This project analyzes solar irradiation across Brazil to identify the best location for installing a solar power plant. It combines geospatial data, energy metrics, and visualization techniques to support strategic decision-making.
The goal of this project is to answer a real-world question:
Where is the best location in Brazil to install a solar power plant?
To achieve this, the project:
- Analyzes solar irradiation data
- Maps geographic distribution across Brazil
- Evaluates seasonal variation
- Considers infrastructure constraints (power grid)
- Narrows down optimal regions and cities
- ☀️ Solar irradiation analysis (monthly averages)
- 🗺️ Geospatial mapping using shapefiles
- 📍 Identification of high-potential regions
- 📈 Seasonal trend visualization
- ⚡ Integration with power grid data
- 🌐 Interactive map visualization with Folium
- Python 3
- Pandas – data manipulation
- GeoPandas – geospatial analysis
- Shapely – geometry handling
- Matplotlib – data visualization
- Folium – interactive maps
solar-power-plant/
│
├── brazil-solar-irradiation-per-state.ipynb # Main analysis notebook
├── data/ # (Kaggle datasets - external)
├── shapefiles/ # Geographic data (states, cities)
└── README.md
⚠️ Note: The datasets used in this project are loaded from Kaggle input paths (../input/...), so they are not included in the repository.
The project uses multiple datasets, including:
- Solar irradiation data (monthly averages)
- Brazilian states shapefile
- City-level geographic data
- Power grid transmission lines
These datasets are typically sourced from Kaggle and public GIS repositories.
- Import solar irradiation dataset
- Load shapefiles for Brazil regions
- Convert latitude and longitude into geometry points
- Build a
GeoDataFramefor spatial analysis
- Plot irradiation levels across Brazil
- Identify regions with highest solar potential
- Visualize irradiation trends over months
- Understand variability throughout the year
- Zoom into a high-potential state
- Analyze cities and subregions
- Overlay power grid distribution lines
- Evaluate feasibility of energy transmission
-
Combine:
- Irradiation data
- Cities
- Power grid
-
Generate an interactive map using Folium
git clone https://github.com/gabri-1910/solar-power-plant.git
cd solar-power-plantpip install pandas geopandas shapely matplotlib foliumjupyter notebookOpen:
brazil-solar-irradiation-per-state.ipynb
From the analysis, you can:
-
Identify regions with highest solar irradiation
-
Compare seasonal stability
-
Select cities with:
- High solar potential ☀️
- Proximity to power grid ⚡
- Geographic feasibility 🗺️
- Renewable energy planning
- Government energy policy analysis
- Solar farm site selection
- Academic research in energy & geography
- Data science portfolio project
- 🤖 Add machine learning for energy prediction
- 📡 Integrate real-time weather data
- 🧭 Multi-criteria decision model (cost, terrain, etc.)
- 📊 Dashboard (Streamlit or Power BI)
- 🌎 Expand analysis to all Latin America
- Data sourced externally (not included in repo)
- Analysis depends on dataset quality
- Does not include economic cost modeling
- Infrastructure analysis is simplified
Gabriel da Silva Araújo
- GitHub: https://github.com/gabri-1910
- Location: Pará, Brazil 🇧🇷
This project demonstrates how data analysis + geospatial intelligence can be applied to solve real-world energy problems.
It’s a strong example of:
- Data science applied to sustainability
- Practical use of GeoPandas
- Decision-making with real datasets
Give it a star on GitHub and feel free to contribute!
- Or even a business idea for solar in your region ⚡