🌏 Geodata Processing using Python and Machine Learning

📚 Overview

This repository contains all the materials, datasets, and Jupyter notebooks from the Geodata Processing using Python and Machine Learning course. The course focuses on leveraging Python libraries and machine learning techniques to process, analyze, and visualize geospatial data.

---

📁 Folder Structure

ML/
├── Tehri/
│   ├── L3-NH44G07-096-049-05Apr19-BAND2.tif
│   ├── L3-NH44G07-096-049-05Apr19-BAND3.tif
│   ├── L3-NH44G07-096-049-05Apr19-BAND4.tif
│   ├── L3-NH44G07-096-049-05Apr19-BAND5.tif
│   ├── L3-NH44G07-096-049-05Apr19.xml
│   ├── policy.txt
│   └── readme.txt
├── vizag_lulc.tif
├── vizag_sample_data.csv
├── Water_Map.tif
├── water_train.csv
├── dlp_lec1.ipynb
├── dlp_lec2.ipynb
├── dlp_lec3.ipynb
├── dlp_lec4.ipynb
├── dlp_lec5.ipynb
├── dlp_lec6.ipynb
├── dlp_lec9_v2.ipynb
└── haridwar.tif

---

📊 Datasets

• Tehri folder: Contains satellite images in .tif format for various bands (BAND2, BAND3, BAND4, BAND5) along with metadata (.xml).
• vizag_lulc.tif: Land use/land cover data for Vizag.
• vizag_sample_data.csv: Sample CSV file containing geospatial data.
• Water_Map.tif: A geospatial map representing water bodies.
• water_train.csv: Training dataset for water body detection.
• haridwar.tif: Satellite data for the Haridwar region.

---

📒 Jupyter Notebooks

• dlp_lec1.ipynb: Introduction to Geospatial Data and Libraries in Python.
• dlp_lec2.ipynb: Working with Raster and Vector Data using rasterio and geopandas.
• dlp_lec3.ipynb: Geospatial Data Visualization with matplotlib, folium, and plotly.
• dlp_lec4.ipynb: Preprocessing Geospatial Data: Resampling, Reprojection, and Clipping.
• dlp_lec5.ipynb: Machine Learning Models for Geospatial Data: Classification and Regression.
• dlp_lec6.ipynb: Supervised Learning for Land Cover Classification.
• dlp_lec9_v2.ipynb: Advanced ML models and Hyperparameter Tuning for Geospatial Analysis.

---

⚙️ Technologies Used

• Python
• Jupyter Notebooks
• Rasterio (for raster data manipulation)
• Geopandas (for vector data processing)
• Matplotlib, Folium, Plotly (for visualization)
• Scikit-learn (for machine learning models)
• Pandas and Numpy (for data manipulation)

---

🚀 How to Use

1. Clone the repository:

   git clone https://github.com/rohanmistry231/Geodata-Processing-using-Python-and-Machine-Learning.git

2. Navigate to the project directory:

   cd Geodata-Processing-using-Python-and-Machine-Learning

3. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

4. Launch Jupyter Notebook:

   jupyter notebook

5. Open any notebook and start experimenting!

---

📧 Contact

For any queries or collaboration opportunities, feel free to reach out:

• LinkedIn: profile
• Email: rohanmistry231@gmail.com

---

⭐ Acknowledgements

Special thanks to ISRO and the course instructors for providing such an insightful learning experience.

---

🌟 Contribute

Contributions are welcome! If you want to improve this repository, feel free to fork it and create a pull request.

---

📌 Note

Make sure to adhere to any data usage policies mentioned in the policy.txt file.

---

Happy Coding! 💻🌍