“This is largely a vehicle through which continued growth of the constellation can be supported, as well as some work on research and development to continue to improve the hardware and performance of the balloons,” WindBorne co-founder and CTO Andrey Sushko said.
Sushko said the agreement was awarded without a competitive bidding process because the government determined WindBorne could provide the required global data-collection capability.
The company operates autonomous balloons that gather atmospheric sensor readings and transmit the information for use by customers. WindBorne also feeds those observations into WeatherMesh, its own deep-learning forecasting system.
The startup has previously worked with U.S. government organizations including the National Weather Service, Air Force and Navy. The new agreement gives the Air Force flexibility to purchase additional observations as operational needs change rather than committing the entire contract value immediately.
WindBorne has also been expanding its AI forecasting work. The company released WeatherMesh 6 earlier this summer and says the model produces more accurate forecasts than the traditional system operated by the European Centre for Medium-Range Weather Forecasts.
Unlike conventional forecasting systems that rely on supercomputers to calculate atmospheric behavior through physics-based equations, AI models can learn patterns from large historical weather datasets and produce forecasts more quickly. WindBorne combines that approach with observations gathered directly by its own balloon network.
The company demonstrated another use for that combination in August, when one of its unpowered systems collected data from inside the eye of a typhoon. WindBorne controls the movement of its balloons by changing altitude, releasing air or dropping ballast so they can enter different wind currents.
“That's a pretty novel step, and the two ingredients for that are one, having good wind and weather models, and knowing how to navigate them; and two, having a large enough constellation that you have balloons in the right places,” Sushko said. “It's one of the first times that a deep-learning model was used for actual operational decisions.”
WindBorne raised a $37 million Series B round announced in August to continue expanding the business. Under the Air Force agreement, further orders could provide additional funding for both the balloon fleet and research aimed at improving the systems that operate it.
This analysis is based on reporting from Yahoo Finance courtesy of TechCrunch.
Image courtesy of Windborne Systems.
This article was generated with AI assistance and reviewed for accuracy and quality.
