AI Restores Century-Old Solar Drawings to Study Space Weather
Indian astronomers have employed artificial intelligence (AI) to trace shifts in magnetically active patches on the sun from 1916 to 2007 by scanning hand-drawn sun records spanning over 100 years from the Kodaikanal Solar Observatory (KSO). This breakthrough enables a better understanding of long-term space weather risks that can affect technology on Earth, according to the Ministry of Science and Technology.
Why Historical Solar Records Matter
Long-term, consistent records of the sun’s magnetic activity are crucial because they allow scientists to compare how different solar cycles vary in strength and structure. They also improve reconstructions of how the sun’s energy output and magnetic influence have changed over time. For more than a century, scientists have sought to understand the rhythmic rise and fall of the sun’s magnetic activity. These cycles influence sunspots, flares, and eruptions that can disrupt satellites, navigation systems, and power grids on Earth. However, older observations are often incomplete and inconsistent, making long-term study difficult. That is why historical records are extremely valuable, the Ministry said.
Study Published in The Astrophysical Journal
The new study, undertaken by researchers from the Aryabhatta Research Institute of Observational Sciences (ARIES) along with collaborators from the Indian Institute of Space Science and Technology, Thiruvananthapuram; Southwest Research Institute, USA; and Indian Institute of Astrophysics, Bangalore, has been published in The Astrophysical Journal. The work, led by Dibya Kirti Mishra, demonstrates that 100 years of hand-drawn sun records from KSO can be transformed into usable data using modern machine learning techniques. The observatory holds a unique collection of observations, including daily 'suncharts' from 1904 to 2022, where features such as sunspots, plages, filaments, and prominences were carefully drawn on a standard grid.
Challenges with Hand-Drawn Archives
Before digital tools, scientists relied on careful drawings to record their observations. KSO's suncharts are valuable because they capture solar activity over many cycles and include various features marked in specific ways. However, differences in drawing styles, paper aging, and scan quality make it difficult to create a clean and consistent dataset using traditional methods.
Machine Learning Solution: U-Net Model
To address the problem of messy, hand-drawn historical records, the research team used a supervised machine learning approach called U-Net in two main steps. First, the model automatically located the sun's disk in each scanned drawing, pinpointing the center, size, and tilt so that every feature could be placed in the correct location on the sun. Next, it identified and traced magnetically active patches on the sun across drawings covering nine solar cycles from 1916 to 2007. This is important because such patches, called plages, are a reliable 'fingerprint' of the sun's magnetism. Extracting them from old archives helps scientists connect today's space-age measurements with what the sun was doing decades earlier.
Butterfly Diagram and Validation
By turning drawings into machine-readable data, the researchers were able to track how plage activity shifts over time, creating a 'butterfly diagram' that illustrates the solar cycle, the study said. They also found that the plage areas from these drawings match well with those derived from KSO's full-disk observations, proving that the sun charts can help fill gaps and improve long-term solar data.
