Merge pull request #132 from EhsanGharibNezhad/joss

Joss

publications/joss/paper.md

@@ -57,11 +57,13 @@ of space missions will not be fully accomplished. Different analytical and stati
 Bayesian statistics, and packages have been developed [e.g., @batalha2017pandexo; @batalha2019picaso; @MacDonald2023POSEIDON]
 and are utilized in the context of forward- and retrieval-radiative transfer modeling to interpret these datasets and 
 extract crucial information, such as atmospheric temperature, metallicity, carbon-to-oxygen ratio, and surface gravity 
-[e.g., see @Marley2015; @line2014systematic; @Iyer2023Sphinx]. These atmospheric models rely on the synthetic training 
+[@line2014systematic; @Iyer2023Sphinx; @Marley2015]. These atmospheric models rely on the synthetic training 
 datasets generated by simulating the physics and chemistry of these atmospheres for a wide range of thermal structures 
 and compositions. In addition, different machine learning and deep learning methods have been developed in recent years 
 to perform various tasks, such as confirming the detection of exoplanets [e.g., @Valizadegan2021 by implementing CNN 
-techniques] and brown dwarfs [e.g., @Lueber2023RandomForesr_BDs using Random Forest ensembles].
+techniques] and brown dwarfs [e.g., @Lueber2023RandomForesr_BDs using Random Forest ensembles]. However, to the best of
+our knowledge, this is the first time, deep learning and convolutional neural networks is implemented on brown dwarf 
+atmospheric datasets to predict parameters such as temperature and gravity simultaneously.  
 
 With the continuous observation of these objects and the increasing amount of data coming to Earth each day, there is a 
 critical need for a systematic pipeline to explore the datasets and extract important information from them. This 
@@ -79,15 +81,15 @@ for interpreting observational data captured by telescopes.
 `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 and visualized in Figure \autoref{fig:TelescopeML_modules}:
+outlined below and visualized in following Figure:
 
-    * __StatVisAnalyzer module__: Explore and process the synthetic datasets (or the training examples) and provide functions for statistical analysis.
-    * __DeepBuilder module__: Specify training and target features, normalize/scale datasets, and pass them to the ML training phase.
-    * __DeepTrainer module__: Create an ML model, train the model with the training examples, and utilize hyperparameters.
-    * __Predictor module__: Process the observational datasets and deploy the trained ML model to predict atmospheric parameters such as gravity and temperature.
+- **DeepBuilder module**: Specify training and target features, normalize/scale datasets, and pass them to the ML training phase.
+- **DeepTrainer module**: Create an ML model, train the model with the training examples, and utilize hyperparameters.
+- **Predictor module**: Process the observational datasets and deploy the trained ML model to predict atmospheric parameters such as gravity and temperature.
+- **StatVisAnalyzer module**: Explore and process the synthetic datasets (or the training examples) and provide functions for statistical analysis.
 
 ![TelescopeML main modules to manipulate the training example, build the ML model, train and tune it, and ultimately 
-extract the target features from the observational data.\label{fig:TelescopeML_modules}](TelescopeML_modules.png)
+extract the target features from the observational data.](TelescopeML_modules.pdf){height="600pt"}
 
 
 # Documentation
@@ -98,11 +100,11 @@ extract the target features from the observational data.\label{fig:TelescopeML_m
 documentation is hosted with _Sphinx_ using _ReadtheDocs_ tools and includes several instructions and tutorials 
 as follows: 
 
-    * __Main page__: https://ehsangharibnezhad.github.io/TelescopeML/
-    * __Installation__: https://ehsangharibnezhad.github.io/TelescopeML/installation.html
-    * __Tutorials and examples__: https://ehsangharibnezhad.github.io/TelescopeML/tutorials.html
-    * __The code__: https://ehsangharibnezhad.github.io/TelescopeML/code.html
-    * __ML Concepts__: https://ehsangharibnezhad.github.io/TelescopeML/knowledgebase.html
+- **Main page**: [ehsangharibnezhad.github.io/TelescopeML/](https://ehsangharibnezhad.github.io/TelescopeML/)
+- **Installation**: [ehsangharibnezhad.github.io/TelescopeML/installation.html](https://ehsangharibnezhad.github.io/TelescopeML/installation.html)
+- **Tutorials and examples**: [ehsangharibnezhad.github.io/TelescopeML/tutorials.html](https://ehsangharibnezhad.github.io/TelescopeML/tutorials.html)
+- **The code**: [ehsangharibnezhad.github.io/TelescopeML/code.html](https://ehsangharibnezhad.github.io/TelescopeML/code.html)
+- **ML Concepts**: [ehsangharibnezhad.github.io/TelescopeML/knowledgebase.html](https://ehsangharibnezhad.github.io/TelescopeML/knowledgebase.html)
 
 
 #  Users  and Future Developments
@@ -127,9 +129,8 @@ the package to apply to a wider range of telescope datasets.
 
 
 # Acknowledgements
-Ask the team if they want to acknowledge any grant!!!! 
+Ask the team if they want to add any grant!!!! 
 Ask Natasha for the Grant!!
 Ask Janet for Gopal's summer support from NASA!!
-E. Gharib-Nezhad expresses gratitude to the developers of many open source Python packages used by `TelescopeML`, ...
 
 # References