Figure 5
From: Forecasting high-dimensional dynamics exploiting suboptimal embeddings
Forecast performance with the Lorenz’96I model for various numbers of variables: cases where (a) a half of the variables are substituted with random walks and (b) all variables are available. We computed the RMSE of the five-steps-ahead forecasts with randomly distributed embedding (RDE), multiview embedding (MVE), state-dependent weighting (SDW), single-best embedding based on the (μ + λ)-ES algorithm (SBE), single-variable embedding (SVE), all-variable embedding (AVE), and the proposed framework. These tests were carried out with 20 datasets generated with different random initial conditions and noise. The median, upper quartile, and lower quartile are shown.
