A Machine Learning Approach to Modeling Tropical Cyclone Wind Field Uncertainty

Abstract

Tropical cyclone (TC) risk assessment models and probabilistic forecasting systems rely on large ensembles to simulate the track trajectories, intensities, and spatial distributions of damaging winds from severe events. Given computational constraints associated with the generation of such ensembles, the representation of TC winds is typically based on very simple parametric formulations. Such models strongly underestimate the full range of TC wind field variability and thus do not allow for accurate representation of the risk profile. With this in mind, this study explores the potential of machine learning algorithms as an alternative to current parametric methods. First, a catalog of high-resolution TC wind simulations is assembled for the western North Pacific using the Weather Research and Forecasting (WRF) Model. The simulated wind fields are then decomposed via principal component analysis (PCA) and a quantile regression forest model is trained to predict the conditional distributions of the first three principal component (PC) weights. With this model, predictions can be made for any quantiles in the distributions of the PC weights thereby providing a way to account for uncertainty in the modeled wind fields. By repeatedly sampling the quantile values, probabilistic maps for the likelihood of attaining given wind speed thresholds can be easily generated. Similarly the inclusion of such a model as part of a TC risk assessment framework can greatly increase the range of wind field patterns sampled, providing a broader view of the threat posed by TC winds.

Prediction of Idai and 38 Other Tropical Cyclones and Storms in the Mozambique Channel

“…Several promising studies using AI for TC detection and prediction have already been published (e.g. Jin et al, 2008;Loridan et al, 2017;Mercer and Grimes, 2017;Matsuoka et al, 2018;Wimmers et al, 2019). One can hope that a continuing improvement of AI technology can be harnessed to enhance high-impact weather forecasting in regions with a vulnerable population, including south-eastern Africa.…”

Machine Learning in Tropical Cyclone Forecast Modeling: A Review

“…Previously, modeling wind uncertainty was a challenging topic, and traditional empirical equations have difficulty in describing the real wind field associated with TCs. In [145], PCA and RF were used to train the model to predict the conditional distribution of the first three principal component weights, thus providing a method to model the uncertainty of the wind field. This study may be able to provide a viable way of thinking for more precise representation of the initial vortex structure in the future.…”

Forecasting Severe Weather with Random Forests

“…Many of these studies have applied machine learning (ML) to the prediction task; in general, ML techniques have demonstrated great promise in applications to high-impact weather prediction (e.g., McGovern et al 2017McGovern et al , 2019. In addition to severe weather, ML has demonstrated success in forecasting heavy precipitation (e.g., Gagne et al 2014;Herman and Schumacher 2018a,b;Whan and Schmeits 2018;Loken et al 2019), cloud ceiling and visibility (e.g., Herman and Schumacher 2016;Verlinden and Bright 2017), and tropical cyclones (Loridan et al 2017;Alessandrini et al 2018;Wimmers et al 2019). Furthermore, automated probabilistic guidance, including ML algorithms, have been identified as a priority area for integrating with the operational forecast pipeline (e.g., Rothfusz et al 2014;Karstens et al 2018).…”