Google · Google Research
In September, we released a preprint introducing Empirical Research Assistance (ERA) to help scientists generate expert-level empirical
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
★ Tier-1 Source
Since then, Google scientists and their academic collaborators have been developing and using ERA to test its capabilities and explore potential applications.
Key facts
- Atmospheric CO 2 concentration over the Los Angeles area on October 18, 2024, as seen from GOES-East ( left ) and the Orbiting Carbon Observatory-2 ( right )
- Current space-based CO 2 sensors, like NASA’s Orbiting Carbon Observatory-2 (OCO-2) were designed to make high-precision observations, but they only map a tiny fraction of the Earth’s surface
- After training on the sparse observations from OCO-2 and OCO-3, the model was then able to derive estimates of column-averaged CO 2 everywhere and every 10 minutes
- The AI-developed model on the left takes GOES-East weather satellite data and combines it with other information to estimate column-averaged CO 2 concentration every 10 minutes at all locations
Summary
Since introducing Empirical Research Assistance in the fall, Google Research scientists have been using it to address real-world applications in epidemiology, cosmology, atmospheric monitoring, and neuroscience, providing a hint of AI’s transformational capabilities to accelerate scientific discoveries. AI’s capabilities to advance scientific discovery are growing every week, with outcomes that promise not to enable breakthrough discoveries but to transform how science is done. It’s been inspiring to see the excitement of Google research scientists, visiting faculty researchers and academic collaborators as they experiment with ERA. In the preprint, authors used ERA to predict U.S. hospitalizations for COVID-19, showing that it could retrospectively match or outperform existing tools from the Centers for Disease Control and Prevention (CDC) and leading research institutions.