eWEEK content and product recommendations are editorially independent. We may make money when you click on links to our partners. Learn More.
Two recent developments in AI and astrophysics might be crucial to humanity’s quest for finding extraterrestrial life and spacecraft in the vastness of space.
One is the NASA-inspired, AI-powered infrared camera to scan the skies and detect Unidentified Aerial Phenomena (UAP). The other is the new Bern-based machine learning (ML) model to identify Earth-like exoplanets.
AI-equipped eye on the sky
The Harvard-Smithsonian Center for Astrophysics (CfA) and the Galileo Project have introduced an infrared camera equipped with artificial intelligence called Dalek to survey the skies for alien life and spacecraft.
This multisensor Dalek IR camera aligns with specifications outlined in NASA’s 2023 independent study: “Purpose-built future sensors for UAP detection… designed to adjust on millisecond timescales to aid better detection.”
The study suggested the AI camera is a “multi-modal, multi-spectral ground-based observatory to continuously monitor the sky and collect data for UAP studies via a rigorous long-term aerial census of all aerial phenomena, including natural and human-made.”
The Dalek IR camera might help researchers address the problem of the lack of publicly available scientific information on UAP.
According to Avi Loeb, Frank B. Baird Jr. Professor of Science at Harvard University and Head of the Galileo Project, in a statement, “Often U.S. government data is classified, either because it was collected by classified sensors or because it is not fully understood and could potentially be relevant for national security. When in doubt, the data is not released to the public or the scientific community.”
“However, the sky is not classified,” Loeb said. Therefore, anything that can be observed and detected with the AI camera could be shared to the public, which ensures transparency.
The project uses machine learning software to detect and systematically analyze large datasets from three observatories that capture an average of 100,000 objects a month each.
One outlier discovered would mean a scientific breakthrough in the search for extraterrestrial intelligence, an advanced technological civilization that humans can learn from.
New ML model for finding the next Earth
In Europe, researchers from the Swiss University of Bern and the National Centre of Competence in Research (NCCR) PlanetS developed a machine learning model that identifies planetary systems with potentially Earth-like planets.
The team is led by Jeanne Davoult, a postdoctoral researcher at Deutsches Zentrum für Luft- und Raumfahrt (DLR) in Berlin. She studied exoplanets and has developed the ML model at the Space Research and Planetary Sciences Division (WP) of the Physics Institute of the University of Bern.
“Our model is based on an algorithm that I developed and that was trained to recognize and classify planetary systems that harbor Earth-like planets,” said Davoult in a press statement.
When applied to observed planetary systems, Davoult said, “The results are impressive: the algorithm achieves precision values of up to 0.99, which means that 99% of the systems identified by the machine learning model have at least one Earth-like planet.”
Built on the existing Bern Model developed in 2003 and that is constantly updating, the new model can identify the conditions of how the planets were formed. Its algorithm is trained to infer correlations between habitable planets and the properties of their systems.
Promising sign of alien life on planet K2-18b
Meanwhile, 124 light-years away from Earth, an exoplanet called K2-18b orbits a star in the habitable zone, and scientists found evidence of biosignature chemicals present. The detected biosignature chemicals are similar to the chemicals made by life on Earth.
NASA’s James Webb Space Telescope (JWST) spotted the biosignature in the atmosphere of K2-18b, suggesting promising evidence of alien life. The chemicals detected are dimethyl sulfide (DMS) and dimethyl disulfide (DMDS), molecules that are only produced by microbes. No such biosignature in the atmosphere has been detected before on any planets or moons.
JWST researchers wrote in a paper, “Recent JWST transmission spectroscopy of the candidate hycean world K2-18… We report new independent evidence for DMS and/or DMDS in the atmosphere.”
The levels of DMS and DMDS on K2-18b are 10 parts per million by volume, which is much higher than the levels found on Earth at 1 part per billion by volume.
The findings are new evidence of the potential biosphere present on K2-18b, which would be a significant development in the search for extraterrestrial life. The planet is 2.6 times the size of Earth and 8.6 times the mass located in the constellation of Leo. It potentially has an ocean and a hydrogen-rich atmosphere.
Nikku Madhusudhan, a professor of astrophysics at the University of Cambridge, said in a statement: “This is an independent line of evidence, using a different instrument than we did before and a different wavelength range of light, where there is no overlap with the previous observations.”
Bridging the known and the unknown with AI
Automating the processes of space object detection and analysis accelerates the search for Earth-like habitable planets, such as K2-18b, outside our solar system.
A collaboration between the fields of astrophysics and AI would make the quest for extraterrestrial life and spacecraft promising as there will be more Earth-like exoplanets waiting to be discovered.
AI might just be the right tool for bridging the gap between the known and the yet unknown phenomena that lurk in that vast expanse of the universe.