Skip to content
Christman Field Latest Observations
Select Units
Date Time
MST
Temp
°F
RH
%
DewPt
°F
Wind
mph
Dir
°
Gust
mph
Dir
°
Press
in Hg
Solar
W/m^2
Prec
in
2023-01-31 22:10 10.6 78.0 5.1 2.2 216 4.9 244 24.900 0.0 0.00
2023-01-31 22:05 10.3 78.3 4.9 3.1 247 3.8 248 24.899 0.0 0.00
2023-01-31 22:00 9.5 80.2 4.6 4.5 219 5.5 255 24.897 0.0 0.00
2023-01-31 21:55 11.1 76.3 5.1 4.2 262 8.2 255 24.896 0.0 0.00
2023-01-31 21:50 9.0 86.9 5.9 5.5 251 8.9 253 24.898 0.0 0.00
2023-01-31 21:45 5.8 84.0 2.0 3.7 265 5.0 247 24.899 0.0 0.00
2023-01-31 21:40 6.2 83.5 2.2 3.5 259 4.4 247 24.897 0.0 0.00
2023-01-31 21:35 5.7 85.8 2.4 2.7 317 3.5 316 24.896 0.0 0.00
2023-01-31 21:30 5.3 84.5 1.7 3.1 299 4.3 261 24.899 0.1 0.00
2023-01-31 21:25 5.2 84.3 1.5 2.7 248 4.3 237 24.901 0.0 0.00
2023-01-31 21:20 5.3 82.4 1.1 1.8 249 3.2 249 24.899 0.0 0.00
2023-01-31 21:15 4.7 83.7 0.9 0.8 286 2.1 286 24.897 0.1 0.00
2023-01-31 21:10 4.9 82.6 0.7 1.8 343 2.4 351 24.898 0.1 0.00
2023-01-31 21:05 4.9 82.2 0.7 3.0 351 3.7 310 24.900 0.0 0.00
2023-01-31 21:00 5.1 80.8 0.5 3.2 310 3.9 326 24.900 0.0 0.00
2023-01-31 20:55 6.6 79.4 1.6 3.4 326 4.5 345 24.900 0.0 0.00
2023-01-31 20:50 7.8 78.0 2.3 3.6 1 4.2 4 24.895 0.0 0.00
2023-01-31 20:45 7.3 82.0 3.0 2.6 350 3.0 351 24.895 0.0 0.00
2023-01-31 20:40 5.6 83.8 1.8 2.1 288 2.8 299 24.897 0.0 0.00
2023-01-31 20:35 5.8 78.4 0.5 2.5 231 4.7 337 24.895 0.0 0.00
2023-01-31 20:30 6.4 82.6 2.3 4.9 337 5.8 349 24.894 0.0 0.00
2023-01-31 20:25 5.7 82.4 1.5 3.5 11 4.8 11 24.892 0.0 0.00
2023-01-31 20:20 5.8 81.1 1.3 2.3 356 3.8 12 24.889 0.0 0.00
2023-01-31 20:15 6.4 79.5 1.4 2.1 66 3.4 252 24.889 0.0 0.00
2023-01-31 20:10 7.0 82.2 2.7 2.9 252 3.6 263 24.885 0.0 0.00
2023-01-31 20:05 7.2 83.1 3.1 4.5 264 5.5 260 24.888 0.0 0.00
2023-01-31 20:00 6.8 81.0 2.2 4.6 249 5.7 256 24.887 0.0 0.00
2023-01-31 19:55 6.5 83.1 2.5 4.5 257 5.3 244 24.890 0.0 0.00
2023-01-31 19:50 7.5 79.7 2.6 2.3 229 3.1 228 24.889 0.0 0.00
2023-01-31 19:45 7.4 82.0 3.0 2.1 212 2.6 171 24.889 0.1 0.00
Date Time
MST
Temp
°C
RH
%
DewPt
°C
Wind
m/s
Dir
°
Gust
m/s
Dir
°
Press
hPa
Solar
W/m^2
Prec
mm
2023-01-31 22:10 -11.9 78.0 -15.0 1.0 216 2.2 244 843.20 0.0 0.00
2023-01-31 22:05 -12.0 78.3 -15.0 1.4 247 1.7 248 843.19 0.0 0.00
2023-01-31 22:00 -12.5 80.2 -15.2 2.0 219 2.5 255 843.12 0.0 0.00
2023-01-31 21:55 -11.6 76.3 -14.9 1.9 262 3.7 255 843.06 0.0 0.00
2023-01-31 21:50 -12.8 86.9 -14.5 2.5 251 4.0 253 843.13 0.0 0.00
2023-01-31 21:45 -14.6 84.0 -16.7 1.7 265 2.2 247 843.17 0.0 0.00
2023-01-31 21:40 -14.4 83.5 -16.5 1.5 259 2.0 247 843.12 0.0 0.00
2023-01-31 21:35 -14.6 85.8 -16.5 1.2 317 1.5 316 843.06 0.0 0.00
2023-01-31 21:30 -14.8 84.5 -16.8 1.4 299 1.9 261 843.18 0.1 0.00
2023-01-31 21:25 -14.9 84.3 -16.9 1.2 248 1.9 237 843.23 0.0 0.00
2023-01-31 21:20 -14.8 82.4 -17.2 0.8 249 1.4 249 843.16 0.0 0.00
2023-01-31 21:15 -15.2 83.7 -17.3 0.4 286 0.9 286 843.11 0.1 0.00
2023-01-31 21:10 -15.1 82.6 -17.4 0.8 343 1.1 351 843.16 0.1 0.00
2023-01-31 21:05 -15.1 82.2 -17.4 1.3 351 1.6 310 843.23 0.0 0.00
2023-01-31 21:00 -14.9 80.8 -17.5 1.4 310 1.7 326 843.21 0.0 0.00
2023-01-31 20:55 -14.1 79.4 -16.9 1.5 326 2.0 345 843.21 0.0 0.00
2023-01-31 20:50 -13.5 78.0 -16.5 1.6 1 1.9 4 843.03 0.0 0.00
2023-01-31 20:45 -13.7 82.0 -16.1 1.2 350 1.3 351 843.05 0.0 0.00
2023-01-31 20:40 -14.7 83.8 -16.8 1.0 288 1.3 299 843.11 0.0 0.00
2023-01-31 20:35 -14.6 78.4 -17.5 1.1 231 2.1 337 843.04 0.0 0.00
2023-01-31 20:30 -14.2 82.6 -16.5 2.2 337 2.6 349 843.00 0.0 0.00
2023-01-31 20:25 -14.6 82.4 -16.9 1.5 11 2.2 11 842.94 0.0 0.00
2023-01-31 20:20 -14.5 81.1 -17.1 1.0 356 1.7 12 842.83 0.0 0.00
2023-01-31 20:15 -14.2 79.5 -17.0 0.9 66 1.5 252 842.84 0.0 0.00
2023-01-31 20:10 -13.9 82.2 -16.3 1.3 252 1.6 263 842.70 0.0 0.00
2023-01-31 20:05 -13.8 83.1 -16.0 2.0 264 2.5 260 842.81 0.0 0.00
2023-01-31 20:00 -14.0 81.0 -16.5 2.1 249 2.5 256 842.78 0.0 0.00
2023-01-31 19:55 -14.2 83.1 -16.4 2.0 257 2.4 244 842.87 0.0 0.00
2023-01-31 19:50 -13.6 79.7 -16.4 1.0 229 1.4 228 842.83 0.0 0.00
2023-01-31 19:45 -13.7 82.0 -16.1 0.9 212 1.2 171 842.85 0.1 0.00
CIRA

