A Comparative Study of Machine Learning Models for Hourly Forecasting of Air Temperature and Relative Humidity

📰 ArXiv cs.AI

Comparing machine learning models for hourly forecasting of air temperature and relative humidity

advanced Published 25 Mar 2026
Action Steps
  1. Collect and preprocess historical climate data
  2. Split data into training and testing sets
  3. Train and evaluate seven machine learning models: XGBoost, Random Forest, SVR, MLP, Decision Tree, LSTM, and CNN-LSTM
  4. Compare model performance using metrics such as mean absolute error and root mean squared error
Who Needs to Know This

Data scientists and researchers on a team can benefit from this study to improve their forecasting models, while urban planners can apply the findings for better management of cities

Key Insight

💡 XGBoost and LSTM models perform well for short-term forecasting of air temperature and relative humidity

Share This
💡 Machine learning models compared for hourly air temperature and humidity forecasting
Read full paper → ← Back to News