TelescopeML -- I. An End-to-End Python Package for Interpreting Telescope Datasets through Training Machine Learning Models, Generating Statistical Reports, and Visualizing Results

TL;DR

TelescopeML is a comprehensive Python package that streamlines the analysis of telescope datasets by training machine learning models, generating statistical reports, and visualizing results to aid space exploration research.

Contribution

It introduces an end-to-end Python toolkit for processing, training, and deploying CNN models on astronomical spectral data, enhancing analysis efficiency.

Findings

Effective processing of synthetic and observational datasets

Successful training of CNN models with optimal hyperparameters

Accurate derivation of spectroscopic parameters from real data

Abstract

We are on the verge of a revolutionary era in space exploration, thanks to advancements in telescopes such as the James Webb Space Telescope (\textit{JWST}). High-resolution, high signal-to-noise spectra from exoplanet and brown dwarf atmospheres have been collected over the past few decades, requiring the development of accurate and reliable pipelines and tools for their analysis. Accurately and swiftly determining the spectroscopic parameters from the observational spectra of these objects is crucial for understanding their atmospheric composition and guiding future follow-up observations. \texttt{TelescopeML} is a Python package developed to perform three main tasks: 1. Process the synthetic astronomical datasets for training a CNN model and prepare the observational dataset for later use for prediction; 2. Train a CNN model by implementing the optimal hyperparameters; and 3. Deploy the trained CNN models on the actual observational data to derive the output spectroscopic parameters.