Exoplanet detection using machine learning
Problem
Conventional algorithm-based approaches for detecting exoplanets via the transit method needed improvement.
Why it matters
Better transit detection methods expand the ability to discover planets around other stars.
What the AI did
789 features were extracted from each light curve using TSFresh and used to train a LightGBM gradient boosting classifier to detect transit signals.
Results
On K2 campaign 7 data with injected artificial transits, the method was competitive with the box least squares (BLS) method and comparable to state-of-the-art deep learning models (abstract truncated mid-sentence).
Impact
Provides a competitive alternative to BLS and deep learning approaches for exoplanet transit searches.
Record
| Venue | Monthly Notices of the Royal Astronomical Society |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Abhishek Malik, Benjamin P. Moster, Christian Obermeier |
| Citations | 36 (OpenAlex, at import time) |
| References | 2 |
| Model or method | LightGBM gradient boosting with TSFresh features |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1093/mnras/stab3692 |
| Open access | green |
| Keywords | exoplanet detection, transit method, LightGBM, TSFresh, light curves, K2 mission |
Importance rating
real but narrower advance
Improves exoplanet transit detection methods, aiding astronomical discovery; a useful research tooling advance but no stated impact on millions of lives or an entire industry.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Solving the quantum many-body problem with artificial neural networks | 2017 | 2,205 |
7
|
| 3 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 4 | Optimizing Quantum Error Correction Codes with Reinforcement Learning | 2019 | 158 |
7
|
| 5 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|