USING NEURAL NETWORKS TO EXPLORE
REGIONAL CLIMATE PATTERNS IN
SINGLE-FORCING LARGE ENSEMBLES
@ZLabe
Zachary M. Labe
with Dr. Elizabeth A. Barnes
Department of Atmospheric Science at Colorado State University
17 December 2021
A52E-01 – AGU Fall Meeting
“Large Ensemble Climate Model Simulations as Tools for Exploring
Natural Variability, Change Signals, and Impacts” [Oral Session I]
TEMPERATURE
TEMPERATURE
We know some metadata…
+ What year is it?
+ Where did it come from?
We know some metadata…
+ What year is it?
+ Where did it come from?
TEMPERATURE
We know some metadata…
+ What year is it?
+ Where did it come from?
TEMPERATURE
Neural network learns nonlinear
combinations of forced climate
patterns to identify the year
----ANN----
2 Hidden Layers
10 Nodes each
Ridge Regularization
Early Stopping
We know some metadata…
+ What year is it?
+ Where did it come from?
[e.g., Barnes et al. 2019, 2020]
[e.g., Labe and Barnes, 2021]
TIMING OF EMERGENCE
(COMBINED VARIABLES)
RESPONSES TO
EXTERNAL CLIMATE
FORCINGS
PATTERNS OF
CLIMATE INDICATORS
[e.g., Rader et al. 2021, drafted]
Surface Temperature Map Precipitation Map
+
TEMPERATURE
----ANN----
2 Hidden Layers
10 Nodes each
Ridge Regularization
Early Stopping
We know some metadata…
+ What year is it?
+ Where did it come from?
[e.g., Barnes et al. 2019, 2020]
[e.g., Labe and Barnes, 2021]
TIMING OF EMERGENCE
(COMBINED VARIABLES)
RESPONSES TO
EXTERNAL CLIMATE
FORCINGS
PATTERNS OF
CLIMATE INDICATORS
[e.g., Rader et al. 2021, in prep]
Surface Temperature Map Precipitation Map
+
TEMPERATURE
THE REAL WORLD
(Observations)
What is the annual mean temperature of Earth?
What is the annual mean temperature of Earth?
THE REAL WORLD
(Observations)
Anomaly is relative to 1951-1980
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)
A CLIMATE MODEL
(CESM1.1-LE)
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)
A CLIMATE MODEL
(CESM1.1-LE)
What is the annual mean temperature of Earth?
[CESM1 "Single Forcing" Large Ensemble Project]
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
So what?
Greenhouse gases = warming
Aerosols = ?? (though mostly cooling)
What are the relative responses
between greenhouse gas
and aerosol forcing?
Surface Temperature Map
ARTIFICIAL NEURAL NETWORK (ANN)
INPUT LAYER
Surface Temperature Map
ARTIFICIAL NEURAL NETWORK (ANN)
INPUT LAYER
HIDDEN LAYERS
OUTPUT LAYER
Surface Temperature Map
“2000-2009”
DECADE CLASS
“2070-2079”
“1920-1929”
ARTIFICIAL NEURAL NETWORK (ANN)
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)
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, JAMES]
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, JAMES]
Layer-wise Relevance Propagation
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
WHY?
= LRP HEAT MAPS
Machine Learning
Black Box
[Labe and Barnes 2021, JAMES]
Layer-wise Relevance Propagation
BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI
WHY?
= LRP HEAT MAPS
Find regions of “relevance”
that contribute to the
neural network’s
decision-making process
[Labe and Barnes 2021, JAMES]
Visualizing something we already know…
Neural
Network
[0] La Niña [1] El Niño
[Toms et al. 2020, JAMES]
Input a map of sea surface temperatures
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
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, JAMES]
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
Colder Warmer
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
Colder Warmer
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
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
Colder Warmer
CLIMATE MODEL DATA PREDICT THE YEAR FROM MAPS OF TEMPERATURE
AEROSOLS
PREVAIL
GREENHOUSE GASES
PREVAIL
STANDARD
CLIMATE MODEL
[Labe and Barnes 2021, JAMES]
OBSERVATIONS PREDICT THE YEAR FROM MAPS OF TEMPERATURE
AEROSOLS
PREVAIL
GREENHOUSE GASES
PREVAIL
STANDARD
CLIMATE MODEL
[Labe and Barnes 2021, JAMES]
OBSERVATIONS
SLOPES
PREDICT THE YEAR FROM MAPS OF TEMPERATURE
AEROSOLS
PREVAIL
GREENHOUSE GASES
PREVAIL
STANDARD
CLIMATE MODEL
[Labe and Barnes 2021, JAMES]
Low High
HOW DID THE ANN
MAKE ITS
PREDICTIONS?
Low High
HOW DID THE ANN
MAKE ITS
PREDICTIONS?
WHY IS THERE
GREATER SKILL
FOR GHG+?
