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

arXiv: https://arxiv.org/abs/2601.08659 · HTML: https://mlsanity.com/paper/2601.08659/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 5 of 5)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splatting](https://mlsanity.com/paper/2507.19718/) (2025)
- [ENTIRE: Learning-based Volume Rendering Time Prediction](https://mlsanity.com/paper/2501.12119/) (2025)
- [Machine Learning for Scientific Visualization: Ensemble Data Analysis](https://mlsanity.com/paper/2511.23290/) (2025)
- [SENSE: Self-Supervised Neural Embeddings for Spatial Ensembles](https://mlsanity.com/paper/2512.11145/) (2025)

## Abstract (arXiv)

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.