Classifying Convective Storms Using Machine Learning

Details

• Journal Title:
  Weather and Forecasting
• Personal Author:
  Jergensen, G. Eli ; McGovern, Amy ; Lagerquist, Ryan ; Smith, Travis
• NOAA Program & Office:
  OAR (Oceanic and Atmospheric Research) ; CIMMS (Cooperative Institute for Mesoscale Meteorological Studies) ; NSSL (National Severe Storms Laboratory)
• Description:
  We demonstrate that machine learning (ML) can skillfully classify thunderstorms into three categories: supercell, part of a quasi-linear convective system, or disorganized. These classifications are based on radar data and environmental information obtained through a proximity sounding. We compare the performance of five ML algorithms: logistic regression with the elastic-net penalty, random forests, gradient-boosted forests, and support-vector machines with both a linear and nonlinear kernel. The gradient-boosted forest performs best, with an accuracy of 0.77 ± 0.02 and a Peirce score of 0.58 ± 0.04. The linear support-vector machine performs second best, with values of 0.70 ± 0.02 and 0.55 ± 0.05, respectively. We use two interpretation methods, permutation importance and sequential forward selection, to determine the most important predictors for the ML models. We also use partial-dependence plots to determine how these predictors influence the outcome. A main conclusion is that shape predictors, based on the outline of the storm, appear to be highly important across ML models. The training data, a storm-centered radar scan and modeled proximity sounding, are similar to real-time data. Thus, the models could be used operationally to aid human decision-making by reducing the cognitive load involved in manual storm-mode identification. Also, they could be run on historical data to perform climatological analyses, which could be valuable to both the research and operational communities.
• Keywords:
  Atmospheric Science
• Source:
  Weather and Forecasting, 35(2), 537-559
• DOI:
  https://doi.org/10.1175/waf-d-19-0170.1
• ISSN:
  0882-8156 ; 1520-0434
• Format:
  PDF
• Publisher:
  American Meteorological Society
• Document Type:
  Journal Article
• Funding:
  Grant no. NA16OAR4320115
• Rights Information:
  Other
• Compliance:
  Library
• Main Document Checksum:
  urn:sha256:8d7499ac9e599344f3c8bfeac9d64ef94132c0e71010aef00032ee23419e5116
• Download URL:
  https://repository.library.noaa.gov/view/noaa/60125/noaa_60125_DS1.pdf
• File Type:
  [PDF - 6.02 MB ]