Science & Technology

AI decodes a century of Kodaikanal Solar Observatory sun records

By TestNeeti Editorial TeamPublished Thursday, 2 July 2026 2 min readSource: GKTodayArticle 17 of 21

Researchers used artificial intelligence to analyse more than a century of hand-drawn solar observations from the Kodaikanal Solar Observatory (KoSO) in Tamil Nadu. The study used digitised solar charts from 1904 to 2022 to build a long, continuous record of solar magnetic activity. It applied a U-Net-based supervised machine learning model to digitised 'suncharts', detecting and mapping plages, the bright magnetically active regions on the Sun, across observations from 1916 to 2007, covering nine full solar cycles. Scientists generated a time-latitude butterfly diagram showing the migration of magnetic activity across latitudes. The research was led by Dibya Kirti Mishra of the Aryabhatta Research Institute of Observational Sciences, an autonomous institute under the Department of Science and Technology, and published in The Astrophysical Journal.

Key Facts & Details

9 points

1
Researchers used artificial intelligence to analyse over a century of hand-drawn solar charts from the Kodaikanal Solar Observatory (KoSO) in Tamil Nadu.
2
The study used digitised solar charts from 1904 to 2022 to build a continuous record of solar magnetic activity.
3
A U-Net-based supervised machine learning model detected and mapped plages across observations from 1916 to 2007, covering nine full solar cycles.
4
Scientists generated a time-latitude butterfly diagram showing the migration of magnetic activity across latitudes.
5
The research was led by Dibya Kirti Mishra of the Aryabhatta Research Institute of Observational Sciences (ARIES), under the Department of Science and Technology.
6
The findings were published in The Astrophysical Journal, a peer-reviewed astronomy journal.

Deep Dive

+
The study also involved the Indian Institute of Space Science and Technology, the Southwest Research Institute (USA) and the Indian Institute of Astrophysics.
+
Plages are bright regions in the Sun's chromosphere associated with strong magnetic fields, while a butterfly diagram tracks latitude-wise movement of solar activity.
+
The solar cycle is an approximately 11-year cycle of changing solar magnetic activity, studied using long archives like KoSO for space-weather research.

Exam Focus

Examiners may ask the location of the Kodaikanal Solar Observatory (Tamil Nadu), the AI model used (U-Net), or what plages and butterfly diagrams represent in solar physics.

Exam Relevance & Angle

The study shows how artificial intelligence can unlock value from historical scientific archives. By reconstructing over a century of solar magnetic activity, it strengthens understanding of the solar cycle and space weather that affects satellites, power grids and communications.

Target Exams

UPSC CSESSC CGLRRB NTPCState PCS

Background & Context

The Kodaikanal Solar Observatory (KoSO) in Tamil Nadu, operated by the Indian Institute of Astrophysics, maintains one of the world's longest continuous solar-observation archives, including daily hand-drawn 'suncharts'. Plages are bright chromospheric regions tied to intense magnetic fields, and the butterfly diagram is a classic solar-physics chart mapping where sunspot and magnetic activity appear over the roughly 11-year solar cycle. U-Net is a convolutional neural network widely used for image segmentation. The Department of Science and Technology is a ministry-level body funding research institutes such as ARIES in Nainital.