WeatherNet aims to develop an advanced machine learning model to predict weather conditions using historical weather data. Leveraging high-resolution data from Meteomatics, we seek to enhance the accuracy and reliability of weather forecasts.
- Collect and preprocess historical weather data from Meteomatics.
- Perform exploratory data analysis (EDA) to uncover patterns and correlations.
- Research and evaluate various machine learning algorithms for weather prediction.
- Develop and validate initial models to identify the most promising approaches.
- Document findings and methodologies for future development phases.
- Data Collection and Preprocessing: Gather and clean data using Python and Pandas.
- Exploratory Data Analysis (EDA): Visualize data using Matplotlib and Seaborn.
- Algorithm Research: Investigate suitable machine learning models including Linear Regression, Random Forests, and LSTM.
- Model Development: Create and evaluate initial models with cross-validation.
- Documentation: Record research findings and methodologies.
- Comprehensive dataset and detailed exploratory data analysis.
- Initial machine learning models developed and evaluated.
- Identification of the most promising algorithms for accurate weather prediction.
- Documentation of research findings to guide further development.
- Yuval Rozner
- Dor Shabat
- Python
- Pandas and NumPy
- Scikit-learn
- TensorFlow/Keras
- Meteomatics API
- Matplotlib and Seaborn
For more information, please contact:
- Yuval: yuvalrozner98@gmail.com
- Dor: dorshabat55@gmail.com