The data reduction system of the Gaia space mission generates a large amount of intermediate data and plots for diagnostics, beyond practical possibility of full human evaluation. We investigate the feasibility of adoption of deep learning tools for automatic detection of data anomalies, focusing on convolutional neural networks and comparing with a multilayer perceptron. The results evidence very good accuracy (∼99.7%) in the classification of the selected anomalies.

A Deep Learning Approach to Anomaly Detection in the Gaia Space Mission Data

DRUETTO, ALESSANDRO;ROBERTI, MARCO;Cancelliere R.;Cavagnino D.;
2019-01-01

Abstract

The data reduction system of the Gaia space mission generates a large amount of intermediate data and plots for diagnostics, beyond practical possibility of full human evaluation. We investigate the feasibility of adoption of deep learning tools for automatic detection of data anomalies, focusing on convolutional neural networks and comparing with a multilayer perceptron. The results evidence very good accuracy (∼99.7%) in the classification of the selected anomalies.
15th International Work-Conference on Artificial Neural Networks, IWANN 2019
Gran Canaria, Spain.
June 12-14, 2019
Lecture Notes in Computer Science, Advances in Computational Intelligence
Ignacio Rojas, Gonzalo Joya, Andreu Catala
11507
390
401
https://www.springer.com/series/558
Astronomical data; Big data; Deep learning; Diagnostics
Druetto A.; Roberti M.; Cancelliere R.; Cavagnino D.; Gai M.
File in questo prodotto:
File Dimensione Formato  
IWANN2019.pdf

Accesso aperto

Descrizione: Articolo
Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 411.21 kB
Formato Adobe PDF
411.21 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1706809
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 2
social impact