Relevant Papers

1. Planetary Candidates Observed by Kepler. VIII. A Fully Automated Catalog with Measured Completeness and Reliability Based on Data Release 25

https://doi.org/10.3847/1538-4365/aab4f9

Talks about many things, but the most important is an algorithm called the Robovetter.

Machine Learning Papers (no longer relevant to my topic)

1. Comparative Analysis of Machine Learning Algorithms for Analyzing NASA Kepler Mission Data

https://doi.org/10.1016/j.procs.2022.08.115.

Tested and compared Logistic Regression, k-Nearest Neighbor, Decision Tree, and Random Forest and analyzed their accuracy and pros and cons.

2. Evaluating Classification Algorithms: Exoplanet Detection Using Kepler Time Series Data

https://arxiv.org/pdf/2402.15874.pdf

Tested and compared Random Forest, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Naive Bayes, and Decision Tree and analyzed their accuracy, as well as identified which is the worst and potential directions for new research.

3. Identifying Exoplanets with Machine Learning Methods: A Preliminary Study 

https://doi.org/10.5121/ijci.2022.110203

Analyzed Classification Tree, Random Forest, Naïve Bayes, and Neural Network and looked at the success rates and potential areas for improvement.

4. Random Forest Algorithm for the Classification of Spectral Data of Astronomical Objects

https://doi.org/10.3390/a16060293

A deep dive into Random Forest, a collection of Decision Trees, and evaluates how well it performs compared to humans and other algorithms.

5. Automated Identification of Transiting Exoplanet Candidates in NASA Transiting Exoplanets Survey Satellite (TESS) Data with Machine Learning Methods

https://doi.org/10.1016/j.newast.2021.101693

Looked at an algorithm being developed by a company and was trained on TESS exoplanet data.

6. A Ubiquitous Unifying Degeneracy in Two-Body Microlensing Systems

https://doi.org/10.1038/s41550-022-01671-6

Talks about many things that are not relevant, but the methods are important for its discussion about Neural Network.

7. Deep Learning Exoplanets Detection by Combining Real and Synthetic Data

https://doi.org/10.1371/journal.pone.0268199

Evaluated Convolutional Neural Networks in comparison to other types of Neural Networks.  

8. Computing Transiting Exoplanet Parameters with 1D Convolutional Neural Networks

https://doi.org/10.3390/axioms13020083

Speaks on Convolutional Neural Networks.

9. Planetary Candidates Observed by Kepler. VIII. A Fully Automated Catalog with Measured Completeness and Reliability Based on Data Release 25

https://doi.org/10.3847/1538-4365/aab4f9

Talks about many things, but the most important is an algorithm called the Robovetter.

10. ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier That Validates 301 New Exoplanets

https://doi.org/10.3847/1538-4357/ac4399

Talks about ExoMiner, a currently widely-used algorithm.