RESULTS FROM LRP
[Labe and Barnes 2021, JAMES]
Low High
RESULTS FROM LRP
[Labe and Barnes 2021, JAMES]
Low High
RESULTS FROM LRP
[Labe and Barnes 2021, JAMES]
Low High
RESULTS FROM LRP
[Labe and Barnes 2021, JAMES]
Low High
Higher LRP values indicate greater relevance
for the ANN’s prediction
AVERAGED OVER 1960-2039
Aerosol-driven
Greenhouse gas-driven
All forcings
Low High
[Labe and Barnes 2021, JAMES]
Greenhouse gas-driven
Aerosol-driven
All forcings
AVERAGED OVER 1960-2039
[Labe and Barnes 2021, JAMES]
KEY POINTS
Zachary Labe
zmlabe@rams.colostate.edu
@ZLabe
1. Using explainable AI methods with artificial neural networks (ANN) reveals climate patterns in
large ensemble simulations
2. A metric is proposed for quantifying the uncertainty of an ANN visualization method that
extracts signals from different external forcings
3. Predictions from an ANN trained using a large ensemble without time-evolving aerosols show
the highest correlation with actual observations
QUESTIONS
Zachary Labe
1. Using explainable AI methods with artificial neural networks (ANN) reveals climate patterns in
large ensemble simulations
2. A metric is proposed for quantifying the uncertainty of an ANN visualization method that
extracts signals from different external forcings
3. Predictions from an ANN trained using a large ensemble without time-evolving aerosols show
the highest correlation with actual observations
Labe, Z.M. and E.A. Barnes (2021), Detecting climate signals using
explainable AI with single-forcing large ensembles. Journal of
Advances in Modeling Earth Systems, DOI:10.1029/2021MS002464

Using neural networks to explore regional climate patterns in single-forcing large ensembles

  • 1.
    USING NEURAL NETWORKSTO EXPLORE REGIONAL CLIMATE PATTERNS IN SINGLE-FORCING LARGE ENSEMBLES @ZLabe Zachary M. Labe with Dr. Elizabeth A. Barnes Department of Atmospheric Science at Colorado State University 17 December 2021 A52E-01 – AGU Fall Meeting “Large Ensemble Climate Model Simulations as Tools for Exploring Natural Variability, Change Signals, and Impacts” [Oral Session I]
  • 2.
  • 3.
    TEMPERATURE We know somemetadata… + What year is it? + Where did it come from?
  • 4.
    We know somemetadata… + What year is it? + Where did it come from? TEMPERATURE
  • 5.
    We know somemetadata… + What year is it? + Where did it come from? TEMPERATURE Neural network learns nonlinear combinations of forced climate patterns to identify the year
  • 6.
    ----ANN---- 2 Hidden Layers 10Nodes each Ridge Regularization Early Stopping We know some metadata… + What year is it? + Where did it come from? [e.g., Barnes et al. 2019, 2020] [e.g., Labe and Barnes, 2021] TIMING OF EMERGENCE (COMBINED VARIABLES) RESPONSES TO EXTERNAL CLIMATE FORCINGS PATTERNS OF CLIMATE INDICATORS [e.g., Rader et al. 2021, drafted] Surface Temperature Map Precipitation Map + TEMPERATURE
  • 7.
    ----ANN---- 2 Hidden Layers 10Nodes each Ridge Regularization Early Stopping We know some metadata… + What year is it? + Where did it come from? [e.g., Barnes et al. 2019, 2020] [e.g., Labe and Barnes, 2021] TIMING OF EMERGENCE (COMBINED VARIABLES) RESPONSES TO EXTERNAL CLIMATE FORCINGS PATTERNS OF CLIMATE INDICATORS [e.g., Rader et al. 2021, in prep] Surface Temperature Map Precipitation Map + TEMPERATURE
  • 8.
    THE REAL WORLD (Observations) Whatis the annual mean temperature of Earth?
  • 9.
    What is theannual mean temperature of Earth? THE REAL WORLD (Observations) Anomaly is relative to 1951-1980
  • 10.
    What is theannual 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) A CLIMATE MODEL (CESM1.1-LE)
  • 11.
    What is theannual 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) A CLIMATE MODEL (CESM1.1-LE)
  • 12.
    What is theannual mean temperature of Earth? [CESM1 "Single Forcing" Large Ensemble Project]
  • 13.
    Greenhouse gases fixedto 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
  • 14.
    So what? Greenhouse gases= warming Aerosols = ?? (though mostly cooling) What are the relative responses between greenhouse gas and aerosol forcing?
  • 15.
  • 16.
    INPUT LAYER Surface TemperatureMap ARTIFICIAL NEURAL NETWORK (ANN)
  • 17.
    INPUT LAYER HIDDEN LAYERS OUTPUTLAYER Surface Temperature Map “2000-2009” DECADE CLASS “2070-2079” “1920-1929” ARTIFICIAL NEURAL NETWORK (ANN)
  • 18.
    INPUT LAYER HIDDEN LAYERS OUTPUTLAYER 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 OUTPUTLAYER 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, JAMES]
  • 20.
    OUTPUT LAYER Layer-wise RelevancePropagation “2000-2009” DECADE CLASS “2070-2079” “1920-1929” BACK-PROPAGATE THROUGH NETWORK = EXPLAINABLE AI WHY? = LRP HEAT MAPS [Labe and Barnes 2021, JAMES]
  • 21.
