Dynamic Time Warping as a New Evaluation for Dst Forecast with Machine Learning

TL;DR

This paper introduces a novel evaluation method using Dynamic Time Warping to better assess neural network forecasts of geomagnetic indices, addressing limitations of traditional metrics like RMSE and correlation.

Contribution

The study proposes a new Dynamic Time Warping-based metric for evaluating time series predictions, improving detection of persistence behavior in geomagnetic index forecasts.

Findings

The DTW-based metric effectively identifies persistence-like predictions.

Neural network models still exhibit persistence behavior despite traditional evaluation metrics.

Different training methodologies can reduce persistence effects in forecasts.

Abstract

Models based on neural networks and machine learning are seeing a rise in popularity in space physics. In particular, the forecasting of geomagnetic indices with neural network models is becoming a popular field of study. These models are evaluated with metrics such as the root-mean-square error (RMSE) and Pearson correlation coefficient. However, these classical metrics sometimes fail to capture crucial behavior. To show where the classical metrics are lacking, we trained a neural network, using a long short-term memory network, to make a forecast of the disturbance storm time index at origin time $t$ with a forecasting horizon of 1 up to 6 hours, trained on OMNIWeb data. Inspection of the model's results with the correlation coefficient and RMSE indicated a performance comparable to the latest publications. However, visual inspection showed that the predictions made by the neural network were behaving similarly to the persistence model. In this work, a new method is proposed to measure whether two time series are shifted in time with respect to each other, such as the persistence model output versus the observation. The new measure, based on Dynamical Time Warping, is capable of identifying results made by the persistence model and shows promising results in confirming the visual observations of the neural network's output. Finally, different methodologies for training the neural network are explored in order to remove the persistence behavior from the results.