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

2026-02-20

AI Summary

This work proposes RGD-Blast, a deep surrogate model for blast wave propagation that addresses the challenges of strong nonlinearity, steep gradients, high computational cost, and the degradation of long-term prediction accuracy in existing machine learning surrogates—particularly under out-of-distribution conditions such as complex urban environments. By integrating multi-scale feature extraction with a dynamic-static feature coupling mechanism, RGD-Blast effectively mitigates error propagation inherent in autoregressive forecasting, significantly enhancing generalization across unseen building layouts and varying explosion parameters. The model achieves computational efficiency two orders of magnitude higher than conventional numerical simulations while maintaining comparable accuracy, demonstrating exceptional long-horizon predictive performance and robustness with an average RMSE below 0.01 and R² exceeding 0.89 over 280 time steps.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• blast wave prediction
• long-term forecasting
• out-of-distribution generalization
• error accumulation
• spatio-temporal dynamics

Innovation

• deep surrogate model
• multi-scale module
• dynamic-static feature coupling
• out-of-distribution generalization
• long-term blast wave prediction