Using Machine Learning with Polarimetric Radar Data to Predict Hail Size

During the summers from 2006 through 2015, CIMMS and NSSL conducted the Severe Hazards Analysis and Verification Experiment (SHAVE). The goal for SHAVE was to primarily collect hail reports at high spatial resolution following thunderstorms. This was completed by using student telephone operators who monitored Multi-Radar, Multi-Sensor (MRMS) outputs on a web-enabled data entry page. The project collected over 54,000 hail reports during the 10 years of operations. Cases exhibiting good spatial resolution have been collected and radar data, including MRMS data, have been processed. In total, 735 cases were processed, with 427 polarimetric cases yielding around 20,000 hail reports, and SHAVE reports were paired to both single-radar and MRMS data.

The Maximum Estimated Size of Hail (MESH) algorithm is an operational hail size estimation algorithm used with both for single-radar and MRMS data; it uses a vertical integration of reflectivity weighted by both height relative to the melting level and reflectivity magnitude. However, MESH, despite its name, is not meant to be a 1-to-1 estimate of the absolute maximum hail size expected. Rather, the MESH output is meant to represent the 75th percentile of observed hail diameters (i.e., ~75% of hail stones will be smaller than the MESH value). This 75% threshold is roughly accurate for both single-radar and MRMS applications. However, anecdotally, MESH is often used as a 1-to-1 estimate of maximum hail size, which then leads to mixed impressions regarding the accuracy of the algorithm when verification information is available.

Recently, an effort has started at CIMMS and NSSL to apply a range of machine learning techniques to the SHAVE data in an effort to improve hail size estimation (both in terms of detection and prediction). Machine learning techniques can vary from linear regression to random forests to neural networks. Multi-layered neural networks and convolutional neural networks are examples of deep learning techniques that can be applied to the hail sizing problem. The presentation will explore different data inputs to the techniques and different techniques’ capability to accurately predict hail size in a 1-to-1 manner. Since the techniques can operate on data ranging from simple images to derived radar statistics, different data inputs may lead to different performance of the machine learning techniques and different data configurations will be explored.