✦
Summary
Planetary Prediction Engine is an experimental Google Earth AI system that automates geospatial prediction from natural-language questions. It covers data discovery, preparation, feature construction, model selection, evaluation, and reporting, targeting research questions involving environmental conditions, populations, food security, and regional risk.
Key Features
A natural-language geospatial prediction question defines the analysis objective.
The system searches established geospatial repositories and relevant public web sources.
Data Commons and Google Earth Engine provide structured source data.
AlphaEarth embeddings contribute satellite-imagery semantics to the feature set.
Population Dynamics Foundation Model embeddings represent socio-demographic signals.
A feature gate filters target components, shared-source leakage, downstream effects, and future data.
The workflow searches model families and evaluates predictions automatically.
The system produces predictions with a comprehensive analysis report.
About Planetary Prediction Engine
LLM-orchestrated stages translate a query into geographic constraints, retrieve relevant covariates, and combine them with foundation-model embeddings. A feature gate checks for several forms of target leakage before the system searches predictive model families and evaluates results using the assembled spatial data.
The system is useful as a research example of automating workflows that normally require extensive specialist data engineering. It can draw on Data Commons, Earth Engine, and publicly discoverable sources. The announcement describes an experimental capability, not a generally available standalone service with established pricing.