Researchers have used Artificial Intelligence (AI) to analyse more than a century of hand-drawn solar observations from the Kodaikanal Solar Observatory (KoSO), creating one of the longest continuous records of the Sun’s magnetic activity and offering fresh insights into how solar cycles evolve over time.
The study, led by Dibya Kirti Mishra of the Aryabhatta Research Institute of Observational Sciences (ARIES)—an autonomous institute under the Department of Science and Technology (DST)—demonstrates how machine learning can transform historical astronomical records into valuable scientific datasets. The research was carried out in collaboration with the Indian Institute of Space Science and Technology (IIST), Southwest Research Institute, USA, and the Indian Institute of Astrophysics (IIA), and has been published in The Astrophysical Journal.
For over a century, scientists have studied the Sun’s magnetic activity, which follows periodic cycles that influence the occurrence of sunspots, solar flares and eruptions. These phenomena can affect satellites, navigation systems, communication networks and power grids on Earth. However, long-term studies have often been limited by incomplete or inconsistent historical observations.
The researchers addressed this challenge by applying a U-Net-based supervised machine learning model to digitised versions of KoSO’s hand-drawn “suncharts”, which document daily solar observations from 1904 to 2022. These charts include detailed records of sunspots, plages, filaments and prominences.
The AI model first identified the Sun’s disc in each scanned image, accurately determining its centre, size and orientation. It then automatically detected and mapped plages—bright, magnetically active regions on the Sun—across observations spanning 1916 to 2007, covering nine solar cycles.
Using the extracted data, researchers generated a time-latitude “butterfly diagram”, which illustrates how solar magnetic activity migrates across different latitudes during successive solar cycles. The study found that the plage patterns identified from the hand-drawn charts closely matched observations derived from KoSO’s Ca II K solar images, confirming the reliability of the historical records.
According to the Department of Science and Technology, converting these century-old drawings into machine-readable data will help bridge historical observations with modern space-age measurements, enabling scientists to better understand long-term changes in the Sun’s magnetic behaviour.
The study also highlights the potential of artificial intelligence to preserve and analyse historical scientific archives that were previously difficult to use because of variations in drawing styles, ageing paper and inconsistent scan quality.
Researchers say long-term records of solar magnetic activity are essential for improving models of the Sun’s behaviour, reconstructing past solar activity and enhancing understanding of space weather, which can have significant implications for satellite operations, communication systems and critical infrastructure on Earth.
