Era: From Nature publication to catalyzing Computational Discovery
Google Research has introduced Empirical Research Assistance (ERA), an AI tool designed to enhance scientific coding and discovery. Published in Nature, ERA aims to streamline the process of testing and refining computational experiments across various scientific disciplines. The tool has already shown promising results in applications such as epidemiological forecasting and environmental modeling.
- ▪ERA is an AI tool developed by Google that helps scientists write and optimize empirical software.
- ▪The tool has been tested on benchmark problems in genomics, public health, and neuroscience, achieving expert-level performance.
- ▪ERA forecasts for respiratory viruses have ranked highly on CDC leaderboards, demonstrating its effectiveness in epidemiological predictions.
Opening excerpt (first ~120 words) tap to expand
Home Blog Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery May 19, 2026Lizzie Dorfman, Product Manager, and Michael Brenner, Research Scientist, Google Research Published today in Nature, Empirical Research Assistance (ERA) is an AI tool for expert-level scientific coding that helped build the Computational Discovery prototype, now available through a trusted tester program in Google Labs. Quick links Nature paper Github code ERA introductory blog post ERA applications blog post Gemini for Science Epidemiology CO2 mapping Snow runoff Solar energy design Cosmology Neuroscience Share Copy link × One of AI’s greatest potential benefits to humanity is increasing the speed and scope of scientific discovery.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Research.
Discussion
0 commentsMore from Research
