Adapting a deep convolutional RNN model with imbalanced regression loss for improved spatio-temporal forecasting of extreme wind speed events in the short to medium range

Abstract

Abstract. The number of wind farms and amount of wind power production in Europe, both on- and offshore, have increased rapidly in the past years. To ensure grid stability and on-time (re)scheduling of maintenance tasks and to mitigate fees in energy trading, accurate predictions of wind speed and wind power are needed. Particularly, accurate predictions of extreme wind speed events are of high importance to wind farm operators as timely knowledge of these can both prevent damages and offer economic preparedness. This work explores the possibility of adapting a deep convolutional recurrent neural network (RNN)-based regression model to the spatio-temporal prediction of extreme wind speed events in the short to medium range (12 h lead time in 1 h intervals) through the manipulation of the loss function. To this end, a multi-layered convolutional long short-term memory (ConvLSTM) network is adapted with a variety of imbalanced regression loss functions that have been proposed in the literature: inversely weighted, linearly weighted and squared error-relevance area (SERA) loss. Forecast performance is investigated for various intensity thresholds of extreme events, and a comparison is made with the commonly used mean squared error (MSE) and mean absolute error (MAE) loss. The results indicate the inverse weighting method to most effectively shift the forecast distribution towards the extreme tail, thereby increasing the number of forecasted events in the extreme ranges, considerably boosting the hit rate and reducing the root-mean-squared error (RMSE) in those ranges. The results also show, however, that such improvements are invariably accompanied by a pay-off in terms of increased overcasting and false alarm ratio, which increase both with lead time and intensity threshold. The inverse weighting method most effectively balances this trade-off, with the weighted MAE loss scoring slightly better than the weighted MSE loss. It is concluded that the inversely weighted loss provides an effective way to adapt deep learning to the task of imbalanced spatio-temporal regression and its application to the forecasting of extreme wind speed events in the short to medium range.

ASER: Adapted squared error relevance for rare cases prediction in imbalanced regression

“…In this section, we discuss the impact of parameter settings on the weighting function. The first weighting function described in Equation (7) has two parameters, t w and k. We attempt to tune the weighting function parameters on nine simulated datasets, and two types of ASERA have been used to test the results.…”

“…Handling imbalanced data is a challenging technical issue that is important in various application scenarios, such as medical area (e.g., medical diagnosis 4 ), informatics (e.g., text categorization 5 ), and financial markets (e.g., fraudulent credit card transactions 6 ). In addition to these more traditional fields, there are also some new ones, such as meteorology (e.g., wind speed forecasts 7 ), biology (e.g., estimation of plant transpiration 8 ), geography (e.g., prediction of vegetation conditions 9 ), and metabolomics. 10 The problem of data imbalance has always been a challenge that many scientists strive to solve, but only a few aspects related to imbalanced learning have been addressed with some solutions.…”

Learning Extreme Vegetation Response to Climate Forcing: A Comparison of Recurrent Neural Network Architectures

“…These metrics are standard tools for evaluating deep learning models for predicting atmospheric variables such as wind speed (Scheepens et al, 2023) and precipitation (Shi et al, 2015).…”

Comprehensive Analysis and Evaluation of the Operation and Maintenance of Offshore Wind Power Systems: A Survey

“…Refs. [29,31,[128][129][130][131][132][133][134] mainly used machine learning, deep learning, wavelet transform, time-series analysis, and other methods to predict wind speed, wind power, wave height, and wave period, and to design optimal maintenance strategies. These studies have been empirically validated in different sea areas and time frames, and the results show that they outperform other traditional models.…”

“…A deep convolutional recurrent neural network and inverse weighted loss function were used for the spatiotemporal prediction of extreme wind speed events [134]. • A Markov decision process was used for the design of optimal maintenance strategies for wave energy converters [132].…”