SAN FRANCISCO – Weather intelligence startup Tomorrow.io unveiled DeepSky, a satellite constellation designed to refine atmospheric forecasts by gathering large amounts of data needed to feed artificial intelligence models.
DeepSky, an expansive low-Earth orbit constellation, “will be a quantum leap in all dimensions,” Ree Goffer, co-founder and chief strategy officer of Tomorrow.io, told Space News.
The individual satellites in the DeepSky constellation, announced Jan. 20, will be much larger than the six-unit CubeSats inhabiting Tomorrow.io’s initial constellation, Gen1. And the DeepSky satellite will be equipped with “instruments of a completely different capability,” Gopher said. “We’re not sharing yet what these sensors are, but we are saying that our satellites will carry multiple very high-impact, co-located sensors.”
DeepSky news comes on January 12th Announcement Tomorrow.io’s Gen1 group achieved a global revisit rate of 60 minutes for atmospheric observations with its January 11 launch and rapid commissioning of its 10.th and 11th Microwave sounder satellite. Tomorrow.io’s Gen1 group attracted hundreds of government and enterprise customers, including Ford, Uber, BNSF Railway, JetBlue, and the U.S. Air Force.
“When we interact with users ranging from railway operators to civil aviation authorities, agriculture ministries or disaster management authorities, we understand their various problems and gaps that need to be filled,” Gopher said.
“Operational resiliency now depends on treating atmospheric data with the same rigor as any other mission-critical infrastructure,” said Nikhil Ahuja, senior director, planning and supply chain, Amazon. “Advances in sensing and the faster refresh frequency DeepSky enables create a new
Class of AI-powered decision systems that are more adaptive and localized. This development will define the future of the world’s largest scale operation.
data-hungry models
AI promises dramatic improvements in weather forecast accuracy. But models require extensive data.
DeepSky is designed to provide comprehensive, high-resolution data. Tomorrow.io needs to feed a new generation of proprietary weather models. In the past, weather models were often limited by the available computation power and physical understanding of the atmosphere. Now, data is the bottleneck.
According to the news release, “AI systems depend on dense, high-frequency and diverse observations – coverage that today’s satellite infrastructure cannot consistently provide.”
“Modern supply chains can no longer rely on static planning or historical averages,” BNSF Chief Technology Officer Matt Garland said in a statement. “True resiliency comes from continuously understanding operational conditions and translating that intelligence into network-wide decisions. DeepSky represents a meaningful step toward defining a new category of what is possible as agentic AI becomes a critical part of planning
and creating an integrated operational picture.”
The news release said DeepSky will complement existing satellite systems, including geostationary and low-Earth-orbit constellations, that feed public weather models, by offering “improved predictions of rapidly evolving and extreme weather events.”
Without providing details, Tomorrow.io announced that the DeepSky satellites will include “new types of sensors, including capabilities that were historically limited to one-off science missions due to cost and vetting constraints.”
DeepSky aims to address and exceed the baseline observational needs of major government and international customers while remaining adaptable to evolving mission priorities and emerging applications, the news release said.
