Technology

Google to use Machine Learning to predict floods and save lives in India

Google's logo

Google is a company that is making machines to help mankind. There are a lot of things which the company has made till date which are outstandingly helping humans without us even remotely noticing it. The company has a huge experience in the field of Machine Learning and Artificial Intelligence. The inventions and the reinventions are just for the purpose of fulfilling some of the needs our race has.

India has been Google’s favorite market for trying out its new inventions. The company recently launched an app that will help kids learn languages. The target audience for the same were rural areas of India. There are many other initiatives which Google has started in India, it is also educating the journalists over identifying news and fake news. These are some of the initiatives taken up by Google.

Meanwhile, there is another thing the company is doing in India which might actually save lives. It is using Machine Learning (ML) to do the same. The Indian government is also complying with the same. They are giving everything to the American company as this might turn out to be groundbreaking.

Google has decided to set up in Patna, Bihar. The company has narrowed down to Bihar because it is the state which sees most floods in the country. Bihar’s 73% area gets flooded annually and this was reported by the International Water Management Institute (IWMI).

About 20% of deaths occurred due to floods around the world are from India. There is a reason for that and that is poor flood forecasting systems in India. Google’s ML and their methods might just improve the same.

The Indian government is providing Google with stream gauge measurements. These measurements are very important as these are the parameters on which Google will predict the flood-prone areas. Google uses these measurements as inputs to its system and then the system will provide a map which will show the areas that are going to be affected.

It will only be based on the measurements but ML will come into play here. The power of the system to compute the measurements and the data available will play a huge role in this. This is will improve the forecasting accuracy, the lead time and also the entire systems of forecasting in India. Sello Nevo, who is responsible for the project told Livemint about the same.

There was another test that was conducted in the monsoon of 2018. The results were fantastic as over 90% of the predictions were correct. Google even alerted the people within 1000 km around Patna.

“In one of the recent trials conducted in the past monsoon season in September last year, Google was able to provide 90% accuracy in the flood alert with inputs received from the Central Water Commission (CWC). For that event, we sent an alert to people within about 1,000 square kilometers around Patna and the alert had a map that indicated which areas are likely to get flooded or are somewhat likely to get flooded and which areas are not likely to get flooded,” Nevo said.

-Unmesh Phule

Comment here