9621 Agnes Crossing, Lake Suzanneview, New Mexico Island 84604-9295.
Researchers at the University of Hawaii are harnessing the power of the world’s largest solar telescope and advanced artificial intelligence to transform our understanding of the Sun. Their
Researchers at the University of Hawaii are harnessing the power of the world’s largest solar telescope and advanced artificial intelligence to transform our understanding of the Sun. Their project aims to quickly analyze large data sets to better predict solar events such as solar storms; this could lead to advances in the accuracy and speed of solar research.
Astronomers and computer scientists at the University of Hawaii Institute for Astronomy (IfA) are conducting groundbreaking research that could revolutionize our understanding of the Sun.
As part of the SPIn4D project, the team is combining advanced solar astronomy with advanced computer science to process data collected by the world’s largest ground-based solar telescope, located atop Haleakala on Maui.
Recently published works Astrophysical JournalNSF focused on developing deep learning models that can quickly analyze the massive data sets produced by the Daniel K. Inouye Solar Telescope. These efforts aim to maximize the telescope’s capabilities, paving the way for significant advances in the speed, accuracy and depth of solar data analysis.
“Major solar storms cause spectacular aurora borealis, but can also pose threats to satellites, radio communications and power grids. “A better understanding of the solar atmosphere, where they are born, is extremely important,” said IfA postdoctoral researcher Kai Yang, who led the study. “We used state-of-the-art simulations to simulate what Inouye would see. “Combining this data with machine learning provides an invaluable opportunity to explore the 3D solar atmosphere in near real time.”
The Inouye Solar Telescope, operated by NSF’s National Solar Observatory (NSO), is the world’s most powerful solar telescope to date and is located atop the 10,000-foot peak of Haleakala, which means “house of the sun” in Maui. The telescope’s instruments are designed to measure the Sun’s magnetic field using polarized light, and the SPIn4D project is specifically designed to use this data available only in the Solar Telescope’s instrument set.
A team of scientists from NSO and the High Altitude Observatory (HAO) is using deep neural networks to predict physical properties of the solar photosphere based on high-resolution observations from the Inouye Solar Telescope. This method promises to significantly speed up the analysis of the huge amounts of data produced by the solar telescope, which can reach tens of terabytes per day.
“Machine learning is very good at quickly approximating expensive calculations. In this case, the model will allow astronomers to visualize the Sun’s atmosphere in real time, rather than waiting hours to achieve the same accuracy,” said co-author Peter, an associate professor of information and computer science at UH Mānoa Sadowski.
The team created a large dataset of simulated observations of the Sun to train AI models. Using more than 10 million computing hours on NSF’s Cheyenne supercomputer, they produced 120 terabytes of data simulating extremely high-resolution observations from the Inouye Solar Telescope.
The team has already released a 13-terabyte subset of its data along with a detailed tutorial. They plan to release fully trained deep learning models as a community tool for analyzing Inouye Solar Telescope observations.
Source: Port Altele
As an experienced journalist and author, Mary has been reporting on the latest news and trends for over 5 years. With a passion for uncovering the stories behind the headlines, Mary has earned a reputation as a trusted voice in the world of journalism. Her writing style is insightful, engaging and thought-provoking, as she takes a deep dive into the most pressing issues of our time.
