#earth-observation

#earth-observation

In the 25 years since the first permanent crew docked at the International Space Station, fewer than 300 people have experienced what life is like there, 250 miles above Earth. The rest of us can only imagine it. So, for NASA astronauts like Don Pettit, taking photographs of our planet while aboard the ISS is a way to share the experience with people on the ground.

That's now changing with OlmoEarth, a new open-source, no-code platform that runs powerful AI models trained on millions of Earth observations-from satellites, radar, and environmental sensors, including open data from NASA, NOAA, and the European Space Agency-to analyze and predict planetary changes in real time. It was developed by Ai2, the Allen Institute for AI, a Seattle-based nonprofit research lab founded in 2014 by the late Microsoft co-founder Paul Allen.

Microsoft has made NASA's Harmonized Landsat and Sentinel-2 (HLS) dataset available on Azure via the Windows giant's Planetary Computer platform. It seems an excellent use for all that Azure capacity - petabytes of global environmental data can be accessed through APIs or directly via Azure storage. "This flexible scientific environment allows users to answer questions about the data, and both build applications and use applications on top of the platform," Microsoft said.

GHGSat, an emissions-monitoring company in Montreal, Canada, tracks methane leaks from landfill sites and oil rigs. Earth-imaging firm Planet in San Francisco, California, uses more than 200 satellites to record land and infrastructure for the energy, insurance and maritime sectors. Data-analytics company Spire in San Francisco converts radio signals from navigation satellites into estimates of ocean height and wind speed to support weather forecasts. European aerospace firm Airbus operates radar satellites that can be used to study volcanoes, wetlands and sea ice.

Google DeepMind introduced AlphaEarth Foundations, an artificial intelligence model designed to integrate massive volumes of Earth observation data into a unified digital representation of the planet. The system, described as functioning like a "virtual satellite", can process petabytes of multimodal inputs. The model addresses a long-standing challenge in Earth science: the difficulty of combining data from diverse sources and refresh rates into formats that researchers can use consistently.

ESA's Biomass satellite captures its first images of Earth’s forests, revealing insights into carbon storage crucial for climate change monitoring.