Finding Patterns in Planets: A Neural Network Approach to the Exoplanet Dataset
We now know of over 3,700 exoplanets; an explosion in growth since the 1990s that shows no sign of abating. 96% of these new worlds have been discovered by either the radial velocity technique (that measures the doppler wobble of the star as it orbits with the planet) or the transit technique (the dip in brightness as the exoplanet crosses the line-of-sight between the star and Earth). However, both these techniques provide only a single measurement of the planet’s bulk properties; either the planet’s minimum mass or the radius. This leaves us with the conundrum of attempting to understand the exploding exoplanet dataset with scant details about the individual entries.
However, while the information per planet is small, the number of discoveries allows the potential for meaningful statistical analysis. Such techniques can identify relationships between properties to infer missing information. One pathway is to take advantage of the capabilities of neural networks. The principal behind such algorithms is to present the computer with a dataset but no a priori knowledge about links between the elements, allowing the network to locate its own patterns. This technique is particularly strong at finding connections between multiple elements at once (hard to view on a graph) and also at identifying connections that have been missed as they fall outside expectations (a real risk with exoplanet discoveries!). This research looks at one example of a neural network for estimating the mass and radius of a planet, based on properties available from both radial velocity and transit observations. This could be an added tool to guide sample selection in the future.
General Interest Talk: The Search for Our Beginnings: JAXA and the Hayabusa2 Mission
The Japan Aerospace Exploration Agency is Japan’s national space program. JAXA missions cover a wide range of astronomical interests, from X-ray observatories to Solar System exploration. A particular focus in the latter category is sample return from small bodies, such as asteroids and moons, in which Japan is a world leader. Our current mission, Hayabusa2, is an asteroid exploration spacecraft to return a sample of a carbonaceous chondrite meteorite to Earth. Hayabusa2 arrived at asteroid Ryugu at the end of June and is currently exploring the asteroid remotely in preparation for the first surface operations this fall. This mission is also linked with the NASA OSIRIS-REx asteroid explorer, which will arrive at asteroid Bennu at the end of the year. The two teams will exchange samples upon mission return. Here, I’ll introduce JAXA current and future planned missions and describe the latests results from Hayabusa2.