPES
PREDICT THE YEAR FROM MAPS OF TEMPERATURE
[Labe and Barnes 2021, in revision]
AEROSOLS
PREVAIL
GREENHOUSE GASES
PREVAIL
STANDARD
CLIMATE MODEL
30. HOW DID THE ANN
MAKE ITS
PREDICTIONS?
WHY IS THERE
GREATER SKILL
FOR GHG+?
31. Higher LRP values indicate greater relevance
for the ANN’s prediction
AVERAGED OVER 1960-2039
[Labe and Barnes 2021, in revision]
Aerosol-driven
Greenhouse gas-driven
All forcings
Low High
32. [Labe and Barnes 2021, in revision]
Greenhouse gas-driven
Aerosol-driven
All forcings
AVERAGED OVER 1960-2039
33. KEY POINTS
Zachary Labe
zmlabe@rams.colostate.edu
@ZLabe
1. Using explainable AI methods with artificial neural networks (ANNs) reveals patterns of climate
change in climate models
2. ANN trained using a large ensemble simulation without time-evolving aerosols makes
predictions that have a higher correlation with observations
3. The North Atlantic is an important region for the ANN to make predictions in climate model
experiments forced by aerosols and greenhouse gases