Representative image.
Bengaluru may soon set a benchmark for air pollution monitoring with a pilot project by the National Institute of Advanced Studies (NIAS) seeking to build a predictive model that leverages historical data to forecast and validate air quality. It will soon be extended to monitor water pollution and electromagnetic radiation among others.
The announcement was made by ISRO Chair professor, NIAS, P G Diwakar at the India Clean Air Summit on Thursday. He said the project supported by the Greater Bangalore Parisara Foundation was presently under evaluation to assess its effectiveness.
Diwakar said the goal was to extend the innovative technology to predict and monitor air quality in the city.
“By integrating diverse data sources through conventional artificial neural network techniques, we’re building a powerful predictive model. This collaborative project led by NIAS emphasises the importance of geospatial data, ensuring comprehensive and impactful solutions for Bengaluru’s air quality challenges,” said Diwakar, according to a press release.
The project will include the acquisition of low-cost sensors for better ground observations that will add value to the high-resolution satellite data.
“Our model will operate within a comprehensive geospatial framework. All data will seamlessly integrate into our meticulously curated geospatial database. As we progress, our focus extends beyond air pollution to encompass broader Sustainable Development Goals (SDGs), addressing issues such as water pollution, electromagnetic radiation, and more,” he said.
He said this holistic initiative reflects NIAS’s commitment to pioneering transformative solutions that transcend conventional boundaries.
Selvi PK, Scientist, Central Pollution Control Board, reiterated the importance of the national clean air programme. Besides the focus on Bengaluru, which has the country’s second highest vehicle population, the CPCP was also focusing on tier-2 cities like Hubballi and Kalaburagi, she added.
The three-day summit was organised by the Center for Study of Science, Technology and Policy.
Technology and approach The project involves integrating historical data to create a predictive model for air quality. Conventional artificial neural network techniques are used to integrate diverse data sources. The model operates within a comprehensive geospatial framework. The project incorporates high-resolution satellite data and low-cost sensors for ground observations.