Winter Precipitation Type Diagnosis and Uncertainty Quantification with a Physically Consistent Machine Learning Method

TL;DR

This paper introduces an evidential neural network that predicts winter precipitation types and their uncertainties, improving forecast reliability by integrating physical consistency and uncertainty quantification from curated observational and model data.

Contribution

The paper presents a novel evidential neural network that jointly predicts precipitation type probabilities and epistemic uncertainty, enhancing winter weather forecasting accuracy and reliability.

Findings

The model provides meteorologically consistent forecasts.

Uncertainty quantification improves forecast reliability.

Outperforms existing thermodynamic and NWP models.

Abstract

Correctly forecasting the timing and location of changes in winter precipitation type could help decision makers mitigate the worst impacts of winter storms. Multiple precipitation type algorithms have been developed from both physical and statistical perspectives, but all of them struggle in certain scenarios, and most of them do not account for uncertainty with a single model. We developed an evidential neural network that can predict both the probability of each winter precipitation type as well as the epistemic uncertainty. We trained our model on quality controlled and curated observations from the crowd-sourced mPING dataset in conjunction with vertical profiles from the NOAA Rapid Refresh model analyses. Our static and interactive evaluation revealed that the data curation procedure resulted in meteorologically consistent forecasts and appropriately represents uncertainty in difficult regimes where predictability may be limited by the atmospheric representations of current NWP models. We compare our model to both the Rapid Refresh NWP model in addition to other thermodynamic area-based methods from June of 2020 through June of 2022 and from a High Resolution Rapid Refresh central plains case study from December 24-26, 2023.