Published June 10, 2024 | Version 0.0.5
Software Open

EhsanGharibNezhad/TelescopeML: Release 0.0.5

Creators

  • 1. NASA Ames Research Center

Contributors

  • 1. NASA Ames Research Center
  • 2. ROR icon Helmholtz-Zentrum Dresden-Rossendorf
  • 3. ROR icon University of California, Riverside

Description

Summary

We are on the verge of a revolutionary era in space exploration, thanks to advancements in telescopes such as the James Webb Space Telescope (*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. `TelescopeML` is a Python package developed to perform three main tasks:
  •  Process the synthetic astronomical datasets for training a CNN model and prepare the observational dataset for later use for prediction; 
  • Train a CNN model by implementing the optimal hyperparameters; and 
  • Deploy the trained CNN models on the actual observational data to derive the output spectroscopic parameters

Documentation

 

 

Files

TelescopeML-main-v005.zip

Files (6.8 MB)

Name Size Download all
md5:d122feef3595ccc4f7e31d111692bf2c
6.8 MB Preview Download

Additional details

Additional titles

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

Dates

Accepted
2024-06-10
Accepted to JOSS

Software

Repository URL
https://github.com/EhsanGharibNezhad/TelescopeML
Programming language
Python
Development Status
Active