IMPRINT Sponsored Project Reaps Rewards: Prof. S.K. Das

IMPRINT Sponsored Project Reaps Rewards: Prof. S.K. Das

'What we know is a drop, what we don't know is an ocean.'

All Departments at NIT Rourkela are centres for cutting edge research and high-quality research output is one of the landmarks of the institute. The researchers are toiling hard to make further exploration in the field of Science and technology and at the same time, the Government has left no stone unturned in supporting the science enthusiasts with the various initiatives. IMPRINT is one of the initiatives taken by the Govt. of India for product development.

Prof S.K. Das of the Department of Electronics and Communication Engineering had bagged the grant in this scheme. One of his contributions from the IMPRINT project related to PM2.5 environmental pollution monitoring technique was recently accepted. 

Team Monday Morning interacted with Prof S.K. Das to know more about IMPRINT projects in general and this specific research contribution in particular.

Monday Morning (MM): Throw light in brief about your recently accepted research article. What is the background of the research?

Prof. Santos Kumar Das (SKD):

It is all about PM2.5 forecasting with missing values. It is a research contribution to environmental pollution monitoring.

The above illustration is taken from here.

Due to the rapid development of industrial technology, the global environment has become more polluted. As the deep learning approach is flexible and deep, the research mainly deals with "multidirectional temporal convolutional artificial neural network". The reasons for environmental pollution are analysed using prediction methods and model selections.

MM: How did you bag the IMPRINT sponsorship? Can you share some tips for researchers who want to bag such sponsorships?

Prof. SKD: IMPRINT is a govt. Make in India initiative on product development in line with “ATMA NIRBHARSHILA”. It was proposed in 2016 by Govt. of India, and many of the researchers (including IITs and NITs) all over India had applied to get grants in this scheme. I was one of them, and luckily I got it. Getting such type of project grant depends on the idea and methodologies to develop for societal benefit. It is not related to research publications, but the objective is to develop products that the govt sectors can use, private and Indian citizens.

MM: Throw some light on the nature of such sponsorships. Is it overall funding under which the researcher can do several research works, or does it apply to only one specific research project?

Prof. SKD:

The IMPRINT scheme was for all the sectors. The nature of sponsorship is to focus on product development and start-up initiation in several research domains.

IMPacting Research INnovation and Technology or IMPRINT. IMPRINT is a first-of-its-kind Pan-IIT and IISc joint initiative to develop a New Education Policy and Roadmap for Research to solve major engineering and technology challenges in selected domains needed by the country. It is funding for Healthcare, Information technology, Energy, Sustainable Habitat, Water resources and river systems and many more. (Source)

MM: Please explain how the temporal convolutional neural networks work in PM2.5 forecasting?

Prof. SKD:

It is a well-known technique that is used for the prediction of missing values in pollution data (PM2.5).

The above illustration is taken from here.

Over the past few decades, air pollution has caused serious damage to public health. Therefore, making accurate predictions of PM2.5 is a crucial task. Due to the transportation of air pollutants among areas, the PM2.5 concentration is strongly spatiotemporal correlated. This study proposes a weighted long short-term memory neural network extended model (WLSTME), which addressed how to consider the effect of the density of sites and wind conditions on the spatiotemporal correlation of air pollution concentration. (Source)

MM: What are the common drawbacks in the domain of pm2.5 forecast using artificial neural networks? How can they be overcome in future works?

Prof. SKD:

Every technique has applications. Depending on the requirements, one can be used to enhance prediction accuracy.

Traditional machine learning methods and neural networks with a simple structure were applied in PM2.5 prediction. However, the existing machine learning prediction methods of air quality fail to analyse the reasons for air pollution concentration because most of the prediction methods focus on model selection. Overcoming those in these recent years, deep learning has promoted the development of PM2.5 prediction. More and more complicated deep networks are applied in this field to obtain better fitting results. Furthermore, the method provided novel ideas of interpolation, prognosis, and feature analysis. (Source)

MM: How successful can this pollution forecasting model become in India, according to you?

Prof. SKD:

Pollution forecasting is essential to take health precautions. Based on this, citizens can avoid polluted places.

It aims to be a source of actionable information on air quality and other environmental data for cities in India and perhaps beyond. It aims to provide practical, affordable and scalable insights regarding environmental conditions for decision-makers in India. It empowers governments, businesses and citizens to make plans to minimise exposure to hazardous conditions and mitigate pollution sources. In other words, it is a perfect initiative in disguise to reduce particulate matter concentrations across the country by up to 30%. (Source)

MM: Share with us the moment when your research article was finally accepted.

Prof. SKD:

Yes, it is normal for us and not very exciting. But it does encourage us.

MM: What are your views on the research culture of NIT Rourkela? What are the scopes of improvement?

Prof. SKD:

Research culture at NIT Rourkela is as per the best in India. We are getting all the required facilities. The only thing is students who are the key to our research work, and they need to focus on work. Also, from time to time, the institute has to encourage the researchers positively.

MM: What would be your final message to students?

Prof. SKD:

Work hard and enjoy harder.

Team Monday Morning congratulates Prof. Santos Kumar Das for bagging the IMPRINT sponsorship. Team Monday Morning wishes him and all other researchers all the best for all their future endeavours ahead.

DISCLAIMER: The content, opinions or views expressed on the Monday Morning's website and its social media platforms, including, but not limited to Facebook, Instagram and Twitter pages, are strictly the property of Monday Morning and represent the extensive research and work of the working team of respective academic year of Monday Morning and not those of the institute. The reports and statements published are consolidated from the collected background research and interviews. The institute's official statements can be found in the press releases published by the institute or via an RTI application.

No article or any statements by Monday Morning is to be reproduced, presented or distributed in part or whole without prior permission of the Executive Body of Monday Morning for any purposes, including, but not limited to print and electronic form.


    Leave a comment

    Login to comment.
    Ask a Question Forum