TRACE: Reconstruction-Based Anomaly Detection in Ensemble and Time-Dependent Simulations

TL;DR

This paper introduces TRACE, a reconstruction-based anomaly detection method using convolutional autoencoders for high-dimensional, time-dependent simulation data, emphasizing the importance of temporal context for improved detection accuracy.

Contribution

It compares 2D and 3D autoencoders for anomaly detection in ensemble simulation data, demonstrating the benefits of spatio-temporal analysis over single-frame methods.

Findings

3D autoencoders better detect motion patterns.

Temporal context reduces redundant detections.

Detection errors depend on spatial mass distribution.

Abstract

Detecting anomalies in high-dimensional, time-dependent simulation data is challenging due to complex spatial and temporal dynamics. We study reconstruction-based anomaly detection for ensemble data from parameterized K\'arm\'an vortex street simulations using convolutional autoencoders. We compare a 2D autoencoder operating on individual frames with a 3D autoencoder that processes short temporal stacks. The 2D model identifies localized spatial irregularities in single time steps, while the 3D model exploits spatio-temporal context to detect anomalous motion patterns and reduces redundant detections across time. We further evaluate volumetric time-dependent data and find that reconstruction errors are strongly influenced by the spatial distribution of mass, with highly concentrated regions yielding larger errors than dispersed configurations. Our results highlight the importance of temporal context for robust anomaly detection in dynamic simulations.