Short‐Term Forecasting of Wind Gusts at Airports Across CONUS Using Machine Learning

Abstract

Short‐term forecasting of wind gusts, particularly those of higher intensity, is of great societal importance but is challenging due to the presence of multiple gust generation mechanisms. Wind gust observations from eight high‐passenger‐volume airports across the continental United States (CONUS) are summarized and used to develop predictive models of wind gust occurrence and magnitude. These short‐term (same hour) forecast models are built using multiple logistic and linear regression, as well as artificial neural networks (ANNs) of varying complexity. A suite of 19 upper‐air predictors drawn from the ERA5 reanalysis and an autoregressive (AR) term are used. Stepwise procedures instruct predictor selection, and resampling is used to quantify model stability. All models are developed separately for the warm (April–September) and cold (October–March) seasons. Results show that ANNs of 3–5 hidden layers (HLs) generally exhibit higher hit rates than logistic regression models and also improve skill with respect to wind gust magnitudes. However, deeper networks with more HLs increase false alarm rates in occurrence models and mean absolute error in magnitude models due to model overfitting. For model skill, inclusion of the AR term is critical while the majority of the remaining skill derives from wind speeds and lapse rates. A predictive ceiling is also clearly demonstrated, particularly for the strong and damaging gust magnitudes, which appears to be partially due to ERA5 predictor characteristics and the presence of mixed wind climates.

Quantifying the compound hazard of freezing rain and wind gusts across CONUS

“…The geospatial atlas [55] of FZG compound hazard presented herein is designed to inform infrastructure design codes and to aid in hazard mitigation planning. The FZG timeseries can also be used to condition statistical downscaling model [47,56] for use in examining long-term variability/trends in frequency and/or severity and derive future projections.…”

“…Many stations within this swath exhibit >6 h of FZ per year. The Northern and Southern Great Plains and Northeast also tend to experience both a higher frequency of G > 10.5 ms −1 and higher magnitude extreme wind gusts [37,48] (figure 2(b)). FZ is also indicated frequently (>6 h yr −1 ) in the Northwest but there are relatively few mentions of FZ or ice accumulation in the Storm Reports possibly due to the low population density and fewer infrastructure assets.…”

Ten-Meter Wind Speed Forecast Correction in Southwest China Based on U-Net Neural Network

“…To quantitatively evaluate the wind field correction effect of statistical post-processing, four forecast verification methods were employed in this study: the root mean square error (RMSE) [42], the mean absolute error skill score (MAESS) [43], the hit rate (HR) [44], and the pa ern correlation coefficient (PCC) [45]. The corresponding formulas are as follows: The U-Net model was trained using data from 2000 to 2017, with 2018 data used as the validation set for the forecast correction in the southwestern region of China in 2019.…”

“…To quantitatively evaluate the wind field correction effect of statistical post-processing, four forecast verification methods were employed in this study: the root mean square error (RMSE) [42], the mean absolute error skill score (MAESS) [43], the hit rate (HR) [44], and the pattern correlation coefficient (PCC) [45]. The corresponding formulas are as follows:…”