Quasi-Operational Testing of Real-Time Storm-Longevity Prediction via Machine Learning

Abstract

Real-time prediction of storm longevity is a critical challenge for National Weather Service (NWS) forecasters. These predictions can guide forecasters when they issue warnings and implicitly inform them about the potential severity of a storm. This paper presents a machine-learning (ML) system that was used for real-time prediction of storm longevity in the Probabilistic Hazard Information (PHI) tool, making it a Research-to-Operations (R2O) project. Currently, PHI provides forecasters with real-time storm variables and severity predictions from the ProbSevere system, but these predictions do not include storm longevity. We specifically designed our system to be tested in PHI during the 2016 and 2017 Hazardous Weather Testbed (HWT) experiments, which are a quasi-operational naturalistic environment. We considered three ML methods that have proven in prior work to be strong predictors for many weather prediction tasks: elastic nets, random forests, and gradient-boosted regression trees. We present experiments comparing the three ML methods with different types of input data, discuss trade-offs between forecast quality and requirements for real-time deployment, and present both subjective (human-based) and objective evaluation of real-time deployment in the HWT. Results demonstrate that the ML system has lower error than human forecasters, which suggests that it could be used to guide future storm-based warnings, enabling forecasters to focus on other aspects of the warning system.

Tropical Cyclones Intensity Prediction in the Western North Pacific Using Gradient Boosted Regression Tree Model

“…One of the core ideas of GBRT is to use the value of the negative gradient of the loss function in the current model as an approximation of the residual, which is essentially a first-order Taylor expansion of the loss function to fit a regression tree. Besides, the samples in the training set with the largest residuals are weighted the most heavily in GBRT (Schapire, 2003), encouraging the model to improve its worst predictions (McGovern et al, 2019). In addition, the importance of each input variable can be ranked in GBRT model.…”

On the Application of an Observations‐Based Machine Learning Parameterization of Surface Layer Fluxes Within an Atmospheric Large‐Eddy Simulation Model

“…Machine learning (ML) techniques have recently experienced a boost in popularity and have been applied to a variety of meteorological problems (e.g., McGovern et al., 2017). Recent examples of the use of ML for prediction of meteorological processes include thunderstorm initiation (Williams et al., 2008), mesoscale convective system initiation (Ahijevych et al., 2016), solar irradiance (Gagne, McGovern, Haupt, & Williams, 2017), convective winds (Lagerquist et al., 2017), hail (Burke et al., 2020; Gagne, McGovern, Haupt, Sobash, et al., 2017), 2‐m temperature (Rasp & Lerch, 2018), extreme precipitation (Herman & Schumacher, 2018), storm longevity (McGovern et al., 2019), wind power (Kosović et al., 2020), severe weather (Hill et al., 2020), fugitive methane source attribution (Travis et al., 2020), and upper‐level turbulence for aviation (Muñoz‐Esparza et al., 2020), to name a few. ML techniques provide an attractive alternative in pursuit of more efficient parameterizations of atmospheric processes (i.e., emulators) given their capability to untangle complex patterns in big‐data problems, and to be dynamically embedded within atmospheric models.…”