At this point in time we are nearly a hundred percent certain about the existence of thousands of planets outside our solar system. The reason for finding other planets has always been a search for the next house for the human race to ensure survival.
If you think that “pollution and population” are our only problems let me assure you that even if in a wild dream the human race completely controls itself produced hazards, we are still endangered. To summarize that, I should say, think that much like our time in life, Earth’s time in the cosmos is limited. The result of what can be the death of a planet and a race. Also, finding a way to live on mars is not gonna help us much, in a longer run. Thus, making it super essential to find Earth like conditions on planets outside our solar system.
These planets are called exo-planets and Nasa has already registered thousands of such astronomical bodies that may be very close to being like earth itself.
Why are we talking about this here?
An algorithm found 50 new exoplanets that skipped the human eye. (NASA)
On analyzing the data from telescope missions of TESS and NASA’s Kepler mission, it was discovered that these planets were missed by the scientists while analyzing the data.
What’s interesting about this news is that although previous machine learning techniques could mark the possibility of a planet being real, this particular algorithm was able to register the possibility of them being exoplanets, making it a first in the world discovery of such a kind. With the help of the algorithm, astronomers can now better prioritize which are worthy of further explanation.
The 50 planets range from the size of Neptune to smaller than the Earth. Some have orbits that last as long as 200 days on Earth, while others spin around their respective stars as quickly as once a day.
Giada Arney, an astrobiologist at NASA’s Goddard Space Flight Center in Greenbelt, Maryland, hopes machine learning can help her and her colleagues find a needle of life in a haystack of data that will be collected by future telescopes and observatories such as NASA’s James Webb Space Telescope.
“These technologies are very important, especially for big data sets and especially in the exoplanet field,” Arney says. “Because the data we’re going to get from future observations is going to be sparse and noisy. It’s going to be really hard to understand. So using these kinds of tools has so much potential to help us.”
What else,
These Goddard scientists expect to one day use advanced machine learning techniques to accelerate the translation of data that reveals molecular proteins based on molecules emitted or mixed by long-range light in space. Scientists want the combination of advanced protein synthesis and innovation that helps reduce the small number of candidates who deserve costly and progressive research.
FDL teams Arney and Domagal-Goldman, with technical support from Google Cloud, provided advice on implementing a strategy called “neural network.” This technology can solve major complex problems in a process similar to how the brain works. In neural networks, billions of “nerves”, neurons in the brain, help us think and make decisions and interact with billions of people. The process of sending data. Adam Cobb, a computer science student at Oxford University, and Michael D. Himes, a mathematics student at the University of Central Florida, led a study that uses learning strategies to test “Bayesian Neural Network” against the widely accepted “Random Forest” model. Some teams other than the FDL research team at NASA used this latest method to study the condition of WASP-12b, an exoplanet discovered in 2008, according to enormous data collected by NASA’s Hubble Space Telescope.
Is the Bayesian Neural Network, actually better than other technologies out there?
