Space Explorers - Rural Electrification Impact Analysis

Team Members:

• Vaibhav Pawar
• Atharva Gulkotwar
• Tanya Nijhawan
• Parva Sheta

College/University:

Vellore Institute of Technology

---

Problem Statement:

Nighttime light data is a powerful tool for studying city growth, economic activities, and environmental changes. The team aims to utilize this data to understand how rural electrification impacts education, agriculture, and overall economic conditions. By correlating NTL data with socio-economic factors from 2018 to 2022, the team intends to create a formula showing each state's contribution to the country's economic growth.

---

Approach:

1. Comprehensive Data Analysis:

   • Extensively analyzed diverse datasets, correlating Nighttime Light (NTL) data with socio-economic factors from 2018 to 2022.

2. Innovative Prediction Model:

   • Implemented an advanced model addressing data scarcity by estimating key socio-economic characteristics based on insights from prior years' datasets.

3. Strategic Feature Selection:

   • Incorporated significant columns in predicted datasets by district/state, enhancing interpretability.

4. Dynamic Shaded Maps:

   • Utilized color-coded maps for each dataset, dynamically representing the association between NTL data and socio-economic parameters.

5. Insightful Graphs by Region:

   • Employed engaging graph visualizations depicting the region's dynamics over time.

---

Key Features:

1. Dynamic Visualizations:

   • Utilized Plotly tools for interactive, dynamic data exploration.

2. Explainability:

   • Provided transparent explanations on socio-economic factors and NTL data impact.

3. Scalability:

   • Ensured adaptability across regions for versatility with diverse datasets.

4. Real-world Impact:

   • Discussed practical implications for decision-making and regional development.

5. Collaborative Approach:

   • Integrated external datasets for richer insights and real-world relevance.

---

Programming Languages:

• Python: For Data analysis, Machine Learning, and Deep Learning.
• R: For Data Visualization and 3D maps plotting.

Libraries and Packages:

• Pandas, NumPy: For data manipulation, analysis, and numerical operations.
• Sci-kit Learn: For implementing machine learning models and feature selection techniques.
• Matplotlib, Seaborn, Plotly: For plotting and creating dynamic and interactive visualizations.
• Geopandas, Folium: For working with geospatial data and creating maps.
• TensorFlow: For implementing deep learning models.

Tools and Technologies:

• Jupyter Notebook or Jupyter Lab: For interactive development and presentation.
• GIS Tools: For advanced mapping and spatial analysis.
• GitHub: For version control and collaboration.

---

References/Acknowledgement:

• RBI Document on Rural Electrification
• Bhuvan Panchayat
• GIS Vacancy
• NITI Aayog Data Portal

---

For Further Details:

Please refer to the detailed documentation in the repository.