A Deep Learning Approach to Space Weather Proxy Forecasting for Orbital Prediction

Stevenson, Emma, Rodriguez-Fernandez, Victor, Minisci, Edmondo and Camacho Fernandez, David (2020). A Deep Learning Approach to Space Weather Proxy Forecasting for Orbital Prediction. En: "71st International Astronautical Congress - The CyberSpace Edition (IAC 2020)", 12-14 Oct 2020.

Descripción

Título: A Deep Learning Approach to Space Weather Proxy Forecasting for Orbital Prediction
Autor/es:
  • Stevenson, Emma
  • Rodriguez-Fernandez, Victor
  • Minisci, Edmondo
  • Camacho Fernandez, David
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: 71st International Astronautical Congress - The CyberSpace Edition (IAC 2020)
Fechas del Evento: 12-14 Oct 2020
Título del Libro: 71st International Astronautical Congress (IAC 2020)
Fecha: 2020
Materias:
Palabras Clave Informales: Solar Radio Flux, Deep Learning, Time Series Forecasting, Space Weather
Escuela: E.T.S.I. de Sistemas Informáticos (UPM)
Departamento: Sistemas Informáticos
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[thumbnail of IAC-57835.pdf]
Vista Previa
PDF (Portable Document Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (676kB) | Vista Previa

Resumen

The effect of atmospheric drag on spacecraft dynamics is considered one of the predominant sources of uncertainty in Low Earth Orbit. These effects are characterised in part by the atmospheric density, a quantity highly correlated to space weather. Current atmosphere models typically account for this through proxy indices such as the F10.7, but with variations in solar radio flux forecasts leading to significant orbit differences over just a few days, prediction of these quantities is a limiting factor in the accurate estimation of future drag conditions, and consequently orbital prediction. This has fundamental implications both in the short term, in the day-to-day management of operational spacecraft, and in the mid-to-long term, in determining satellite orbital lifetime. In this work, a novel deep residual architecture for univariate time series forecasting, N-BEATS, is employed for the prediction of the F10.7 solar proxy on the days-ahead timescales relevant to space operations. This untailored, pure deep learning approach has recently achieved state-of-the-art performance in time series forecasting competitions, outperforming well-established statistical, as well as statistical hybrid models, across a range of domains. The approach was found to be effective in single point forecasting up to 27-days ahead, and was additionally extended to produce forecast uncertainty estimates using deep ensembles. These forecasts were then compared to a persistence baseline and two operationally available forecasts: one statistical (provided by BGS, ESA), and one multi-flux neural network (by CLS, CNES). It was found that the N-BEATS model systematically outperformed the baseline and statistical approaches, and achieved an improved or similar performance to the multi-flux neural network approach despite only learning from a single variable.

Proyectos asociados

Tipo
Código
Acrónimo
Responsable
Título
Horizonte 2020
813644
Stardust-R
Massimiliano Vasile
Stardust Reloaded

Más información

ID de Registro: 64345
Identificador DC: https://oa.upm.es/64345/
Identificador OAI: oai:oa.upm.es:64345
Depositado por: Dr. Victor Rodríguez
Depositado el: 20 Oct 2020 17:06
Ultima Modificación: 20 Oct 2020 17:06
  • Logo InvestigaM (UPM)
  • Logo Sherpa/Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Logo Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Logo del Portal Científico UPM
  • Logo de REBIUN Sexenios Logo de la ANECA
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo de Recolecta
  • Logo de OpenCourseWare UPM