https://github.com/fazej99/u.s-climate-and-temperature-analysis
This project analyzes historical temperature trends in the U.S., explores their economic impacts, predicts future changes using machine learning, visualizes regional anomalies with GIS, and presents findings through a secure and interactive Streamlit dashboard.
https://github.com/fazej99/u.s-climate-and-temperature-analysis
data-analysis data-science data-visualization gis machine-learning streamlit
Last synced: about 1 month ago
JSON representation
This project analyzes historical temperature trends in the U.S., explores their economic impacts, predicts future changes using machine learning, visualizes regional anomalies with GIS, and presents findings through a secure and interactive Streamlit dashboard.
- Host: GitHub
- URL: https://github.com/fazej99/u.s-climate-and-temperature-analysis
- Owner: FazeJ99
- Created: 2025-01-21T11:54:57.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-21T12:10:11.000Z (over 1 year ago)
- Last Synced: 2025-01-21T13:22:33.937Z (over 1 year ago)
- Topics: data-analysis, data-science, data-visualization, gis, machine-learning, streamlit
- Language: Jupyter Notebook
- Homepage:
- Size: 10.6 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# Climate Change Analysis: Temperature Trends in the U.S.
## **Project Overview**
This project examines annual temperature trends in the U.S. over the past century, their impacts on economic sectors, and predicts future trends using machine learning. It integrates GIS mapping for visualization, cryptography for data protection, and an interactive Streamlit application for results.
---
## **Objectives**
- Analyze historical temperature trends in the U.S.
- Assess impacts on key economic sectors.
- Predict temperature trends for the next 7 years.
- Visualize regional temperature changes using GIS.
- Ensure data security through cryptography.
---
## **Key Features**
1. **Data Analysis**: Preprocessed and analyzed historical data to uncover trends.
2. **Machine Learning**: Identified Random Forest as the best-performing model for temperature prediction.
3. **GIS Mapping**: Created a choropleth map for temperature changes in New York State.
4. **Data Protection**: Applied cryptography to secure sensitive data.
5. **Interactive Dashboard**: Built a Streamlit app to present findings and predictions.
---
## **Workflow**
1. Data collection and preprocessing.
2. Exploratory data analysis.
3. Machine learning for predictions.
4. GIS-based visualization.
5. Dashboard development.
---
## **Technologies Used**
- **Python Libraries**: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn, PyCryptodome, Folium, Geopandas
- **Tools**: Streamlit, GIS (Folium, Geopandas)
---
## **How to Run**
1. Clone the repository:
```bash
git clone
cd
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Run the Streamlit app:
```bash
streamlit run app.py
```
---
## **Findings**
- U.S. temperatures have risen significantly over the past century.
- Random Forest provided accurate predictions of warming trends for the next 7 years.
- GIS maps highlighted regional anomalies, particularly in New York State.
---
## **Applications**
- Inform climate policy and action plans.
- Help businesses adapt to climate impacts.
- Guide infrastructure planning to mitigate risks.
---
## **Future Improvements**
- Extend GIS analysis to other U.S. states.
- Incorporate advanced models for better accuracy.
- Expand analysis to other climate variables like precipitation.
---
## **Acknowledgments**
- Data sourced from NOAA and other reliable databases.
- Thanks to open-source libraries and tools for enabling this analysis.