New AI Algorithm Found Over 20,000 Asteroids New AI Algorithm Found Over 20,000 Asteroids
A new AI-powered algorithm has enhanced our ability to detect asteroids, uncovering more than 27,000 previously unnoticed space rocks within existing... New AI Algorithm Found Over 20,000 Asteroids

A new AI-powered algorithm has enhanced our ability to detect asteroids, uncovering more than 27,000 previously unnoticed space rocks within existing telescope images. According to Space.com, it was announced by the scientists behind the algorithm.

This new algorithm and the research now mark a significant advancement in the global capacity to track millions of asteroids, including those that could potentially pose a threat to Earth.

In-Person and Virtual Conference

September 5th to 6th, 2024 – London

Featuring 200 hours of content, 90 thought leaders and experts, and 40+ workshops and training sessions, Europe 2024 will keep you up-to-date with the latest topics and tools in everything from machine learning to generative AI and more.


In the past, astronomers have relied on repeatedly scanning specific sections of the sky using telescopes, capturing images several times each night. Scientists can identify moving asteroids by observing the specks of light that shift position against the static backdrop of stars, planets, and galaxies. Once spotted, these objects’ orbits are meticulously calculated and monitored.

The thing is, this manual and repetitive process is now being transformed by artificial intelligence. “This is really a job for AI,” stated Ed Lu, executive director of the Asteroid Institute and co-founder of the B612 Foundation, emphasizing the efficiency of AI in these searches.

The AI tool in question, developed by Lu’s team, is called Tracklet-less Heliocentric Orbit Recovery (THOR). It analyzes over 400,000 archival sky images stored by the National Optical-Infrared Astronomy Research Laboratory (NOIRLab).

THOR’s approach is innovative: it does not require direct telescope operation but instead analyzes vast amounts of data to connect points of light across different images, determining whether they represent the same asteroid.

This method has proven highly effective, as demonstrated by THOR’s recent discovery of 150 near-Earth asteroids in just five weeks—none of which, thankfully, are on a collision course with our planet.

The algorithm’s efficiency stems from its design, which enables it to handle up to 1.7 billion light dots in a single image, provided there are about five observations of the same area of the sky within 30 days. This capability has been crucial in scaling up the search for asteroids, leveraging the computational power and data storage services of Google Cloud to test thousands of asteroid orbits.

We don’t own a telescope, we don’t operate a telescope,” Lu remarked during a recent discussion, highlighting the data-centric approach of his team. “We’re doing this from a data science perspective.”

The impact of AI on asteroid detection extends beyond THOR. Other AI tools and efforts are also advancing the field. For instance, citizen scientists recently trained an algorithm using Hubble Space Telescope images, leading to the discovery of 1,000 new asteroids.

In-Person & Virtual Data Science Conference

October 29th-31st, 2024 – Burlingame, CA

Join us for 300+ hours of expert-led content, featuring hands-on, immersive training sessions, workshops, tutorials, and talks on cutting-edge AI tools and techniques, including our first-ever track devoted to AI Robotics!


Additionally, a software named HelioLinc3D, designed for tracking near-Earth asteroids, identified a 600-foot-wide asteroid last July, which is expected to come closer to Earth than the moon. These advancements are setting the stage for the Vera C. Rubin Observatory in Chile, which is equipped to start operations next year.

The observatory’s 8.4-meter telescope will scan the southern sky nightly over the next decade, supported by AI-driven software like THOR and HelioLinc3D. It is expected to discover approximately 2.4 million asteroids in just the first six months of its operation, potentially doubling the current catalog of known asteroids.

This AI-driven revolution in astronomy not only enhances our understanding of the cosmos but also bolsters our planetary defense, preparing us to better identify and potentially deflect hazardous asteroids long before they pose a real threat to humanity.



ODSC gathers the attendees, presenters, and companies that are shaping the present and future of data science and AI. ODSC hosts one of the largest gatherings of professional data scientists with major conferences in USA, Europe, and Asia.