A Real-Time, Auto-Regression Method for In-Situ Feature Extraction in Hydrodynamics Simulations

2025-04-14

AI Summary

In fluid dynamics simulations, post-processing I/O overhead is substantial, and existing in situ analysis methods struggle to simultaneously achieve high accuracy and computational efficiency. To address this, we propose a lightweight, incremental autoregressive in situ feature extraction framework. Our method integrates spatiotemporal curve fitting with mini-batch online training, enabling low-intrusion, real-time analysis via autoregressive modeling and incremental learning. Its key contribution is the first simulation-oriented lightweight API library and in situ analysis framework, which preserves high fidelity while drastically reducing computational load. Evaluated on material deformation and white dwarf merger simulations, our approach achieves feature extraction accuracy of 94.44%–99.60%, with only 0.11%–4.95% additional computational overhead—effectively breaking the traditional accuracy-efficiency trade-off bottleneck.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Feature Construction/Reformulation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Hydrodynamics simulations are powerful tools for studying fluid behavior under physical forces, enabling extraction of features that reveal key flow characteristics. Traditional post-analysis methods offer high accuracy but incur significant computational and I/O costs. In contrast, in-situ methods reduce data movement by analyzing data during the simulation, yet often compromise either accuracy or performance. We propose a lightweight auto-regression algorithm for real-time in-situ feature extraction. It applies curve-fitting to temporal and spatial data, reducing data volume and minimizing simulation overhead. The model is trained incrementally using mini-batches, ensuring responsiveness and low computational cost. To facilitate adoption, we provide a flexible library with simple APIs for easy integration into existing workflows. We evaluate the method on simulations of material deformation and white dwarf (WD) mergers, extracting features such as shock propagation and delay-time distribution. Results show high accuracy (94.44%-99.60%) and low performance impact (0.11%-4.95%) demonstrating the method's effectiveness for accurate and efficient in-situ analysis.

Problem

• Real-time feature extraction in hydrodynamics simulations
• Reducing computational and I/O costs in simulation analysis
• Balancing accuracy and performance in in-situ methods

Innovation

• Lightweight auto-regression for real-time feature extraction
• Incremental mini-batch training for low computational cost
• Flexible library with simple APIs for easy integration