Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
When a hurricane forms or a river swells, the pressing question is not only where the crisis will strike, but also who will be most affected. Latest update from Google’s Earth AI It aims to answer both questions simultaneously.
The company said Thursday that it is expanding its geospatial technology, linking its Gemini AI model with the vast store of weather, population and satellite data it has built over decades of mapping the planet. The result is a system that can connect the dots between physical events and human impact — forecasting not just the storm, but the communities most vulnerable to it.
Read also: Google Earth is 20 years old, and Digital Globe has two new features that will be useful to you
Don’t miss any of our unbiased technical content and lab reviews. Add CNET As Google’s preferred source.
New features of Google Earth AI
At the heart of the update is a feature Google Earth calls geospatial inference. It’s essentially a connected layer that allows AI to “think through” different types of Earth data — weather forecasts, population maps, images — to produce more complete answers.
Rather than simply showing where a hurricane might make landfall, for example, this geospatial logic identifies which neighborhoods are likely to be flooded, how many people live there, and what infrastructure, such as power lines, might fail first. Google says this approach is already helping groups like GiveDirectly, which is using the system to identify households most in need of cash assistance after floods.
Instead of showing where a storm might hit, geospatial inference can identify which neighborhoods are likely to flood, how many people live there, and what infrastructure is at risk.
This is part of a broader trend within Google to use Gemini not just for chatting or programming, but for thinking about the physical world. “To solve a complex problem, you have to see the whole picture,” the company wrote in its press release, and geospatial logic is designed to do just that.
The new capabilities also arrive in Google Earth, where users can now ask questions directly in natural language, typing phrases like “find algae blooms” or “show where rivers have dried up.” Gemini scans satellite images to identify patterns that previously required teams of analysts and custom GIS (geographic information system) scripts.
For example, a city official can collect flood forecasts, compare them to demographic data, and quickly determine which hospitals or power lines are most at risk. What used to take days or weeks of analysis can now happen in minutes.
Read also: Be prepared for natural disasters by preparing a Go Bag
AI models are coming to Google Cloud
For governments, NGOs, and companies with their own data, Google is also bringing core Earth AI models — covering imagery, population, and environmental layers — to Google Cloud. A select group of trusted testers can now mix these models with their own data sets to track everything from vegetation encroachment on power lines to pollution near schools.
Organizations such as the World Health Organization’s Africa Office are already using the system to predict cholera outbreaks in the Democratic Republic of the Congo, while insurance companies and energy companies are testing it to predict damage and prevent power outages.
According to Google Earth, you can now ask questions to find objects or patterns in satellite images, such as “find algae blooms” in order to monitor water supplies.
Disaster forecasting on disaster response
These updates are based on Google’s current crisis toolsincluding flood forecasting that already covers more than two billion people. During the 2025 California wildfires, Google Alerts reached 15 million residents. But with Gemini now integrated into Google Earth AI, the company is trying to move from reactive alerts to proactive prevention, helping responders anticipate what’s coming and who needs help first.
Right now, most of these features are limited to early testers, but Google says it plans to expand access in the coming months. If AI takes off on Earth as promised, it could make global disaster response less concerned with scrambling to catch up and more concerned with staying one step ahead of the storm or natural disaster.
Read also: We are all at risk of natural disasters. This is my plan to protect and restore vital records