A Deep Surrogate Model for Robust and Generalizable Long-Term Blast Wave Prediction

TL;DR

This paper introduces RGD-Blast, a deep surrogate model that accurately predicts long-term blast wave dynamics with high speed and robustness, even on unseen urban layouts, by combining multi-scale features and dynamic-static coupling.

Contribution

The paper presents RGD-Blast, a novel deep surrogate model that improves long-term blast wave prediction accuracy and generalization through multi-scale modules and feature coupling mechanisms.

Findings

Achieves two orders of magnitude speedup over numerical methods.

Maintains RMSE below 0.01 on unseen layouts over 280 time steps.

Demonstrates strong generalization across different blast scenarios.

Abstract

Accurately modeling the spatio-temporal dynamics of blast wave propagation remains a longstanding challenge due to its highly nonlinear behavior, sharp gradients, and burdensome computational cost. While machine learning-based surrogate models offer fast inference as a promising alternative, they suffer from degraded accuracy, particularly evaluated on complex urban layouts or out-of-distribution scenarios. Moreover, autoregressive prediction strategies in such models are prone to error accumulation over long forecasting horizons, limiting their robustness for extended-time simulations. To address these limitations, we propose RGD-Blast, a robust and generalizable deep surrogate model for high-fidelity, long-term blast wave forecasting. RGD-Blast incorporates a multi-scale module to capture both global flow patterns and local boundary interactions, effectively mitigating error accumulation during autoregressive prediction. We introduce a dynamic-static feature coupling mechanism that fuses time-varying pressure fields with static source and layout features, thereby enhancing out-of-distribution generalization. Experiments demonstrate that RGD-Blast achieves a two-order-of-magnitude speedup over traditional numerical methods while maintaining comparable accuracy. In generalization tests on unseen building layouts, the model achieves an average RMSE below 0.01 and an R2 exceeding 0.89 over 280 consecutive time steps. Additional evaluations under varying blast source locations and explosive charge weights further validate its generalization, substantially advancing the state of the art in long-term blast wave modeling.