AI is a wonder created by humans. But can we use it for understanding the unknown facts about the universe? 

The broad reach of AI and ML algorithms is evident in space examinations for navigating, routing the safest route for the spacecraft and more. The amount of data that space agencies receive with the help of AI is beyond imagination.  Recently, Senior Heliophysicist at the National Aeronautics and Space Administration (NASA) Madhulika Guhathakurta said that ML, AI, and Deep Learning techniques could help perform advanced scientific space research and better plan future space missions. She was speaking on ‘Applied AI for Science and Exploration Enabled by Public-Private Partnerships’ organized as part of a workshop on long-term study of solar activity during the 40th meets of the Astronomical Society of India (ASI)- 2022 at IIT Roorkee.   

“AI is becoming a powerful tool for not only making discoveries, but it can also help create and plan future space missions. The models and AI tools have to be readily deployable both onboard space missions and those used for predicting space weather”, said Guhathakurta.  

How does ISRO use AI?  

ISRO is proven to be one of the most elite space organizations. They are nourishing their space missions with AI. ISRO’s research on AI for observational purposes, satellite navigation, meteorology and space assistance started in November 2018. They had published a synopsis to the universities regarding their study. Mentioned following are some of the ISRO initiatives that revolve around AI and ML:  

  • Chandrayaan 2: AI-powered ‘Pragyan’ Rover  

On 22nd July 2019, ISRO launched Chandrayaan 2 spacecraft into the earth’s orbit as part of the second lunar mission. The spacecraft was AI-powered and could communicate only with the lander. However, it includes a piece of motion technology developed by IIT-Kanpur researchers that will help the manoeuvre on the surface of the moon and aid in landing. The algorithm will allow the rover to trace water and other minerals on the lunar surface and send pictures for research and examination.  

  • Multi-Object Tracking Radar (SDSC-SHAR)  

The challenge of building a Space object tracking solution to build successful sustenance of satellites through the difficult terrain of open space with millions of unknown objects that could impact every ISRO sponsored mission. ISRO first developed Target identification using machine learning algorithms from MOTR radar data. Followed by the development of “Real-time JPDA & MHT based data association in dense multi-target tracking environment”. 

  • Image Processing and Pattern Recognition (IIRS)  

ISRO leveraged Artificial Neural networks (ANN) which is the generic name for a large class of machine learning algorithms. Most of them are trained with an algorithm called backpropagation. ISRO’s team used various paths to explore different deep learning algorithms in various applications of earth observation data like; self-learning-based classification, prediction, multi-sensor temporal data in crop/forest species identification, and remote sensing time series data analysis.  

  • Autonomously Navigating Robot for Space Mission (IISU)  

ISRO’s challenge was to build and send unmanned robots to help fetch critical space information in multiple missions throughout the year. They leveraged Artificial Intelligence enabled Path Navigation algorithms to resolve this.  

Apart from the projects mentioned above, ISRO uses AI in Structural health monitoring through classification of strain patterns, respond basket-capacity building program, geospatial technology-based services, earth observation, and forest conservation monitoring system. The organization also offered free courses in Machine Learning and AI for remote sensing data.  

Future of AI in space exploration  

NASA, the space giant that the whole world looks up to for space exploration, also uses AI and ML for their projects. They have been collaborating with tech giants like Google, Intel, and IBM to develop advanced learning algorithms. Also, NASA conducts an 8-week long program called frontier development lab for space innovators.   

According to Madhulika Guhathakurta, public-private partnerships are vital because, more than scientific institutions, industries are capable of investing in the development of AI and ML tools shared with the scientists for testing. The senior NASA scientist added that AI and ML facilitate auto-corrections, track complex structures inside solar winds, and facilitate the replacement of multiple filters fitted on payloads for observations. They are thus capable of contributing to the reduction of mission costs.  

 

Want to publish your content?

Publish an article and share your insights to the world.

Get Published Icon
ALSO EXPLORE