Labe, Z.M., N.C. Johnson, and T.L. Delworth. Distinguishing the regional emergence of United States summer temperatures between observations and climate model large ensembles, 23rd Conference on Artificial Intelligence for Environmental Science, Baltimore, MD (Jan 2024). https://ams.confex.com/ams/104ANNUAL/meetingapp.cgi/Paper/431288
Distinguishing the regional emergence of United States summer temperatures between observations and climate model large ensembles
1. Distinguishing the regional emergence of United States
summer temperatures between observations
and climate model large ensembles
Zachary M. Labe
Postdoc in Seasonal-to-Decadal Variability and Predictability Division
NOAA GFDL and Princeton University
with…
Nathaniel C. Johnson, NOAA GFDL
Thomas L. Delworth, NOAA GFDL
1 February 2024 – 104th
AMS Annual Meeting
15B.3 – Artificial Intelligence for Environmental Science
@ZLabe
https://zacklabe.com/
5. Temperature anomalies [ °C ] relative to 1981-2010
Observations from NClimGrid
Climate model data from GFDL SPEAR_MED
United States – Summer
1920 2020
6. Temperature anomalies [ °C ] relative to 1981-2010
United States – Summer
1920 2020
Dust Bowl – July 1936
Mt. Pinatubo
2022
7. Eischeid, J. K., Hoerling, M. P., Quan, X. W., Kumar, A., Barsugli, J., Labe,
Z. M., ... & Zhang, X. (2023). Why Has the Summertime Central US
Warming Hole Not Disappeared? Journal of Climate, 36(20), 7319-7336.
https://doi.org/10.1175/JCLI-D-22-0716.1
Persistence is consistent with
unusually high summertime
rainfall over the region
Large ensembles demonstrate
that this rainfall trend can arise
from atmospheric internal
variability alone
Recent trend in tropical Pacific
SST can also reinforce this
pattern
11. We know some metadata…
+ What year is it?
+ Where did it come from?
[Labe and Barnes, 2022; ESS]
TEMPERATURE
12. TEMPERATURE
Neural network learns nonlinear
combinations of forced climate
patterns to identify the year
We know some metadata…
+ What year is it?
+ Where did it come from?
[Labe and Barnes, 2022; ESS]
13. ----ANN----
2 Hidden Layers
10 Nodes each
Ridge Regularization
Early Stopping
[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. 2022]
Surface Temperature Map Precipitation Map
+
TEMPERATURE
We know some metadata…
+ What year is it?
+ Where did it come from?
[Labe and Barnes, 2022; ESS]
22. June – August – Timing of Emergence (ToE) For Observations Over United States
23. How is the neural network able to detect the year prior to ~1990?
Temperature anomalies [ °C ] relative to 1981-2010
Machine learning predictions GFDL SPEAR_MED simulation
24. Machine Learning Explainability Methods – Ad Hoc Feature Attribution
Decrease
likelihood of year
Increase
likelihood of year
30. 50 km resolution 100 km resolution
2) Is it related to resolution?
SPEAR_MED SPEAR_LO
MAE
(years)
Mean Absolute Error (MAE) for ensemble member predictions over 1921 to 1989 for different spatial resolutions
33. TRENDS FROM 1921 TO 1950
SPEAR_MED, but NO anthropogenic aerosols SPEAR_MED, but NO anthropogenic forcings
Warmer
Colder
Fully-Coupled [Historical]
34. TRENDS FROM 1921 TO 1950
SPEAR_MED, but NO anthropogenic aerosols SPEAR_MED, but NO anthropogenic forcings
Warmer
Colder
Fully-Coupled [Historical]
35. TRENDS FROM 1921 TO 1950
Fully-Coupled [Historical] SPEAR_MED, but NO anthropogenic aerosols SPEAR_MED, but NO anthropogenic forcings
Warmer
Colder
36. TRENDS IN EVAPORATION
SPEAR_MED, but NO anthropogenic aerosols SPEAR_MED, but NO anthropogenic forcings
35
Increase
Decrease
Fully-Coupled [Historical]
37. KEY POINTS
1. Forced temperature changes have emerged in observations during
summer in the United States as detected by an artificial neural network
2. Increasing spatial resolution improves neural network skill for predicting the
year of a given summer temperature map
3. Western United States land surface climate properties contribute to earlier
timing of emergence predictions for the SPEAR climate model
zachary.labe@noaa.gov
Thursday, 1 February 2024
104th American Meteorological Society Annual Meeting
15B.3 – Artificial Intelligence for Environmental Science
Labe, Z.M., N.C. Johnson, and T.L Delworth (2024). Changes in United States summer temperatures
revealed by explainable neural networks, Earth’s Future, DOI: 10.1029/2023EF003981