Boffins use machine-learning tricks to create a starlight dimmer switch
The FLIP framework combines physics-based telescope modeling with machine learning optimization to subtract starlight glare that often hides planets. When tested on James Webb Space Telescope data, it improved sensitivity by up to 15 times and successfully imaged planet 51 Eridani b at a wavelength where previous methods failed.
Key points
- FLIP framework uses ML to subtract starlight from telescope images
- Sensitivity to faint exoplanets increased by 2 to 15 times
- Successfully imaged planet 51 Eridani b at 4.3 micrometers
- The method can be applied to other space and ground-based observatories
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Register did the reporting; read the original for the full story.
Read the full story at The Register
