Temperature Prediction: A Comparative Comprehensive Study Between Machine Learning Algorithms

In this study, we address the critical research area of temperature prediction, which holds significant implications for practical fields such as meteorology and agricultural studies. Our approach involves temperature forecasting, using three different machine learning algorithms: Multiple Linear Regression (MLR), Random Forest (RF) and Artificial Neural Network (ANN). We conduct a comparative study using sample experimental weather and temperature data collected from GitHub. The evaluation of experimental results is based on key metrics, including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Correlation Coefficients (CC). Through a thorough examination of these metrics, we find that MLR emerges as a better model for temperature prediction compared to both Artificial Neural Network and Random Forest. The results of our study contribute valuable insights into the effectiveness of these machine learning models in the context of temperature forecasting.