A New AI System Could Help Prevent Water Exploitation in Cities | News from India

NEW DELHI: A team of engineering students has developed an artificial intelligence (AI) system capable of identifying areas prone to water and water exploitation. can help metropolitan cities avoid the tedious congestion caused by monsoon showers.

Researchers, including Aman Bansal and Apoorva Gupta of the Netaji Subhas Institute of New Delhi, combined rainfall, circulation and location data to predict the severity of the exploitation of the rainforest. water in vulnerable areas.

"In many developing countries, including India, the problem of water exploitation persists: in 2016, the roads of Gurgaon were flooded, leading to the streets severely engorged, leaving thousands of people stranded for hours, such incidents are very common, "said Rishab Gupta of NSIT.

"The damage caused by such events led us to find a practical and workable solution," said Gupta, one of the leading authors of the study presented at the 15th international conference of the 39; IEEE (Institute of Electrical and Electronics Engineers). on Smart City in Bangkok last year.

The study was first conducted in Manila, the Philippine capital that has environmental conditions similar to those of Indian cities.

"We first marked Manila areas already established to be prone to water exploitation, based on data obtained from previously conducted surveys" Gupta said.

Areas likely to be exploited were located using past travel time data (the time required to get from one point to another) from cabin service. Uber and altitude data of the region.

The intensity of water exploitation was calculated on the basis of rainfall data and the day of the week, with week-end traffic well below that of the week .

"After analyzing these data across our neural network, we checked the vulnerability of these sites and we even found more defenseless areas against water infiltration," he said. -he declares.

The data was introduced into an artificial intelligence system which consists of a network of neurons that can derive patterns from the information provided to it.

The system was formed by students to reveal a water intensity recording score using an algorithm that could determine the end of the problem in the area.

"Our work can be easily modulated for Delhi because the Uber data for Delhi is available now, I can produce the results in 5-10 days," Gupta said.

"This system can be driven to detect patterns on an hourly basis and for the future, which even Google can not calculate," Gupta said.

Previously, researchers used Internet of Things (IoTs) – a network of small electronic devices installed in different locations to collect data on humidity, traffic, and so on. However, the high cost of these devices made the project economically unsustainable.

"The fact that we can easily access free travel time data at Uber, which is like an open repository of traffic data, has made things simpler and more feasible, and has given practical appeal to the technology".

The system can also be used to locate hilly areas and times in a city, to dynamically determine strategic points for positioning ambulances, calculate the effect of festivals and holidays on traffic, and can also be used in urban planning, he said.