How Machine Learning is helping Google to enhance wind prediction

When Google first launched its moonshot “Project Loon” to provide internet connectivity to farthest corners of the world by launching dozens of balloons, the thought process was, as one balloon drifted away, another would be ready to take its place. A continuous stream of balloons was to circumnavigate the world on a daily basis. The project which was unofficially started back in 2011 is now much closer to reality than it ever was, all thanks to – Machine Learning! 

Project Loon – Google

Machine Learning for wind prediction

One of the biggest hurdles for the success of Project Loon was the number of balloons Google would have had to launch if they were to maintain internet connectivity over a particular location. Over time, the team behind Project Loon figured that with updates to their navigation technology, they were able to maximize the time a balloon spend over areas internet connectivity was required.

“We wondered, what if instead of circling the world, we could ride these winds in small enough loops to cluster balloons over a single area? Forget a ring around the world – just hang out!” – Project Loon – Improving Navigation

At 20 Kilometers above the Earth’s surface in the Stratosphere where the Ballons are traveling, the winds are stratified with each layer of wind varying in velocity. Google’s team began using predictive models of the winds and decision-making algorithms to move each balloon up or down into a layer of wind blowing in the right direction, to get the Ballons to go where they wanted them to go. Last summer, they put those updates to the test in Peru, managing to keep the balloons drifting within Peruvian airspace for a total of 98 days!

wind prediction with ML

Wind prediction – Flight Path of the Peru test flight – Google

It’s amazing to see how Google’s engineers were able to use Machine Learning algorithms to predict wind patterns with such accuracy. Many weather researchers would love to get their hands on the data and algorithm. Apparently, the navigation system onboard the balloons were able to predict the wind patterns using relatively small amounts of data using an artificial intelligence technique known as Gaussian Processes. (Related: AI Is About to Learn More Like Humans—with a Little Uncertainty)

For now, most of what machine learning can accomplish takes place in the purely digital realm. But as the Project Loon experiment shows, these systems have the potential to play a role not only online but in the physical world, too. And not just with driverless cars. – Wired

It’s true that Machine Learning has largely been used to analyze phenomena that are purely in the digital realm but perhaps the biggest benefits of using Machine Learning will be in the physical world. It will not be long before Machine Learning algorithms are able to predict the weather better than our current systems, helping us farm better and help feed the 7 billion people that call the Earth their home.

Did you like this article about ML and wind prediction? Read more and subscribe to our monthly newsletter!

Say thanks for this article (0)
The community is supported by:
Become a sponsor
#0.30m #Business #Construction #Drones #Featured
What Construction KPIs Can Be Measured Using Satellite and Drone Data?
Aleks Buczkowski 12.7.2023
#Agriculture #Business #Construction #Data processing #Energy #Environmental Protection #ESG #Financial Services #Geospatial analytics #Geospatial for Good #Government #Health Care #Military #Natural Resources #Real Estate #Transportation
Making Sense of Satellite Imagery: How Can We Process Data at Scale?
Avatar for Barry Morisse
Barry Morisse 05.13.2024
#Featured #Ideas
Have your say in the Earth Observation Survey: What’s the current state of the geospatial industry?
Nikita Marwaha Kraetzig 10.12.2023
Next article

Why the PSLV-C37 launch is a ‘big deal’ for commercial Earth Observation

Rocket launches are always exciting but tomorrow’s PSLV-C37 mission is probably the most exciting mission for someone following the developments in the commercial Earth Observation industry.

The Indian Space Organization (ISRO) will attempt to launch 104 satellites (which is a record in itself) during the PSLV-C37 (Polar Satellite Launch Vehicle) mission, including 88 “dove” nanosatellites belonging to Planet Labs and 8 Lemur-2 nanosatellites for Spire Global. Besides the nanosatellites, ISRO will also be launching Cartosat-2D, an 714kg Indian Earth Observation satellite with panchromatic and multi-spectral sensors on board. Cartosat-2D will have the same features and sensors as the earlier Cartosat-2 series satellites.

PSLV-C37 mission

The list of satellites to be launched during the PSLV-C37 mission. Source: Wikipedia

Planet’s Doves! 

The 88 satellites onboard PSLV-C37 are the largest fleet of satellites to be launched in its history. Planet’s Dove satellites collectively known as “Flock 3p” will be put in a Sun Synchronous Orbit at an altitude of approximately 500km, joining the current 12
“Flock-2p” Dove satellites which are an in a similar orbit. Interestingly, the Flock-2p satellites were also launched by ISRO, earlier last year during the PSLV-C34 mission.

With this launch, Planet will officially have 100 Dove satellites imaging the Earth each day. February is indeed turning out to be an important month for the Earth Observation startup, who just a few days ago announced the acquisition of Terra Bella from Google (Read: Planet Labs acquired Google’s satellite imagery unit – Terra Bella).

With 97 Earth Observation satellites being launched as part of the PSLV-C37 launch, it is an important mission for the Earth Observation industry as a whole.

Did you like this article? Read more and subscribe to our monthly newsletter!

Read on