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

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

Description

Title: A Deep Learning Approach to Space Weather Proxy Forecasting for Orbital Prediction
Author/s:
  • Stevenson, Emma
  • Rodriguez-Fernandez, Victor
  • Minisci, Edmondo
  • Camacho Fernandez, David
Item Type: Presentation at Congress or Conference (Article)
Event Title: 71st International Astronautical Congress - The CyberSpace Edition (IAC 2020)
Event Dates: 12-14 Oct 2020
Title of Book: 71st International Astronautical Congress (IAC 2020)
Date: 2020
Subjects:
Freetext Keywords: Solar Radio Flux, Deep Learning, Time Series Forecasting, Space Weather
Faculty: E.T.S.I. de Sistemas Informáticos (UPM)
Department: Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (676kB) | Preview

Abstract

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.

Funding Projects

TypeCodeAcronymLeaderTitle
Horizon 2020813644Stardust-RMassimiliano VasileStardust Reloaded

More information

Item ID: 64345
DC Identifier: http://oa.upm.es/64345/
OAI Identifier: oai:oa.upm.es:64345
Deposited by: Dr. Victor Rodríguez
Deposited on: 20 Oct 2020 17:06
Last Modified: 20 Oct 2020 17:06
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM