Machine Learning-Based Approach for Predicting Ocean Surface Temperature

Abstract

The sea surface temperature (SST) is an essential parameter for the investigation of sea and ocean ecosystems owing to its interaction with water quality, organisms, and hydrological events including floods and droughts. This is because the SST is a measure of how hot the water is at the surface of the ocean. SST forecasting is the technique for estimating future SST values, based on historical SST data, which is useful for analyzing and tracking changes in hydroclimatic variables. Most earlier studies have used complex neural network-based architectures for SST prediction. These models have low accuracy due to high variance. In this paper, a new approach based on Random Forest (RF) of machine learning has been proposed to predict the surface temperature of the global ocean using hydrographic sea surface parameters. The hydrographic datasets provided by California Cooperative Oceanic Fisheries Investigations (CalCOFI) are used in this research. The results indicated that STheta, Salnty, O2ml_L, O2Sat, and Oxy_µmol/Kg are useful parameters for predicting thermal information accurately. The suggested technique achieves an R2 score of 0.986 while having a Mean Absolute Error of 0.08°C, which is a significant improvement above the performance shown by the previous research.