NASA aims to bring interpretations of the data from future telescopes or satellites to a new level by using artificial intelligence, revealed space agency representatives in a statement.
NASA astrobiologist Giada Arney explained that the raw data collected by next generation telescopes and satellites is very likely to contain a lot of noise and be of an enormous volume, therefore AI tools could be very useful for its interpretation:
“These technologies are very important, especially for big data sets and especially in the exoplanet field”
NASA heliophysicist Madhulika Guhathakurta detailed that currently the agency is able to analyse “only a fraction” of the data collected from space crafts, due to limited resources, therefore scientists “need to utilise” AI tools.
To accelerate the development of appropriate AI tools, NASA’s Frontier Development Lab brings together talented people to accelerate the development of technologies, involving Silicon Valley startups and university researchers.The scientists leading the program aim to develop techniques to detect new exoplanets, for which the team partnered with Google Cloud and has deployed Bayesian “neural network” for prediction analyses.
Some of the developed during the summer FDL program tools are already being used to identify asteroids and their properties, including shape, size and spin rates, “find planets, and predict extreme solar radiation events”. The success of the project brings hope for further expansion of AI into space data analysis, and paths the way for deeper theoretical research:
“AI methods will help us free up processing power from our own brains by doing a lot of the initial legwork on difficult tasks”