Detecting technical anomalies in high-frequency water-quality data using Artificial Neural Networks - Université de Pau et des Pays de l'Adour Accéder directement au contenu
Article Dans Une Revue Environmental Science and Technology Année : 2020

Detecting technical anomalies in high-frequency water-quality data using Artificial Neural Networks

Résumé

2 1 Anomaly detection (AD) in high-volume environmental data requires one to tackle a series of challenges associated with the typical low frequency of anomalous events, the broad-range of possible anomaly types and local non-stationary environmental conditions, suggesting the need for flexible statistical methods that are able to cope with unbalanced high-volume data problems. Here, we aimed to detect anomalies caused by technical errors in water-quality (turbidity and conductivity) data collected by automated in-situ sensors deployed in contrasting riverine and estuarine environments. We first applied a range of Artificial Neural Networks (ANN) that differed in both learning method and hyper-parameter values, then calibrated models using a Bayesian multiobjective optimisation procedure, and selected and evaluated the "best" model for each water-quality variable, environment and anomaly type. We found that semi-supervised classification was better able to detect sudden spikes, sudden shifts and small sudden spikes whereas supervised classification had higher accuracy for predicting long-term anomalies associated with drifts and periods of otherwise unexplained high-variability.
Fichier principal
Vignette du fichier
AD_ANN_ms_FINAL.pdf (2.51 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02929461 , version 1 (27-02-2021)

Identifiants

Citer

Javier Rodriguez Perez, Catherine Leigh, Benoit Liquet, Claire Kermorvant, Erin Peterson, et al.. Detecting technical anomalies in high-frequency water-quality data using Artificial Neural Networks. Environmental Science and Technology, 2020, 54 (21), pp.13719-13730. ⟨10.1021/acs.est.0c04069⟩. ⟨hal-02929461⟩
167 Consultations
288 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More