DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting

TL;DR

DSPR introduces a dual-stream neural network framework that combines statistical temporal modeling with physics-guided residual dynamics to improve industrial time series forecasting under regime shifts.

Contribution

The paper proposes DSPR, a novel architecture that explicitly decouples temporal patterns from residual dynamics using physics-informed modules, enhancing accuracy and interpretability.

Findings

Achieves state-of-the-art forecasting accuracy with over 99% Mean Conservation Accuracy.

Demonstrates robustness and physical plausibility across four industrial benchmarks.

Provides interpretable insights into physical interaction structures and transport delays.

Abstract

Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics. The first stream models the statistical temporal evolution of individual variables. The second stream focuses on residual dynamics through two key mechanisms: an Adaptive Window module that estimates flow-dependent transport delays, and a Physics-Guided Dynamic Graph that incorporates physical priors to learn time-varying interaction structures while suppressing spurious correlations. Experiments on four industrial benchmarks spanning heterogeneous regimes demonstrate that DSPR consistently improves forecasting accuracy and robustness under regime shifts while maintaining strong physical plausibility. It achieves state-of-the-art predictive performance, with Mean Conservation Accuracy exceeding 99% and Total Variation Ratio reaching up to 97.2%. Beyond forecasting, the learned interaction structures and adaptive lags provide interpretable insights that are consistent with known domain mechanisms, such as flow-dependent transport delays and wind-to-power scaling behaviors. These results suggest that architectural decoupling with physics-consistent inductive biases offers an effective path toward trustworthy industrial time-series forecasting. Furthermore, DSPR's demonstrated robust performance in long-term industrial deployment bridges the gap between advanced forecasting models and trustworthy autonomous control systems.