Artificial Intelligence has been playing a dynamic role within the field of space engineering and space technology. For example, intelligent robots at the moment are roaming on Mars, which might make certain decisions without commands from mission control.
Many of the galaxies within the Universe live in low-density environments which are generally known as “the field” or in small groups similar to Milky Way. Nevertheless, galaxy clusters are rarer to seek out, and this examine of the galaxy clusters will benefit the astronomers to understand the extreme environmental results on galaxy evolution and determine the cosmological parameters which govern the expansion of large scale structure within the Universe.
In astronomy, deep learning has proven itself to be very handy as a result of an abundance of imaging data available from the modern telescopes. The researchers said that this strategy would be further used to analyze the enormous outputs from the telescopes such as LSST (Large Synoptic Survey Telescope). Nevertheless, the deep learning approach is yet to be developed to detect in addition to determine the intrinsic properties of galaxy clusters from wide-field imaging data.
Lately, researchers from Lancaster University launched a novel deep learning approach known as Deep-CEE (Deep Learning for Galaxy Cluster Extraction and Evaluation) to seek for the galaxy clusters which are hundreds of thousands of lightyears across.
In response to the architecture, the Feature Network is positioned at the beginning of the Faster-RCNN algorithm, which takes a picture as an input. The Region Proposal Network is situated after the Feature Network which consists of a shallow architecture of three convolution layers with a ReLU activation layer-specific only to the first convolution layer. The primary role of this network is to generate probabilities of possible positions at which an object could be situated within an image.