A Comparative Analysis of Artificial Intelligence in Meteorology: Temperature Forecasting in Tripoli as a Case Study

Abstract

This research explores the application of Artificial Intelligence (AI) in predicting short-term temperature variations for the city of Tripoli, Libya. Utilizing a comprehensive historical dataset from the Libyan National Meteorological Center (LNMC) (1943–2014), the study evaluates three distinct models: Random Forest (RF), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM). The experimental results demonstrate that the Random Forest model provided the most accurate predictions with an score of 0.89 and a Mean Absolute Error (MAE) of 1.71°C. These findings establish a reliable data-driven approach for meteorological forecasting in Mediterranean coastal climates.