Texto completo
Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (676kB) | Vista Previa |
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.
Título: | A Deep Learning Approach to Space Weather Proxy Forecasting for Orbital Prediction |
---|---|
Autor/es: |
|
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 |
Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (676kB) | Vista Previa |
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.
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 |