Improving sea level prediction in coastal areas using machine learning techniques
Sarmad Dashti Latif, Mohammad Abdullah Almubaidin, Chua Guang Shen, Michelle Sapitang, Ahmed H Birima, Ali Najah Ahmed, Mohsen Sherif, Ahmed El‐Shafie
Abstract
The objective of the current study is to investigate the effectiveness of specifically the Support Vector Machine (SVM) and the k-Nearest Neighbors (kNN) models for sea level prediction. The SVM and kNN models are compared using the predicted data determined by the machine learning model’s performance. Thirteen models were trained precisely and properly throughout the machine learning process. The results showed that SVM models provide good performance during the training process and attained relatively poor performance during testing process. On the other hand, the KNN model showed consistent performance for both training and testing process. Regarding the effectiveness of different kernels of the SVM algorithm, the Radial Basis Function (RBF) kernel is the most suitable, which provides the finest analysis for the sea level rise dataset and acceptable values for RSME, MAE, and R2.