<ul><li>Space-Time Projection (STP) is introduced as a data-driven forecasting approach for high-dimensional and time-resolved data.</li><li>STP computes extended space-time proper orthogonal modes from training data to generate forecasts by projecting these modes onto new data.</li><li>The method relies on the orthogonality and optimal correlation of the modes, and no additional hyperparameters are required.</li><li>Comparative studies with LSTM neural networks showed that STP consistently provided more accurate forecasts.</li></ul>

Data-Driven Forecasting of High-Dimensional Transient and Stationary Processes via Space-Time Projection

Discover more