Introducing the planetary prediction engine: An experimental research capability that automates global geospatial modeling workflows. From predicting public health outcomes to improving food security, we are simplifying planetary-scale analytics. Learn more: https://goo.gle/4cgIFhn
About us
From conducting fundamental research to influencing product development, our research teams have the opportunity to impact technology used by billions of people every day. We aspire to make discoveries that impact everyone, and sharing our research and tools to fuel progress in the field is fundamental to our approach.
- Website
-
https://research.google/
External link for Google Research
- Industry
- Technology, Information and Internet
- Company size
- 1,001-5,000 employees
Updates
-
We are proud to share that Dr. Marian Croak is on TIME's TIME100 AI list of 2026! This honor celebrates her incredible leadership and her legacy as a pioneer in AI. Check out her profile: https://goo.gle/4wWJNOy #TIME100AI
-
-
Introducing GlucoFM, a lightweight, self-supervised continuous glucose monitoring foundation model that separates metabolic baselines from transient spikes, producing transferable representations and setting new performance standards across diverse metabolic prediction tasks, such as diabetes risk assessment, insulin resistance, and post-prandial glycemic response. Learn more →https://goo.gle/4xUFX9q
-
-
Learn about AgentHands, an LLM-powered XR prototype that augments conversational agents with synchronized, expressive hand gestures to provide spatially grounded guidance, bridging the mental mapping gap and enhancing user engagement in physical tasks: https://goo.gle/4xk2BrT
-
How far in advance can you predict a flood? Today, AI models can forecast riverine floods up to 7 days ahead and urban flash floods up to 24 hours in advance. In this first episode of "Ask a Scientist", Senior Staff Research Scientist Deborah Cohen sat down with Chris Sotelo to talk through how our Climate Crisis Resilience team built Flood Hub and Groundsource to bring flood alerts to 2 billion people across 150 countries. We’ve also open-sourced our hydrology modeling framework on GitHub so researchers and meteorological agencies can build on it. Watch below, and read the Q&A on News from Google: https://goo.gle/4hHkpIG
-
Today we present Mobility-Embedded POIs (ME-POIs), a novel mobility-informed framework that improves text-based place representations derived by language models, allowing AI models to understand the aggregate activity rhythms of places over time. More →https://goo.gle/4zOOBZd
-
-
Finding clinical signals in large-scale health sensing data streams is quite challenging. We introduce a biomarker discovery framework that pairs hypothesis generation with adversarial validation to discover rigorous digital biomarkers alongside human experts. Read more: goo.gle/4c6lqXg
-
-
We've launched Operation Blue Skies, in partnership with the UK government and aviation leaders, to continue our work addressing the climate challenge of contrails. Learn more from Yossi Matias, VP, Google & GM, Google Research ⬇️
We are making a major step in our work on mitigating aviation's climate impact with the launch of Operation Blue Skies — the world’s first state-backed trial to avoid contrails at the scale of an entire oceanic airspace. When you look up at a clear sky and see thin white lines trailing behind airplanes, you are looking at condensation trails, or “contrails”. And while they may seem harmless, contrails are responsible for around a third of aviation’s warming impact, as under the right conditions they can grow into large man-made clouds, trapping heat. We use AI to tackle the challenge of contrail avoidance. In early trials, we’ve seen flights using our AI-based forecasts by Google Research achieve a 62% reduction in contrails. More about the new Operation Blue Skies initiative: ✈️ The trial will operate within the Shanwick oceanic airspace (the eastern half of the North Atlantic corridor), which accounts for approximately 5% of global contrail warming, targeting the high-impact winter season between November and February. ✈️ Around 10,000 flights, originating from hundreds of cities, will pass through Shanwick airspace during trial hours each year in the 30 month program, and a small percentage of these flights that would otherwise pass through contrail-sensitive airspace will be slightly deviated, preventing them from forming strongly warming contrails. ✈️ Operation Blue Skies is co-funded by the Department for Transport (DfT), United Kingdom through the Aerospace Technology Institute Programme, with Google contributing pro-bono AI research expertise, engineering time, and high-performance computing infrastructure. ✈️ We’ll use our AI models to predict and avoid warming contrails, while using machine learning applied to satellite imagery to track and verify our impact. ✈️ Bringing together NATS (the UK's leading air navigation service provider), Contrails.org, Imperial College London, the University of Cambridge, and the Met Office Aviation services to handle everything from air traffic control coordination to independent climate verification. This trial builds directly on our foundational studies with airlines and air navigation service providers, moving us toward a validated blueprint for how global airspaces can be managed to drastically reduce aviation's climate impact. Read more about Operation Blue Skies in the announcement blog: https://lnkd.in/dnMDKUen
-
-
Today on the blog, we demonstrate the feasibility of a deep learning approach estimating body composition from smartphone photos, to predict insulin resistance with accuracy comparable to DXA scans in a clinical research setting. Read more →https://goo.gle/3RZstu2
-
-
Today we discuss knowledge profiling, a behavioral framework that measures both encoding and recall, and use it to examine the underlying bottlenecks of factuality in frontier LLMs. Read more →https://goo.gle/4wt4pxE
-