    Layer-wise Relevance Propagation BACK-PROPAGATETHROUGH NETWORK = EXPLAINABLE AI WHY? = LRP HEAT MAPS Machine Learning Black Box [Labe and Barnes 2021, JAMES]
  • 22.
    Layer-wise Relevance Propagation BACK-PROPAGATETHROUGH NETWORK = EXPLAINABLE AI WHY? = LRP HEAT MAPS Find regions of “relevance” that contribute to the neural network’s decision-making process [Labe and Barnes 2021, JAMES]
  • 23.
    Visualizing something wealready know…
  • 24.
    Neural Network [0] La Niña[1] El Niño [Toms et al. 2020, JAMES] Input a map of sea surface temperatures
  • 25.
    Visualizing something wealready 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
  • 26.
    INPUT LAYER HIDDEN LAYERS OUTPUTLAYER 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, JAMES]
  • 27.
    1960-1999: ANNUAL MEANTEMPERATURE TRENDS Greenhouse gases fixed to 1920 levels [AEROSOLS PREVAIL] Industrial aerosols fixed to 1920 levels [GREENHOUSE GASES PREVAIL] All forcings [STANDARD CESM-LE] DATA Colder Warmer
  • 28.
    1960-1999: ANNUAL MEANTEMPERATURE TRENDS Greenhouse gases fixed to 1920 levels [AEROSOLS PREVAIL] Industrial aerosols fixed to 1920 levels [GREENHOUSE GASES PREVAIL] All forcings [STANDARD CESM-LE] DATA Colder Warmer
  • 29.
    1960-1999: ANNUAL MEANTEMPERATURE TRENDS Greenhouse gases fixed to 1920 levels [AEROSOLS PREVAIL] Industrial aerosols fixed to 1920 levels [GREENHOUSE GASES PREVAIL] All forcings [STANDARD CESM-LE] DATA
  • 30.
    1960-1999: ANNUAL MEANTEMPERATURE TRENDS Greenhouse gases fixed to 1920 levels [AEROSOLS PREVAIL] Industrial aerosols fixed to 1920 levels [GREENHOUSE GASES PREVAIL] All forcings [STANDARD CESM-LE] DATA Colder Warmer
  • 31.
    CLIMATE MODEL DATAPREDICT THE YEAR FROM MAPS OF TEMPERATURE AEROSOLS PREVAIL GREENHOUSE GASES PREVAIL STANDARD CLIMATE MODEL [Labe and Barnes 2021, JAMES]
  • 32.
    OBSERVATIONS PREDICT THEYEAR FROM MAPS OF TEMPERATURE AEROSOLS PREVAIL GREENHOUSE GASES PREVAIL STANDARD CLIMATE MODEL [Labe and Barnes 2021, JAMES]
  • 33.
    OBSERVATIONS SLOPES PREDICT THE YEARFROM MAPS OF TEMPERATURE AEROSOLS PREVAIL GREENHOUSE GASES PREVAIL STANDARD CLIMATE MODEL [Labe and Barnes 2021, JAMES]
  • 34.
    Low High HOW DIDTHE ANN MAKE ITS PREDICTIONS?
  • 35.
    Low High HOW DIDTHE ANN MAKE ITS PREDICTIONS? WHY IS THERE GREATER SKILL FOR GHG+?
  • 36.
    RESULTS FROM LRP [Labeand Barnes 2021, JAMES] Low High
  • 37.
    RESULTS FROM LRP [Labeand Barnes 2021, JAMES] Low High
  • 38.
    RESULTS FROM LRP [Labeand Barnes 2021, JAMES] Low High
  • 39.
    RESULTS FROM LRP [Labeand Barnes 2021, JAMES] Low High
  • 40.
    Higher LRP valuesindicate greater relevance for the ANN’s prediction AVERAGED OVER 1960-2039 Aerosol-driven Greenhouse gas-driven All forcings Low High [Labe and Barnes 2021, JAMES]
  • 41.
    Greenhouse gas-driven Aerosol-driven All forcings AVERAGEDOVER 1960-2039 [Labe and Barnes 2021, JAMES]
  • 42.
    KEY POINTS Zachary Labe zmlabe@rams.colostate.edu @ZLabe 1.Using explainable AI methods with artificial neural networks (ANN) reveals climate patterns in large ensemble simulations 2. A metric is proposed for quantifying the uncertainty of an ANN visualization method that extracts signals from different external forcings 3. Predictions from an ANN trained using a large ensemble without time-evolving aerosols show the highest correlation with actual observations
  • 43.
    QUESTIONS Zachary Labe 1. Usingexplainable AI methods with artificial neural networks (ANN) reveals climate patterns in large ensemble simulations 2. A metric is proposed for quantifying the uncertainty of an ANN visualization method that extracts signals from different external forcings 3. Predictions from an ANN trained using a large ensemble without time-evolving aerosols show the highest correlation with actual observations Labe, Z.M. and E.A. Barnes (2021), Detecting climate signals using explainable AI with single-forcing large ensembles. Journal of Advances in Modeling Earth Systems, DOI:10.1029/2021MS002464