A team of astronomers from the European Space Agency (ESA) has made an exciting discovery of over 800 previously unidentified "astrophysical anomalies" hidden within the archives of the Hubble Space Telescope. Researchers David O'Ryan and Pablo Gómez utilized an AI model to meticulously analyze Hubble's extensive 35-year dataset, searching for unusual objects and marking them for further examination. O'Ryan described the dataset as "a treasure trove of data in which astrophysical anomalies might be found."
Exploring space presents significant challenges due to its vastness, the complexity of data, and the overwhelming volume generated by instruments like Hubble. The introduction of AI proves beneficial in this context, as it excels at processing large datasets to identify patterns and anomalies that may escape human observation.
The AI model, named AnomalyMatch, examined nearly 100 million images from the Hubble Legacy Archive, marking the first systematic search for anomalies within this dataset. It identified uniquely shaped galaxies, light distorted by massive objects, and planet-forming discs viewed edge-on. Remarkably, AnomalyMatch completed its analysis in just two and a half days, a task that would have taken human researchers significantly longer.
The results, published in the journal Astronomy & Astrophysics, revealed nearly 1,400 distinct "anomalous objects," predominantly involving merging or interacting galaxies. Other interesting findings included gravitational lenses, jellyfish galaxies with trailing gas "tentacles," and galaxies featuring large star clusters. ESA noted that some objects defied classification entirely, showcasing the vast potential for discovery.
Gómez praised the application of AI in maximizing the scientific value of Hubble's archive, stating, "Finding so many anomalous objects in Hubble data, where you might expect many to have already been found, is a great result. It also demonstrates the utility of this tool for analyzing other large datasets."