The similar days method for predicting near surface wind vectors

Abstract

A reliable forecast of the wind vector at a given site is an important problem with a broad scope of application. Many uses are in the field of wind power in which prediction of strong winds is important; other uses are in the field of civil engineering, where wind gusts are important to structural integrity. For predicting air pollution events or the hazard zone in case of toxic gas accidents the low wind scenarios are of the highest importance, especially under stable conditions. These low wind scenarios are the situations which meso-scale numerical models encounter difficulties or are often neglected when dealing with wind power tasks. Additional drawbacks of meso-scale numerical models in this context are their lack of site-specific detail and the fact that they are very demanding numerically.The 'similar days' method presented here is a method for the prediction of winds at a given location which works well also for low and variable wind conditions. The method is very efficient numerically: typically, runtime is less than a minute on a single PC. This method is based on using the last few hours' measurements at the given site and comparing it to an historical database. A set of criteria is defined to determine the time series similarity. Those similar days are used to construct the forecast.The similar days method was applied to a total of 5 years of measurements collected in two different locations. Very good agreement was achieved between prediction and measurements.

ARMA based approaches for forecasting the tuple of wind speed and direction

“…Bao et al developed a circular regression based approach along with Bayesian averaging method for bias correction of the forecasts obtained by numerical weather prediction models [24]. Kalsuner et al developed an approach for predicting wind vector based on the ''similar days'' approach, in which the wind pattern is compared with the historical data by using set of criteria defined for assessing similarity [25]. In addition, Potter and Negnevitsky employed an adaptive neuro-fuzzy inference system to forecast the wind vector [26].…”

Analog‐based post‐processing of the ALADIN‐LAEF ensemble predictions in complex terrain

“…Besides single fields, the use of spatially correlated observational variables (Wu et al ., ) also proved to be suitable. Satisfactory results were also achieved for the Southern Oscillation Index (SOI) forecasts using SOI measurements (Drosdowsky, ), point wind‐speed forecasts using wind speed measurements (Klausner et al ., ), for idealized cases with low‐order models (Ren and Chou, ), and general‐circulation modelling (Gao et al ., ; Ren and Chou, ).…”

Improving Wind Forecasts in the Lower Stratosphere by Distilling an Analog Ensemble Into a Deep Neural Network

“…Analog‐based methods, which are a type of machine learning, have been explored for decades (Lorenz, 1969) to develop predictions for a range of weather parameters. The basic idea is to find situations from the past similar to the current one and use what unfolded in these situations to estimate the future evolution of a parameter (Klausner et al., 2009; Panziera et al., 2011) or to infer the errors of today's prediction from a dynamical model's past performance (Delle Monache et al., 2013), an ensemble of model runs (Hamill & Whitaker, 2006), or other methods (Cervone et al., 2017; Mahoney et al., 2012).…”