# Developing Machine Learning-Based Watch-to-Warning Severe Weather Guidance from the Warn-on-Forecast System

arXiv: https://arxiv.org/abs/2603.20250 · HTML: https://mlsanity.com/paper/2603.20250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [A Comparative Analysis of XGBoost](https://mlsanity.com/paper/1911.01914/) (2019)
- [Using Machine Learning to Calibrate Storm-Scale Probabilistic Guidance of Severe Weather Hazards in the Warn-on-Forecast System](https://mlsanity.com/paper/2012.00679/) (2020)
- [Machine Learning Estimation of Maximum Vertical Velocity from Radar](https://mlsanity.com/paper/2310.09392/) (2023)

## Abstract (arXiv)

While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead times (0-3 hours), its application to slightly longer forecast windows remains relatively underexplored. In this study, we develop and evaluate a grid-based ML framework to predict the probability of severe weather hazards over the next 2-6 hours using forecast output from the Warn-on-Forecast System (WoFS). Our dataset includes WoFS ensemble forecasts valid every 5 minutes out to 6 hours from 108 days during the 2019--2023 NOAA Hazardous Weather Testbed Spring Forecasting Experiments. We train ML models to generate probabilistic forecasts of severe weather akin to Storm Prediction Center outlooks (i.e., likelihood of a tornado, severe wind, or severe hail event within 36 km of each point). We compare a histogram gradient-boosted tree (HGBT) model and a deep learning U-Net approach against a carefully calibrated baseline generated from 2-5 km updraft helicity. Results indicate that the HGBT and U-Net outperform the baseline, particularly at higher probability thresholds. The HGBT achieves the best performance metrics, but predicted probabilities cap at 60% while the U-net forecasts extend to 100%. Similar to previous studies, the U-Net produces spatially smoother guidance than the tree-based method. These findings add to the growing evidence of the effectiveness of ML-based CAM post-processing for providing short-term severe weather guidance.