Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks
This work addresses a specific bottleneck in wave propagation forecasting for applications requiring real-time modeling, representing an incremental improvement in method design.
The paper tackles the problem of accumulating phase and amplitude errors in long-horizon wave predictions using deep neural networks by proposing a novel loss decomposition strategy, resulting in improved long-term prediction accuracy through explicit error accounting and reduced error accumulation.
Accurate prediction over long time horizons is crucial for modeling complex physical processes such as wave propagation. Although deep neural networks show promise for real-time forecasting, they often struggle with accumulating phase and amplitude errors as predictions extend over a long period. To address this issue, we propose a novel loss decomposition strategy that breaks down the loss into separate phase and amplitude components. This technique improves the long-term prediction accuracy of neural networks in wave propagation tasks by explicitly accounting for numerical errors, improving stability, and reducing error accumulation over extended forecasts.