Google has introduced new Earth AI innovations, adding new Imagery and Population foundation models and demonstrations of a geospatial reasoning agent that uses these models to solve complex, multi-step geospatial queries.
The company said its AI models help keep Google products current, including Maps, Search alerts about weather, and alerts about natural disasters. It also said that as individual models grow more powerful, some real-world questions require combining insights across domains, such as imagery, population and the environment.
Google Earth AI was introduced earlier this year to address that challenge. The system pairs a family of foundation models with a geospatial reasoning agent that uses the latest Gemini models. Google said the agent breaks down complex questions into multi-step plans, calls the foundation models, queries vast datastores, uses geospatial tools and then fuses the results into a holistic answer.
Today’s update includes:
- New Imagery and Population foundation models, along with technical details and evaluations showing state-of-the-art performance.
- Demonstrations of the geospatial reasoning agent using these models to solve complex, multi-step geospatial queries.
Google also pointed readers to its technical paper, “Google Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning”, and said developers and enterprises can express interest as access expands.
Source: research.google.
Companies can share verified announcements through Newz9’s international press release submission page.
