Scientists have developed a machine-learning model that predicts potential Earth-like planet systems, a move that will speed up the future search for habitable planets.
The search for Earth-like exoplanets (planets orbiting stars other than the Sun) is a central focus of current planetary research, as it is highly likely that extraterrestrial life will be found there.
Researchers at the University of Bern in Switzerland have developed a groundbreaking machine-learning model that identifies planetary systems that could host Earth-like planets, in a study published in the journal Astronomy and Astrophysics, Europa Press reported on Wednesday.
A machine-learning model is a statistical tool trained on data to recognize certain types of patterns and make predictions.
Postdoctoral researcher Jeanne Davoult, lead author of the study, explained in a statement that the model is based on an algorithm she developed that was “trained to recognize and classify planetary systems that host Earth-like planets.”
The model builds on previous studies to infer a correlation between the presence or absence of an Earth-like planet and the properties of its system.
The algorithm was trained and tested using data from the so-called Berne Model of Planetary Formation and Evolution.
“The Berne Model provides insights into how planets formed, how they evolved, and what types of planets develop under certain conditions in a protoplanetary disk,” explained co-author Yann Alibert.
Since 2003, the Berne Model has been continuously developed at the University of Bern.
“The Berne Model is one of the few models in the world that provides such a wide range of interrelated physical processes and allows for such a study,” Alibert added.
The algorithm of the new machine learning model was trained and tested using data from the synthetic planetary system of the Berne Model.
“The results are impressive: the algorithm achieves accuracy values up to 0.99, which means that 99% of the systems identified by the machine learning model contain at least one Earth-like planet,” Davoult said. The model was then applied to observed planetary systems and identified 44 systems with a high probability of hosting previously undetected Earth-like planets.
A subsequent study confirmed the theoretical possibility that these systems could host an Earth-like planet,” Davoult said.
Leave a Reply