Artificial Intelligence (AI) has been able to help in facilitating the functioning of many sectors. It has been considered as a vital tool in order to decipher information or to assist in functions deemed to be impossible for humans. The AI technique has been proved to an excellent alternative for many such functions.
Video Credits: Stanford Woods Institute for the Environment, YouTube
Artificial Intelligence (AI) is now being used by the environmentalists in order to empower environment regulator. According to a new study which is led by the Stanford University environmentalists may soon be able to use the functions of Artificial Intelligence (AI) in order to keep a track of violators any time anywhere.
According to a paper published in the ‘Proceedings of the National Academy of Sciences’ (PNAS) in the week of April 19 demonstrates how Artificial Intelligence combined with satellite imagery can prove to be a low cost and scalable option in order to keep an eye on the industries which are otherwise considered as the hard to regulate ones.
Across the southern part of Asia brick making has served as the key to development for many countries. This is especially true for the regions which are lacking in other construction materials. This also serves as a source of employment as the kilns that manufacture the bricks provide employment to millions of people in these region.
As per Nina Brooks the co lead author a postdoctoral associate at the University of Minnesota’s Institute for Social Research and Data Innovation who did the research while a Ph.D. student at Stanford.”Brick kilns have proliferated across Bangladesh to supply the growing economy with construction materials, which makes it really hard for regulators to keep up with new kilns that are constructed.”
There have been researches done previously which use the combination of Artificial Intelligence (AI) and satellite observation. But such reaserches have been focused mainly on developed countries which can provide dependable data on locations and functionings.
Brooks, Ruby and other researchers from the Stanford University have been working in Bangladesh since 2016. With the help of infrared they have been able to develop an approach to detect coal burning kilns which were located in remotely sensed areas. This approach was very helpful but had a major flaw, it was not able to differentiate between the coal burning kilns and heat trapping agricultural areas.
Along with the computer scientists and engineers at the Stanford University as well as scientists from the International Centre for Diarrhea Disease Research, Bangladesh the team started to employ machine learning. They were then able to develop a highly accurate algorithm which was able to locate kilns in the images but would also learn to localize kilns in the image.
This was achieved with the help of past applications of deep learning to environmental monitoring. Some specific efforts were made to use deep learning to identify such brick kilns. The system is also capable to identify and distinguish based on shape classification.
Jihyeon Lee, the co lead author and a researcher at the Stanford’s Sustainability and Artificial Intelligence Lab said, “We are hopeful our general approach can enable more effective regulation and policies to achieve better health and environmental outcomes in the future.”
For further developments, the researchers are working on developing ways to use lower resolution imagery and are planning on expanding their work to other areas where bricks are constructed similarly.