Machine Learning Models for Predicting Sea Surface Temperature Variability and Trends

Sea Surface Temperature (SST) is an important factor in understanding climate systems, weather patterns, and marine environments. Accurate prediction of SST helps in forecasting events like cyclones, monsoons, and climate change impacts. Traditional methods often fail to capture complex and nonlinear patterns present in SST data. In this research, machine learning models such as Linear Regression, Random Forest, Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Long Short-Term Memory (LSTM) are used to predict SST variability and trends. Historical SST datasets from satellite and climate sources are used for training and testing the models. The performance of each model is evaluated using standard metrics like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R² score. The results show that LSTM performs better than other models due to its ability to learn time-based patterns effectively. This study proves that machine learning can significantly improve SST prediction accuracy and can be useful for climate-related applications.