# Putting Earth AI to work: Geospatial agents for our planet's biggest challenges > Source: > Published: 2026-10-14 16:14:00+00:00 October 14, 2026 Shravya Shetty, Distinguished Engineer, and Luke Barrington, Product Director, Google Research In a new technical report, we demonstrate how combining domain-specific foundation models, spatial tools, and upfront planning enables a Geospatial Reasoning agent to carry out complex spatial analysis and planetary prediction that standalone LLMs can’t. Following promising tests with partners, we’re also expanding experimental agent access via Ask Google Earth and an Agent-to-Agent (A2A) service. When we introduced [Google Earth AI](https://research.google/blog/google-earth-ai-unlocking-geospatial-insights-with-foundation-models-and-cross-modal-reasoning/), we shared a suite of geospatial foundation models — spanning remote sensing, weather, flood hydrology, and population dynamics — alongside an initial prototype showing how a Gemini-powered agent could connect those models to answer cross-modal questions. Since then, we have evolved a Geospatial Reasoning agent from an early concept into a much more capable, experimental system built for multi-step, geospatial reasoning across planet-scale data and autonomous training of custom predictive models. Today, we are sharing three updates: General-purpose LLMs and standard coding tools struggle with real-world spatial problems because planetary datasets are massive, with specialized map and satellite formats that require careful multi-step planning to combine accurately. To tackle complex spatial workflows in practice, our agent brings together four key capabilities: The agent connects Gemini to the capabilities of Earth AI’s foundation models — including [WeatherNext](https://deepmind.google/science/weathernext/), [Flood Forecasting](https://sites.research.google/gr/floodforecasting/), the [Population Dynamics Foundation Model (PDFM)](https://research.google/blog/insights-into-population-dynamics-a-foundation-model-for-geospatial-inference/), [AlphaEarth Foundations](https://deepmind.google/blog/alphaearth-foundations-helps-map-our-planet-in-unprecedented-detail/) and [Remote Sensing Foundations](https://research.google/blog/google-earth-ai-unlocking-geospatial-insights-with-foundation-models-and-cross-modal-reasoning/) — alongside information from [Google Maps Platform](https://mapsplatform.google.com/maps-products/) (e.g., place information, routing, air quality, rooftop solar potential), [Google Earth Engine](https://earthengine.google.com/), [Data Commons](https://datacommons.org/) and [Google Dataset Search](https://datasetsearch.research.google.com/). Earth AI capabilities are packaged as modular skills that the agent calls only when a user question needs them. Before running complex operations, the agent builds a step-by-step analytical plan, selects appropriate fallback datasets when local coverage is sparse, and processes large map layers in a dedicated workspace. This approach avoids overwhelming the agent context with massive amounts of spatial data, while preserving accuracy and tracking data attribution. Every response shows the agent’s plan and the data sources used so experts can check assumptions or substitute datasets. Organizations rarely rely on public data alone. Users can now input their own datasets via the Geospatial Reasoning agent API as CSV spreadsheets, custom map boundaries ([GeoJSON](https://en.wikipedia.org/wiki/GeoJSON)), or cloud tables. Users can then ask the agent to join their private locations with Earth AI’s global models and catalogs. Beyond answering complex analytical questions, the agent also powers our recently announced [Planetary Prediction Engine](https://research.google/blog/planetary-prediction-engine-automating-global-models-via-earth-ai/). Given a user’s local outcome data, such as regional disease rates, crop yields, or grid outages, the agent automatically selects relevant population and environmental signals, uses our [Population Dynamics Insights](https://mapsplatform.google.com/resources/blog/from-static-maps-to-geospatial-ai-announcing-population-dynamics-insights/) and the annual [Satellite Embedding dataset](https://developers.google.com/earth-engine/datasets/catalog/GOOGLE_SATELLITE_EMBEDDING_V1_ANNUAL) (Google products built on PDFM and [AlphaEarth Foundations](https://deepmind.google/blog/alphaearth-foundations-helps-map-our-planet-in-unprecedented-detail/), respectively) and trains validated machine learning models for spatial prediction, super-resolution downscaling, and forecasting. In our recent [public health research](https://research.google/blog/earth-ais-planetary-geospatial-foundation-models-for-global-public-health/), combining these