Cooperative Institute for Research in the Atmosphere

Deep Machine Learning for High-Impact Weather Forecasting

February 10, 2017 11:15 am
ATS 101

Presented by: David John Gagne

Hosted by: Greg Hermand & Russ Schumacher

NCAR


The weather forecasting process has grown more complex in recent years with the growing amount of observational data and model output available to weather forecasters and the trend toward providing more impact-based decision support services. In order to assist forecasters and end-users with the task of managing the firehose of data, I have developed and evaluated machine learning forecast guidance systems for different high-impact weather phenomena. Machine learning models have demonstrated the ability to synthesize large, multifaceted datasets into accurate predictions for many different problems. In this presentation, I will discuss my storm-based machine learning hail forecasting model. The machine learning hail model identifies potential storms in convection-allowing model output, associates each forecast storm with an observed hailstorm, and then feeds storm and environmental information into a machine learning model to predict whether hail will occur and what the size distribution of the hail will be. The machine learning hail model has run in real-time on the Center for Analysis and Prediction of Storms and NCAR Convection-Allowing ensembles and has shown increased skill over other hail forecasting methods for predicting severe and significant severe hail. I will also discuss ongoing work on incorporating deep learning models into different weather prediction tasks. Deep learning models can identify multiscale features in gridded spatio-temporal data and use that information to produce better predictions than traditional machine learning approaches. A form of deep learning called generative adversarial networks will be discussed and demonstrated. It has the ability to learn complex feature representations in spatial data without the need of labeled examples. These deep learning methods will be demonstrated against traditional machine learning models on the GEFS Reforecast dataset for the task of predicting 2 m temperature anomalies.