arXiv subjects

Guillaume Coulaud

Publications and source records attributed to Guillaume Coulaud.

4 recordsLinked to original sources

arXiv2026

Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection

Reconstruction-based methods are widely used for time series anomaly detection, where models are trained to reconstruct subsequences, and anomalies are identified through reconstruction errors. However, reported results are often hard to compare due to heterogeneous evaluation practices and underspecified inference procedures. In this paper, we revisit reconstruction-based anomaly detection in the univariate offline setting and study the role of the inference stride, which controls whether subsequences are processed as disjoint windows or with overlap. We propose a unified training, tuning, and multi-seed evaluation protocol on the curated TSB-AD benchmark, and study how overlapping inference affects anomaly detection performance for a range of reconstruction models, including PCA-based baselines, DLinear, an AutoEncoder, TimesNet, and Transformer variants. The results show that across all models, overlapping windows yield consistent improvements, with average relative gain up to +28%, and can alter method rankings. We further analyze variability across datasets, random seeds, and hyperparameter configurations. Finally, we complement the benchmark study with an evaluation on the full UCR archive using localization criteria aligned with sliding-window reconstruction. Overall, our results highlight that reconstruction-based anomaly detection performance depends not only on model architecture and training, but also on inference choices, motivating a clear and reproducible protocol. Our results show that reconstructionbased baselines achieve strong performance on both TSB-AD and UCR benchmarks, supporting them as competitive and practical approaches for univariate time series anomaly detection.

cs.LG↗

arXiv2026

TRAKNN: Efficient Trajectory Aware Spatiotemporal kNN for Rare Meteorological Trajectory Detection

Extreme weather events, such as windstorms and heatwaves, are driven by persistent atmospheric circulation patterns that evolve over several consecutive days. While traditional circulation-based studies often focus on instantaneous atmospheric states, capturing the temporal evolution, or trajectory, of these spatial fields is essential for characterizing rare and potentially impactful atmospheric behavior. However, performing an exhaustive similarity search on multi-decadal, continental-scale gridded datasets presents significant computational and memory challenges. In this paper, we propose TRAKNN (TRajectory Aware KNN), a fully unsupervised and data-agnostic framework for detecting geometrically rare short trajectories in spatio-temporal data with an exact kNN approach. TRAKNN leverages a recurrence-based algorithm that decouples computational complexity from trajectory length and efficient batch operations, maximizing computational intensity. These optimizations enable exhaustive analysis on standard workstations, either on CPU or on GPU. We evaluate our approach on 75 years of daily European sea-level pressure data. Our results illustrate that rare trajectories identified by TRAKNN correspond to physically coherent atmospheric anomalies and align with independent extreme-event databases.

stat.ML↗

arXiv2024

Investigations on Physics-Informed Neural Networks for Aerodynamics

Physics-Informed Neural Networks (PINNs) have recently emerged as a novel approach to simulate complex physical systems on the basis of both data observations and physical models. In this work, we investigate the use of PINNs for various applications in aerodynamics and we explain how to leverage their specific formulation to perform some tasks effectively. In particular, we demonstrate the ability of PINNs to construct parametric surrogate models, to achieve multiphysic couplings and to infer turbulence characteristics via data assimilation. The robustness and accuracy of the PINNs approach are analysed, then current issues and challenges are discussed.

math.AP↗

arXiv2023

Application of deep learning to the estimation of normalization coefficients in diffusion-based covariance models

Variational data assimilation in ocean models depends on the ability to model general correlation operators in the presence of coastlines. Grid-point filters based on diffusion operators are widely used for this purpose, but come with a computational bottleneck - the costly estimation of normalization factors for every model grid point. In this paper, we show that a simple convolutional neural network can effectively learn these normalization factors with better accuracy than the current operational methods. Our network is tested with a two-dimensional diffusion operator from the NEMOVAR ocean data assimilation system, applied to a global ocean grid with approximately one degree horizontal resolution. The network is trained on exact normalization factors estimated by a brute-force method. Knowing that convolutional networks can only model translation-equivariant functions, we ensure that the normalization estimation problem is indeed translation-equivariant. Specifically, we show how the number of inputs of this problem can be reduced while preserving translation equivariance. Adding the distance to the coastline as an input channel is found to improve the performance of the network around coastlines. Extensions to three-dimensional diffusion and to higher horizontal resolutions are discussed. Removing the computational bottleneck associated with normalization opens the way to using adaptive correlation models for operational ocean data assimilation. The code for this work is publicly available at https://github.com/FolkeKS/DL-normalization/tree/core-features

physics.data-an↗