Artificial Intelligence applications are becoming prominent among researchers who study space and the earth to find answers to some of the most pressing questions about evolution and the universe among others. Here are two such examples where artificial intelligence is being used to monitor solar phenomena and discovering patterns in Earth’s biological mass extinctions.
A new method is developed based on deep learning that enables stable classification and quantification of the image quality in ground-based full-disk solar images. It is essential to continuously monitor the Sun for a better understanding and predicting solar phenomena and the interaction of solar eruptions with Earth’s atmosphere and magnetosphere.
Objective image quality assessment is required for selecting the best images from multiple simultaneous observations and detecting the local quality degradation. In their recent study, researchers employed a neural network that would estimate the deviation of real observations from an ideal reference by learning the characteristics of high-quality images. By doing they achieved quality assessment that is similar to human interpretation. The paper describes an approach based on Generative Adversarial Networks (GAN) that are commonly used to obtain synthetic images.
A central concept in the theory of evolution is that the mass extinctions allow multiple new species to evolve. But contradicting this is a new study that uses artificial intelligence to examine the fossil record that says it is not true.
Now, scientists know that most of the species that have ever existed on Earth are extinct. This extinction of various species has been roughly balanced by the origination of other new species, with a few major imbalances that are temporary in nature and are known as mass extinction events.
The scientists affiliated with the Earth-Life Science Institute (ELSI) at Tokyo Institute of Technology have led a new study that uses machine learning to examine the co-occurrence of fossil species. They have found that radiations and extinctions are rarely connected, and thus mass extinctions likely rarely cause radiations of a comparable scale. Read the full article to know more about this study.
Head to the Great Learning Academy for free courses on Artificial Intelligence and Machine Learning.0