# Detecting Exoplanet Transits through Machine Learning Techniques with Convolutional Neural Networks

## TL;DR

This paper proposes a 2D convolutional neural network approach for detecting exoplanet transits, demonstrating its effectiveness using Kepler data and comparing various deep learning models.

## Contribution

Introduces a novel 2D CNN method with folding for exoplanet transit detection, showing superior performance over other deep learning models.

## Key findings

- 2D CNN with folding achieves high accuracy
- Method outperforms other models in reliability and completeness
- Effective use of Kepler Data Release 25 light curves

## Abstract

A machine learning technique with two-dimension convolutional neural network is proposed for detecting exoplanet transits. To test this new method, five different types of deep learning models with or without folding are constructed and studied. The light curves of the Kepler Data Release 25 are employed as the input of these models. The accuracy, reliability, and completeness are determined and their performances are compared. These results indicate that a combination of two-dimension convolutional neural network with folding would be an excellent choice for the future transit analysis.