Skip to content

Deep Convolutional Neural Networks and Machine Learning Models for Analyzing Stellar and Exoplanetary Telescope Spectra

License

Notifications You must be signed in to change notification settings

EhsanGharibNezhad/TelescopeML

Repository files navigation

TelescopeML

PyPI - Latest Release DOI

Build Status .github/workflows/draft-pdf.yml pages-build-deployment License: GPL v3 Python Downloads

TelescopeML is a Python package comprising a series of modules, each equipped with specialized machine learning and statistical capabilities for conducting Convolutional Neural Networks (CNN) or Machine Learning (ML) training on datasets captured from the atmospheres of extrasolar planets and brown dwarfs. The tasks executed by the TelescopeML modules are outlined below:

  • DataMaster module: Performs various tasks to process the datasets, including:

    • Preparing inputs and outputs
    • Splitting the dataset into training, validation, and test sets
    • Scaling/normalizing the data
    • Visualizing the data
    • Conducting feature engineering
  • DeepTrainer module: Utilizes different methods/packages such as TensorFlow to:

    • Build Convolutional Neural Networks (CNNs) model using the training examples
    • Utilize tuned hyperparameters
    • Fit/train the ML models
    • Visualize the loss and training history, as well as the trained model's performance
  • Predictor module: Implements the following tasks to predict atmospheric parameters:

    • Processes and predicts the observational datasets
    • Deploys the trained ML/CNNs model to predict atmospheric parameters
    • Visualizes the processed observational dataset and the uncertainty in the predicted results
  • StatVisAnalyzer module: Provides a set of functions to perform the following tasks:

    • Explores and processes the synthetic datasets
    • Performs the chi-square test to evaluate the similarity between two datasets
    • Calculates confidence intervals and standard errors
    • Functions to visualize the datasets, including scatter plots, histograms, boxplots

or simply...

  • Load the trained CNN models
  • Follow the tutorials
  • Predict the stellar/exoplanetary parameters
  • Report the statistical analysis

Documentation

Contributors

All Contributors

Thanks goes to these wonderful people (emoji key):

Ehsan Gharib-Nezhad
Ehsan Gharib-Nezhad

💻 🤔 🚧 📚
Natasha Batalha
Natasha Batalha

🧑‍🏫 🐛 🤔
Hamed Valizadegan
Hamed Valizadegan

🧑‍🏫 🤔
Miguel Martinho
Miguel Martinho

🧑‍🏫 🤔
Mahdi Habibi
Mahdi Habibi

💻 🤔
Gopal Nookula
Gopal Nookula

📚

About

Deep Convolutional Neural Networks and Machine Learning Models for Analyzing Stellar and Exoplanetary Telescope Spectra

Topics

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages