Artificial intelligence for the EChO long-term mission planning tool

Álvaro García-Piquer, Ignasi Ribas, Josep Colomé

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

The Exoplanet Characterisation Observatory (EChO) was an ESA mission candidate competing for a launch opportunity within the M3 call. Its main aim was to carry out research on the physics and chemistry of atmospheres of transiting planets. This requires the observation of two types of events: primary and secondary eclipses. The events of each exoplanet have to be observed several times in order to obtain measurements with adequate Signal-to-Noise Ratio. Furthermore, several criteria must be considered to perform an observation, among which we can highlight the exoplanet visibility, its event duration, and the avoidance of overlapping with other tasks. It is important to emphasize that, since the communications for transferring data from ground stations to the spacecraft are restricted, it is necessary to compute a long-term plan of observations in order to provide autonomy to the observatory. Thus, a suitable mission plan will increase the efficiency of telescope operation, and this will result in a raise of the scientific return and a reduction of operational costs. Obtaining a long-term mission plan becomes unaffordable for human planners due to the complexity of computing the large amount of possible combinations for finding a near-optimal solution. In this contribution we present a long-term mission planning tool based on Genetic Algorithms, which are focused on solving optimization problems such as the planning of several tasks. Specifically, the proposed tool finds a solution that highly optimizes the objectives defined, which are based on the maximization of the time spent on scientific observations and the scientific return (e.g., the coverage of the mission survey). The results obtained on the large experimental set up support that the proposed scheduler technology is robust and can function in a variety of scenarios, offering a competitive performance which does not depend on the collection of objects to be observed. Finally, it is noteworthy that the conducted experiments allow us to size some aspects of the mission with the aim of guaranteeing its feasibility.

Idioma originalInglés
Título de la publicación alojadaObservatory Operations
Subtítulo de la publicación alojadaStrategies, Processes, and Systems V
EditoresAlison B. Peck, Chris R. Benn, Robert L. Seaman
EditorialSPIE
ISBN (versión digital)9780819496171
DOI
EstadoPublicada - 2014
Publicado de forma externa
EventoObservatory Operations: Strategies, Processes, and Systems V - Montreal, Canadá
Duración: 25 jun 201427 jun 2014

Serie de la publicación

NombreProceedings of SPIE - The International Society for Optical Engineering
Volumen9149
ISSN (versión impresa)0277-786X
ISSN (versión digital)1996-756X

Conferencia

ConferenciaObservatory Operations: Strategies, Processes, and Systems V
País/TerritorioCanadá
CiudadMontreal
Período25/06/1427/06/14

Huella

Profundice en los temas de investigación de 'Artificial intelligence for the EChO long-term mission planning tool'. En conjunto forman una huella única.

Citar esto