population and satellite signals improved predictions of health outcomes by 12% over demographic baselines and enabled mapping at 8X finer spatial resolution. To measure the impact of domain-specific tools and upfront planning on geospatial reasoning, our [technical report](https://arxiv.org/abs/2610.15750) compares four agent configurations across Gemini 3.8 Flash and Gemini 3.1 Pro: (1) a standalone LLM, (2) the LLM with basic [web search](https://ai.google.dev/gemini-api/docs/google-search) and [maps grounding](https://ai.google.dev/gemini-api/docs/maps-grounding) tools, (3) the LLM with Earth AI tools (such as Remote Sensing Foundations and WeatherNext 3) but without upfront planning, and (4) the full Geospatial Reasoning agent which begins every query with a dedicated planning stage that reasons over available capabilities to assess what it can and cannot do and sets out the stages of retrieval and processing needed to reach an answer. The evaluation spans four benchmarks, covering expert-level open-ended analysis, multi-tool orchestration, and community-developed geospatial problems with deterministic answers. [*CBGB*](https://icml.cc/virtual/2025/47905) and [*UnivEARTH*](https://arxiv.org/html/2504.12110v2) are two externally developed benchmarks that test geospatial code generation and question answering respectively. To test agents on challenging tasks that go beyond a single question or use case, we developed two new benchmarks. *GeoExpertQueries* introduces complex, real-world queries with expert-authored golden workflows that capture analysis best practices in domains like crisis resilience, site selection and public health. *GeoKTools* contains templated queries with verifiable answers, each requiring correct selection and use of 1 to 4 distinct geospatial tools. Together, this suite provides substantially broader coverage than prior evaluations of geospatial reasoning systems. To accelerate research and development of geospatial agents, we [release the development splits](https://github.com/google-research/geospatial-reasoning-benchmarks) of both our new benchmarks in full. Two key takeaways stand out from our evaluation: First, domain-specific skills are essential for spatial reasoning. The agent with only basic tools (web search, maps grounding and code execution) struggles on quantitative spatial tasks. Equipping the agent with Earth AI skills drives a significant jump across GeoExpertQueries, GeoKTools, and CBGB. The only exception is UnivEARTH, where even a standalone LLM scores 93.6%, likely because the source NASA articles and answers are available on the public web. Second, upfront planning unlocks open-ended, real-world workflows. While Earth AI skills alone are enough for narrower tasks like those in CBGB and GeoKTools, tackling open-ended problems in GeoExpertQueries requires upfront planning to keep the agent on track across multi-step analyses and prevent it from making unreliable assumptions or taking shortcuts like using web-search instead of spatial tools. The table below shows scores across all four benchmarks using Gemini 3.8 Flash: The technical report also discusses limitations. GeoExpertQueries scores come from an autorater that compares the agent’s performance to expert workflows that define the steps an analysis should take, not the correct final answer. We therefore consider the agent’s output as a strong first draft for experts to review and build on, not a final answer. To evaluate how this research translates to real-world challenges, we gave a small group of partners early access to test the experimental agent on their toughest problems. Across public health, disaster response, and infrastructure planning, below is an overview of how they are putting Earth AI into action: Early testing with these partners helped our evaluation and expansion of the agent’s geospatial skills, driving our recent additions of road-network routing, support for larger user-uploaded datasets, and better discovery of authoritative local data sources. Today, we are expanding access across our Earth AI research capabilities to gather more feedback on these experimental geospatial reasoning capabilities. We are making these available to a limited group of early users: Our Planetary Prediction Engine capabilities are also available for early preview — accessible both through an interactive interface for rapid, plain-language modeling and via the Agent API for custom workflows. To express interest in getting access to these research capabilities, please [complete our interest form](https://forms.gle/Rj8RopdSFekCxfFA9). To be among the first to try out our early stage projects, you can also sign up for our [Early Access Pool](https://sites.research.google/gr/earlyaccess/).