Google AI is now publically accessible for helping amateur scientists explore the new world. it examines the data obtained from the exoplanet-hunting probe conducted by NASA in order to recognize the most optimistic signals.
The technology has just disclosed evidences of two exoplanets studying a neural network for analyzing the data provided by the Kepler space telescope of NASA and correctly recognizing the planet signals. Since, the research has been conducted by analyzing nearly 700 stars.
Senior Software Engineer, Chris Shallue from the Google Brain Team wrote a blog post saying that, “We consider this a successful proof-of-concept for using machine learning to discover exoplanets, and more generally another example of using machine learning to make meaningful gains in a variety of scientific disciplines.
The research team has designed the new model of neural network based on Google’s AI that helps detecting low noise signals for exoplanets. The similar models are aimed to be developed soon by NASA for more of its missions such as ‘Kepler’s second mission’ and ‘Transiting Exoplanet Survey Satellite’. However, approximately 30,000 Kepler signals were already been analyzed and classified manually by humans, till the date.
Shallue added that, “We are excited to release our code for processing the Kepler data, training our neural network model, and making predictions about new candidate signals. We hope this release will prove a useful starting point for developing similar models for other NASA missions, like K2 (Kepler’s second mission) and the upcoming Transiting Exoplanet Survey Satellite mission.”