Researchexominerexoplanetstessopen source
ExoMiner++ Identifies 7,000 TESS Planet Candidates
8.2
NASA Ames researchers released ExoMiner++, an open-source AI model trained on Kepler and TESS data, and in an initial run identified about 7,000 TESS exoplanet candidates, the team reports in the Astronomical Journal. The GitHub-available tool automates transit vetting to prioritize follow-up observations and could be applied to future NASA datasets, including the Nancy Grace Roman Space Telescope.
Key Points
- 1Identifies 7,000 TESS exoplanet candidates from initial ExoMiner++ run trained on Kepler and TESS.
- 2Automates transit classification to prioritize candidates, reducing manual vetting across hundreds of thousands of signals.
- 3Offers open-source GitHub tool that researchers can apply to TESS, Kepler, and future Roman datasets.
Scoring Rationale
Strong open-source model and official publication; scope limited to exoplanet detection rather than broader ML applications.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
