5B.6 Using Random Forest to Generate Probability of Cloud-to-Ground

Monday, 28 August 2017: 11:45 AM
St. Gallen (Swissotel Chicago)
Tiffany C. Meyer, CIMMS/Univ. of Oklahoma, and NOAA/NSSL, Norman, OK; and K. M. Calhoun, D. M. Kingfield, and C. Karstens

Handout (1.5 MB)

A new Multi-Radar/Multi-Sensor (MRMS) cloud-to-ground (CG) lightning probability product has been created using machine learning methods. With storm-based inputs of Earth Network’s in-cloud lightning, Vaisala’s cloud-to-ground lightning, MRMS radar derived products including the Maximum Expected Size of Hail (MESH) and Vertically Integrated Liquid (VIL), and near storm environmental data including lapse rate and CAPE, a random forest algorithm was trained to produce probabilities of CG lightning. Verification of individual storm objects has been completed to determine how well the algorithm performs in different regions of the United States. As part of the Prototype Probabilistic Hazard Information experiment in the Hazardous Weather Testbed this year, forecasters used this product to create rapidly updating probability grids for the threat of CG lightning for 0-60 minutes.
- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner