Search Results

You are looking at 1 - 2 of 2 items for :

  • Regression analysis x
  • The 1st NOAA Workshop on Leveraging AI in the Exploitation of Satellite Earth Observations & Numerical Weather Prediction x
  • Weather and Forecasting x
  • Refine by Access: All Content x
Clear All
John L. Cintineo, Michael J. Pavolonis, Justin M. Sieglaff, Anthony Wimmers, Jason Brunner, and Willard Bellon

in separate files. Based on the National Weather Service (NWS)-defined severe criteria of hail diameter ≥ 1 in. (25.4 mm), wind gust ≥ 50 kt (25.72 m s −1 ), or the presence of a tornado, 55.5% of the intense class images were from severe storms (irrespective of when a severe report occurred), while only 5.6% of the ordinary class images were from severe storms. This analysis confirms that storms that exhibit one or more of the storm top features (e.g., overshooting tops, cold-U, cloud

Restricted access
Eric D. Loken, Adam J. Clark, Amy McGovern, Montgomery Flora, and Kent Knopfmeier

based on linear regression (e.g., Glahn and Lowry 1972 ), ML techniques are not necessarily linear. A variety of ML approaches, other than regression, have been applied to weather prediction since the 1980s and include: artificial neural networks (ANNs; e.g., Key et al. 1989 ; Marzban and Stumpf 1996 ; Kuligowski and Barros 1998 ; Hall et al. 1999 ; Manzato 2007 ; Rajendra et al. 2019 ), support vector machines (e.g., Ortiz-García et al. 2014 ; Adrianto et al. 2009 ), clustering algorithms

Full access