Tomorrow.io, the world's leading Resilience Platform, announced DeepSky, the world's first AI-native, space-based atmospheric and oceanic sensing network, designed to make Earth's atmosphere and oceans continuously observable in real time, powering faster, smarter global decision-making and response. This will be Tomorrow.io's second constellation, announced just one week after completing the full deployment of its first constellation equipped with Ka-band radar and microwave sounders.

As the global weather enterprise looks toward the next decade, DeepSky positions Tomorrow.io at the forefront of a new generation of weather infrastructure–one that is AI-native, operationally resilient, and commercially scalable by design. Artificial intelligence is transforming weather forecasting, driving major gains in accuracy, speed, and efficiency. Yet as models advance, forecast performance is increasingly constrained not by algorithms or computing power, but by the global observing system itself. AI systems depend on dense, high-frequency, and diverse observations—coverage that today's satellite infrastructure cannot consistently provide.

DeepSky is built to close this gap. It represents a new class of commercial weather infrastructure, purpose-designed to deliver the temporal density and observational diversity required by modern forecasting systems. DeepSky is a proliferated Low Earth Orbit (pLEO) constellation of highly capable satellites, each hosting multiple high-impact, proprietary instruments. Operating at scale, the constellation delivers dramatically higher revisit rates than traditional systems, enabling faster refresh cycles for global and regional models and improved prediction of rapidly evolving and extreme weather events. DeepSky is designed to complement existing government GEO and LEO assets, not replace them—extending their value through higher cadence and new sensing modalities.

Key design principles include:

• Multi-modal sensing on every satellite, spanning much of the usable electromagnetic spectrum for atmospheric and ocean observation
• High-revisit global coverage, significantly increasing temporal density alongside existing GEO and LEO systems
• New classes of sensors, previously limited to bespoke science missions due to cost or revisit constraints

By combining scale with capability, DeepSky enables observation cadences that were previously impractical, while materially lowering cost-per-scan and cost-per-impact. DeepSky is designed to support the full spectrum of operational weather users, including civilian meteorological agencies, severe weather and hurricane forecasting centres, defence and national security organisations, and international partners.

"Operational resilience now depends on treating atmospheric data with the same rigour as any other mission-critical infrastructure," said Nikhil Ahuja, Senior Director, Planning and Supply Chain at Amazon. "The advancement in sensing and rapid refresh frequency DeepSky enables creates a new class of AI-driven decision systems that are more adaptive and localised. This evolution will define the future of the world's largest-scale operations." The constellation is intended to address and significantly exceed the baseline observational requirements of major government and international customers, while remaining adaptable to evolving mission priorities and emerging applications.

By delivering frequent, diverse, and globally consistent observations, DeepSky enables:

• Faster refresh cycles for global and regional models
• Improved prediction of rapidly evolving and extreme weather events
• New AI-native applications that are not feasible with today's observation density

"Modern supply chains can no longer rely on static planning or historical averages. True resilience comes from continuously sensing operating conditions and translating that intelligence into network-wide decisions," said Matt Garland, CTO at BNSF. "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 a unified operational picture."

The constellation builds on Tomorrow.io's proven experience designing, launching, and operating commercial weather satellites and delivering operational data to customers worldwide. Development is underway with a clear path to deployment and scale. DeepSky will be introduced in phases, with additional details shared as the program progresses.

Click here to learn more about Command and Data Handling Systems on SATNow