PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention

• URL: http://arxiv.org/abs/2608.07681v1
• Date: Fri, 07 Aug 2026 18:09:31 GMT
• Title: PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention
• Abstract summary: PhysAttNet is a physics-informed attention framework for time series forecasting.<n>It augments a lightweight CNN forecaster with an attention head guided by domain-informed regularization.<n>It improves forecasting accuracy, generalization, and prediction performance on structurally important events.
• Score: 2.4965742139895313
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate and robust time series forecasting is essential in many applications involving physical processes, such as manufacturing monitoring and astrophysical event detection. In these settings, predictive models must remain reliable under noise, variability, and measurement uncertainty while capturing temporally localized structures corresponding to physically meaningful events. Convolutional neural networks (CNNs) are widely used for such tasks due to their computational efficiency and strong representational capacity. However, their learned temporal representations often exhibit unstable or physically inconsistent attention patterns, reducing robustness, generalization, and interpretability. This paper introduces PhysAttNet, a physics-informed attention framework for time series forecasting. PhysAttNet augments a lightweight CNN forecaster with an attention head guided by domain-informed regularization reflecting the structural properties of physical signals. Specifically, three complementary constraints are imposed during training: an alignment regularization that encourages attention to follow smooth, peak-centered temporal structures derived from the input signal, a smoothness regularization that enforces continuous temporal evolution, and a sparsity regularization that promotes selective focus on informative intervals. These differentiable regularization terms introduce physics-guided inductive bias without requiring annotated explanations or manual supervision. Experiments on two distinct applications, namely predicting cutting forces during milling and forecasting flares in blazar time series, demonstrate that PhysAttNet improves forecasting accuracy, generalization, and prediction performance on structurally important events.

Related papers

• SPEAR: Structure Property Explainability with Attention Regularization [0.6055934915901143]
  We introduce SPEAR (Structure Property Explainability with Attention Regularization), a framework that constrains attention distributions during training to improve their stability, selectivity, and physical interpretability.<n> SPEAR augments attention based regression with a learnable temperature that controls attention concentration and a smoothness penalty that enforces coherence across neighboring spectral positions.<n>We show that attention regularization produces smooth, contiguous attribution profiles aligned with causal features while preserving predictive accuracy.
  arXiv  Detail & Related papers  (2026-08-13T23:24:43Z)
• DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting [14.844711734126681]
  We propose a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics.<n> DSPR consistently improves forecasting accuracy and robustness under regime shifts.<n>It achieves state-of-the-art predictive performance, with Mean Conservation Accuracy exceeding 99% and Total Variation Ratio reaching up to 97.2%.
  arXiv  Detail & Related papers  (2026-04-08T06:21:10Z)
• From Observations to States: Latent Time Series Forecasting [65.98504021691666]
  We propose Latent Time Series Forecasting (LatentTSF), a novel paradigm that shifts TSF from observation regression to latent state prediction.<n>Specifically, LatentTSF employs an AutoEncoder to project observations at each time step into a higher-dimensional latent state space.<n>Our proposed latent objectives implicitly maximize mutual information between predicted latent states and ground-truth states and observations.
  arXiv  Detail & Related papers  (2026-01-30T20:39:44Z)
• Physics-Guided Counterfactual Explanations for Large-Scale Multivariate Time Series: Application in Scalable and Interpretable SEP Event Prediction [0.0]
  This work introduces a Physics-Guided Counterfactual Explanation framework for predicting solar energetic particles.<n>The framework achieves over 80% reduction in Dynamic Time Warping distance increasing the proximity, produces counterfactual explanations with higher sparsity, and reduces runtime by nearly 50% compared to state-of-the-art baselines such as DiCE.
  arXiv  Detail & Related papers  (2026-01-13T21:48:51Z)
• Defining Energy Indicators for Impact Identification on Aerospace Composites: A Physics-Informed Machine Learning Perspective [0.4104921880358479]
  Energy estimation is critical to impact identification on aerospace composites.<n>This study introduces a physics-informed framework that embeds domain knowledge into machine learning.
  arXiv  Detail & Related papers  (2025-11-03T13:58:03Z)
• Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting [50.298817606660826]
  We introduce Powerformer, a novel Transformer variant that replaces noncausal attention weights with causal weights that are reweighted according to a smooth heavy-tailed decay.<n>Our empirical results demonstrate that Powerformer achieves state-of-the-art accuracy on public time-series benchmarks.<n>Our analyses show that the model's locality bias is amplified during training, demonstrating an interplay between time-series data and power-law-based attention.
  arXiv  Detail & Related papers  (2025-02-10T04:42:11Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling [55.13352174687475]
  This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which generalizes weather forecasts to finer-grained temporal scales beyond training dataset.<n>Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale.<n>We also introduce a lead time-aware training framework to promote the generalization of the model at different lead times.
  arXiv  Detail & Related papers  (2024-05-22T16:21:02Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• 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)
• Latent State Inference in a Spatiotemporal Generative Model [3.7525506486107267]
  We focus on temperature and weather processes, including wave propagation dynamics, for which we assume that universal causes apply throughout space and time. A recently introduced DIsed Stemporal graph graph artificial Neural Architecture (DISTANA) is used and enhanced to learn such processes. We show that DISTANA, when combined with a retrospective latent state inference principle called active tuning, can reliably derive location-respective hidden causal factors.
  arXiv  Detail & Related papers  (2020-09-21T12:59:40Z)

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.