IBM’s weather forecast system to tap users’ phones for data

IBM GRAF can generate forecasts at a resolution of 3km, significantly higher than IMD’s 12 km models.

Published - December 13, 2019 02:33 am IST - NEW DELHI

Weathering the storm:  People walking towards a shelter during Cyclone Titli in Odisha in 2018.

Weathering the storm: People walking towards a shelter during Cyclone Titli in Odisha in 2018.

International technology company IBM plans to make a high-resolution weather forecast model that will also rely on user-generated data to improve the accuracy of forecasts available in India.

IBM GRAF, as the forecast system is called, can generate forecasts at a resolution of 3 kilometres. This is a significantly higher resolution than the 12-kilometre models used by the India Meteorological Department to generate forecasts.

These weather forecast techniques rely on dynamic modelling and collect a trove of atmospheric and ocean data, crunch it in supercomputers and generate forecasts over desired time-frames — three days, weekly or fortnightly. “From the tests we’ve done so far, our forecasts are 30% more accurate than those generated by 12-km resolution models,” Cameron Clayton, general manager, IBM Watson Media and Weather, said at a press conference here on Thursday.

For its forecasts, IBM relies on a global network of sensors — automatic weather station, data bouys and barometric pressure data from cellphones of users who’ve downloaded the application. “Nearly 12 trillion pieces of forecast information are issued a day,” said Mr. Clayton. Weather forecasts will be available to individuals for free download and can be used by farmers. The forecast engine will also be used to provide custom forecasts for energy companies, consumer brands, insurance businesses and satellite imagery analysts.

A study by IBM found that 72% Indians believed that the local economy had been disrupted by a severe weather event in the past year and 89% were concerned that climate change could negatively impact the economy.

An independent researcher said that, on its own, a three kilometre resolution didn’t automatically improve accuracy. “It’s the equations used to capture the relationship between atmospheric variables that play a crucial role in the accuracy of a forecast,” said Roxy Mathew Koll, a climate scientist at the Indian Institute of Tropical Meteorology. “A combination of observations, computing and equations underlies forecasts. Moreover forecasting tropical conditions over India is particularly tricky.”

0 / 0
Sign in to unlock member-only benefits!
  • Access 10 free stories every month
  • Save stories to read later
  • Access to comment on every story
  • Sign-up/manage your newsletter subscriptions with a single click
  • Get notified by email for early access to discounts & offers on our products
Sign in


Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.