Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks

• URL: http://arxiv.org/abs/2412.02924v1
• Date: Wed, 04 Dec 2024 00:27:54 GMT
• Title: Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks
• Abstract summary: We propose a novel loss decomposition strategy that breaks down the loss into separate phase and amplitude components.<n>This technique improves the long-term prediction accuracy of neural networks in wave propagation tasks by explicitly accounting for numerical errors.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting [0.0]
  High-resolution precipitation nowcasting is critical for reducing the impacts of severe weather but remains difficult because of rapid storm evolution.<n>Deep learning models have shown great promise for this task, but their predictive skill often deteriorates over longer forecast horizons.<n>We introduce GenONet, a novel architecture for long-range precipitation forecasting up to 3 hours, specifically designed to produce sharp and physically consistent results.
  arXiv  Detail & Related papers  (2026-09-01T01:30:33Z)
• Towards Scaling Law Analysis For Spatiotemporal Weather Data [50.25336689856158]
  We extend neural scaling analysis for autoregressive weather forecasting from single-step training loss to long rollouts and per-channel metrics.<n>We find strong cross-channel and cross-horizon heterogeneity: pooled scaling can look favorable while many channels degrade at late leads.<n>We discuss implications for weighted objectives, horizon-aware curricula, and resource allocation across outputs.
  arXiv  Detail & Related papers  (2026-04-06T18:14:53Z)
• TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting [67.91113180885601]
  TimeAPN explicitly models and predicts non-stationary factors from both the time and frequency domains.<n>TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons.<n>It outperforms state-of-the-art reversible normalization methods.
  arXiv  Detail & Related papers  (2026-03-18T07:21:24Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition [0.0]
  We present a physics-based deep learning framework for data-driven prediction of wave propagation in fluid media. The proposed approach combines a denoising-based convolutional autoencoder for reduced latent representation with an attention-based recurrent neural network. We show that the MI2A framework significantly improves the accuracy and stability of long-term predictions.
  arXiv  Detail & Related papers  (2025-04-15T17:47:20Z)
• Binned Spectral Power Loss for Improved Prediction of Chaotic Systems [0.0]
  We introduce a novel approach to mitigate the spectral bias which we call the Binned Spectral Power ( BSP) Loss. Unlike traditional losses that focus on pointwise misfits, our BSP loss explicitly penalizes deviations in the energy distribution across different scales. Our results demonstrate that the BSP loss significantly improves the stability and spectral accuracy of neural forecasting models.
  arXiv  Detail & Related papers  (2025-02-01T15:58:21Z)
• OneForecast: A Universal Framework for Global and Regional Weather Forecasting [67.61381313555091]
  We propose a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks.<n>By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region.<n>We introduce an adaptive messaging mechanism, using dynamic gating units, to deeply integrate node and edge features for more accurate extreme event forecasting.
  arXiv  Detail & Related papers  (2025-02-01T06:49:16Z)
• Advancing Spatio-temporal Storm Surge Prediction with Hierarchical Deep Neural Networks [1.024113475677323]
  Coastal regions in North America face major threats from storm surges caused by hurricanes and nor'easters. Traditional numerical models, while accurate, are computationally expensive, limiting their practicality for real-time predictions. This study introduces a hierarchical deep neural network (HDNN) combined with a convolutional autoencoder (CAE) to accurately and efficiently predict storm surge time series.
  arXiv  Detail & Related papers  (2024-10-01T15:09:40Z)
• Loss Shaping Constraints for Long-Term Time Series Forecasting [79.3533114027664]
  We present a Constrained Learning approach for long-term time series forecasting that respects a user-defined upper bound on the loss at each time-step. We propose a practical Primal-Dual algorithm to tackle it, and aims to demonstrate that it exhibits competitive average performance in time series benchmarks, while shaping the errors across the predicted window.
  arXiv  Detail & Related papers  (2024-02-14T18:20:44Z)
• Performative Time-Series Forecasting [71.18553214204978]
  We formalize performative time-series forecasting (PeTS) from a machine-learning perspective. We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts. We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-09T18:34:29Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting [50.23240107430597]
  We design a special Transformer, i.e., Channel Aligned Robust Blend Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting. First, CARD introduces a channel-aligned attention structure that allows it to capture both temporal correlations among signals. Second, in order to efficiently utilize the multi-scale knowledge, we design a token blend module to generate tokens with different resolutions. Third, we introduce a robust loss function for time series forecasting to alleviate the potential overfitting issue.
  arXiv  Detail & Related papers  (2023-05-20T05:16:31Z)
• Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data [37.69303106863453]
  We propose a novel approach for phase-resolved wave surface reconstruction using neural networks. Our approach utilizes synthetic yet highly realistic training data on uniform one-dimensional grids.
  arXiv  Detail & Related papers  (2023-05-18T12:30:26Z)
• STGIN: A Spatial Temporal Graph-Informer Network for Long Sequence Traffic Speed Forecasting [8.596556653895028]
  This study proposes a new spatial-temporal neural network architecture to handle the long-term traffic parameters forecasting issue. The attention mechanism potentially guarantees long-term prediction performance without significant information loss from distant inputs.
  arXiv  Detail & Related papers  (2022-10-01T05:58:22Z)
• Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling [32.15071712355222]
  We show how to reduce the maximum mismatch for waveforms in a validation set by 13.4 times. The most significant improvement comes from the addition of a second network that models the residual error.
  arXiv  Detail & Related papers  (2022-03-16T07:12:42Z)
• Extreme precipitation forecasting using attention augmented convolutions [0.913755431537592]
  We propose a self-attention augmented convolution mechanism for extreme precipitation forecasting. Our experimental results show that the framework outperforms classical convolutional models by 12%. The proposed method increases machine learning as a tool for gaining insights into the physical causes of changing extremes.
  arXiv  Detail & Related papers  (2022-01-31T18:16:03Z)
• N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting [17.53378788483556]
  Two common challenges afflicting long-horizon forecasting are the volatility of the predictions and their computational complexity. We introduce N-HiTS, a model which addresses both challenges by incorporating novel hierarchical and multi-rate data sampling techniques. We conduct an empirical evaluation demonstrating the advantages of N-HiTS over the state-of-the-art long-horizon forecasting methods.
  arXiv  Detail & Related papers  (2022-01-30T17:52:19Z)
• Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction [77.57991021445959]
  We propose a neural layer based on the ideas of temporal attention and multi-head attention to extend the capability of the underlying neural network. The effectiveness of our approach is validated using large-scale limit-order book market data.
  arXiv  Detail & Related papers  (2022-01-14T14:02:19Z)
• Adversarial Refinement Network for Human Motion Prediction [61.50462663314644]
  Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend. We propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation.
  arXiv  Detail & Related papers  (2020-11-23T05:42:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.