Our team, ClimaEnergy Lab, is focused on analyzing energy consumption and greenhouse gas (GHG) emissions in relation to environmental changes. We use data from public portals and APIs to predict how climate variations influence energy usage and GHG emissions. Additionally, we visualize the differences between predicted and actual data to improve understanding of these trends.
- Energy Consumption Prediction: Analyze how various climate factors affect energy usage patterns over time.
- GHG Emission Forecasting: Create models to estimate greenhouse gas emissions based on predicted energy consumption and environmental changes.
- Data Visualization: Compare predicted values with actual recorded data and visualize the discrepancies using charts and graphs.
- 한국에너지공단 (Korea Energy Agency): Provides data on energy usage across various sectors in South Korea.
- 온실가스 배출량 (Greenhouse Gas Emissions): Publicly available data on greenhouse gas emissions.
- Weather API: Used to gather real-time and historical climate data, which serves as a key factor in our predictive models.
We use APIs and public data portals to gather the following types of data:
- Energy Usage: Sector-specific energy consumption data from the Korea Energy Agency.
- Greenhouse Gas Emissions: Annual and monthly greenhouse gas emissions data from public sources.
- Weather Data: Data on temperature, humidity, wind patterns, and other environmental factors from the Weather API.
- Data Collection: Automated scripts to gather energy usage, GHG emission, and weather data.
- Data Processing: Clean and preprocess the data to ensure it is ready for analysis and model training.
- Model Development: Use machine learning algorithms to predict energy consumption and GHG emissions based on weather data.
- Visualization: Create interactive charts and graphs to compare predicted values with actual data, helping to highlight discrepancies.
- Python: For data collection, preprocessing, and model training.
- Pandas: For data manipulation and analysis.
- Matplotlib/Seaborn: For data visualization.
- PyTorch/Scikit-learn: For building predictive models.
- APIs: For gathering real-time data (Weather API, public portals).
