Artificial Intelligence has been used to trace the shift in magnetically active patches on the Sun from 1916 to 2007 by scanning 100 years of hand-drawn Sun records from the Kodaikanal Solar Observatory (KoSO). This could give a much longer view of how solar activity changes over time.
For over a hundred years, scientists have tried to understand the Sun’s magnetic activity cycles, which affect sunspots, flares, and eruptions. Disruptions caused by these cycles impact satellites, navigation systems, and power grids on Earth.
Older observations are often incomplete, making long-term studies difficult. The research, led by Dibya Kirti Mishra from the Aryabhatta Research Institute of Observational Sciences (ARIES), shows that hand-drawn records can be analyzed with modern machine learning techniques.
The observatory's collection includes daily suncharts from 1904 to 2022, featuring sunspots, plages, and prominences mapped on a standard grid. Machine learning techniques automated the identification of the Sun’s disk and the tracing of plages through nine solar cycles.