# ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets

arXiv: https://arxiv.org/abs/2111.10009 · HTML: https://mlsanity.com/paper/2111.10009/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 14 references that are in the map.
- First posted on arXiv 19 Nov 2021.

## Builds on (most cited first, 2 of 2)

- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [Exoplanet Validation with Machine Learning: 50 new validated Kepler planets](https://mlsanity.com/paper/2008.10516/) (2020)

## Built on by (most cited first, 17 of 17)

- [Interpretable Machine Learning in Physics: A Review](https://mlsanity.com/paper/2503.23616/) (2025)
- [Data Models for Dataset Drift Controls in Machine Learning With Optical Images](https://mlsanity.com/paper/2211.02578/) (2022)
- [Multiplicity Boost Of Transit Signal Classifiers: Validation of 69 New Exoplanets Using The Multiplicity Boost of ExoMiner](https://mlsanity.com/paper/2305.02470/) (2023)
- [Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI](https://mlsanity.com/paper/2310.09091/) (2023)
- [Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels](https://mlsanity.com/paper/2211.06903/) (2022)
- [Single Transit Detection In Kepler With Machine Learning And Onboard Spacecraft Diagnostics](https://mlsanity.com/paper/2403.03427/) (2024)
- [ExoMiner++: Enhanced Transit Classification and a New Vetting Catalog for 2-Minute TESS Data](https://mlsanity.com/paper/2502.09790/) (2025)
- [Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework](https://mlsanity.com/paper/2311.08080/) (2023)
- [Disentangling CO Chemistry in a Protoplanetary Disk Using Explanatory Machine Learning Techniques](https://mlsanity.com/paper/2312.05254/) (2023)
- [Datacube segmentation via Deep Spectral Clustering](https://mlsanity.com/paper/2401.17695/) (2024)
- [TelescopeML -- I. An End-to-End Python Package for Interpreting Telescope Datasets through Training Machine Learning Models, Generating Statistical Reports, and Visualizing Results](https://mlsanity.com/paper/2407.16917/) (2024)
- [The Clear Sky Corridor: Insights Towards Aerosol Formation in Exoplanets Using An AI-based Survey of Exoplanet Atmospheres](https://mlsanity.com/paper/2410.06804/) (2024)
- [DART-Vetter: A Deep LeARning Tool for automatic triage of exoplanet candidates](https://mlsanity.com/paper/2506.05556/) (2025)
- [Exoplanet Detection Using Machine Learning Models Trained on Synthetic Light Curves](https://mlsanity.com/paper/2507.19520/) (2025)
- [DeepRed: an architecture for redshift estimation](https://mlsanity.com/paper/2602.11281/) (2026)
- [ExoNet: Calibrated Multimodal Deep Learning for TESS Exoplanet Candidate Vetting using Phase-Folded Light Curves, Stellar Parameters, and Multi-Head Attention](https://mlsanity.com/paper/2604.15560/) (2026)
- [Exploring Long-period Architectures: Four New Planet Candidates from Kepler with Periods >342 days](https://mlsanity.com/paper/2608.23425/) (2026)

## Abstract (arXiv)

The kepler and TESS missions have generated over 100,000 potential transit signals that must be processed in order to create a catalog of planet candidates. During the last few years, there has been a growing interest in using machine learning to analyze these data in search of new exoplanets. Different from the existing machine learning works, ExoMiner, the proposed deep learning classifier in this work, mimics how domain experts examine diagnostic tests to vet a transit signal. ExoMiner is a highly accurate, explainable, and robust classifier that 1) allows us to validate 301 new exoplanets from the MAST Kepler Archive and 2) is general enough to be applied across missions such as the on-going TESS mission. We perform an extensive experimental study to verify that ExoMiner is more reliable and accurate than the existing transit signal classifiers in terms of different classification and ranking metrics. For example, for a fixed precision value of 99%, ExoMiner retrieves 93.6% of all exoplanets in the test set (i.e., recall=0.936) while this rate is 76.3% for the best existing classifier. Furthermore, the modular design of ExoMiner favors its explainability. We introduce a simple explainability framework that provides experts with feedback on why ExoMiner classifies a transit signal into a specific class label (e.g., planet candidate or not planet candidate).