Astronomers from the International Centre of Radio Astronomy Research (ICRAR) have produced the largest and most detailed low-frequency radio image of the Milky Way to date, using data from the Murchison Widefield Array telescope in Western Australia. The new image, assembled from years of survey data and advanced supercomputing, offers unprecedented sensitivity and resolution, allowing scientists to study the structure and evolution of our Galaxy in remarkable detail. It reveals new insights into star formation, supernova remnants, and pulsars, and marks a significant milestone in radio astronomy.

The SETI Institute announced that it will incorporate the new NVIDIA IGX Thor platform to enhance its real-time search for signals from space at the Allen Telescope Array (ATA) in Northern California. The collaboration brings cutting-edge AI technology—built for demanding real-world environments—into radio astronomy for the first time at this scale.

The ATA’s 42 antennas scan the sky for radio signals that may reveal cosmic events or, one day, evidence of intelligent life. Using the NVIDIA IGX Thor platform, the SETI Institute will be able to process and interpret these signals directly at the telescope, dramatically reducing the time it takes to recognize unusual or promising data.

“NVIDIA IGX Thor enables us to run AI inference and GPU-accelerated signal processing workloads closer to the edge,” said Luigi Cruz, Staff Engineer at the SETI Institute. “Its compact form factor and power efficiency makes it an ideal development platform for our next-generation pipeline, which is based on NVIDIA Holoscan.”

A pair of distant cosmic black hole mergers, measured just one month apart in late 2024, is improving how scientists understand the nature and evolution of the most violent deep-space collisions in our universe. Data collected from the mergers also validates, with unprecedented accuracy, fundamental laws of physics that were predicted more than 100 years ago by Albert Einstein and furthers the search for new and still unknown elementary particles with the potential to extract energy from black holes. 

In a new paper published Oct. 28 in The Astrophysical Journal Letters, the international LIGO-Virgo-KAGRA Collaboration reports on the detection of two gravitational wave events in October and November of last year with unusual black hole spins. 

The exploration-exploitation dilemma is a long-standing topic in deep reinforcement learning. In recent research, a noise-driven enhancement for exploration algorithm has proposed for UAV autonomous navigation. This algorithm introduces a differentiated exploration noise control strategy based on the global navigation training hit rate and the specific situations encountered by the UAV in each episode. Furthermore, it designs a noise dual experience replay buffer to amplify the distinct effects of noisy and deterministic experiences. This approach reduces the computational cost associated with excessive exploration and mitigates the problem of the navigation policy converging to a local optimum.