Home / Blog / Crowdsourced weather

Crowdsourced weather

Weather forecast image created by a supercomputer leveraging on crowdsourced data. Image credit: IBM

If you can just remember the kind of weather forecast we had 50 years ago (and the various jokes on them, like “we have reached close to 90% accuracy on yesterday’s weather forecast….”) it is surely amazing the increased accuracy we have today.

This is not true everywhere though. Remote and sparsely populated areas are usually getting poorer forecasts and these are updated less frequently.

IBM Weather Company has decided to change this situation by using crowdsourcing and complementary streams of data (like the ones provided by airplanes as they fly) crunched by a supercomputer with the help of AI algorithms.

The company is delivering 26 billion weather forecasts a day, using 162 different weather models to increase accuracy. They cover 2.2 billion locations (that’s quite a bit, isn’t it?) and refresh the forecast every 15 minutes.

The supercomputer is probably the largest IoT platform in the world, processing 400 TB of data every single day.

The AI powers the rendering of data graphs making it easier to interpret the forecast, it can tailor forecast to individual needs (skiing or fishing? No problem different needs are met with different rendering) and can offer red alert for a specific area and a specific business.

Care has been taken to protect the privacy of the data sources (crucial since they are relying also on crowdsourced data)

Better and more focussed weather forecast can be an important asset for business. An ice cream company using IBM Weather forecast saw a 26%  increase in sales thanks to more accurate weather forecast allowing them to customise delivery.

What really amazes me is the huge amount of data that are being used today and the leverage we can have on them. The Digital Transformation is really sweeping the world.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the Industry Advisory Board within the Future Directions Committee and co-chairs the Digital Reality Initiative. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.