Recently, severe warm-water episodes have occurred frequently against a background trend of globalocean warming. Sea Surface Temperature anomalies have an impact on the integrity of marineecosystems which is an important part of the Earth’s climate system. The drastic effects of MarineHeatwaves on aquatic life have been on a steady incline in the recent years, damaging aquaticecosystems resulting in enormous loss of marine life. The study of Marine Heatwaves has arisenas a fast-rising topic of inquiry. Operational forecasting and early warning systems that can predictsuch events can help in proactive planning and better mitigation strategies. In this study, the potentialof machine learning models, namely Random Forest and N-BEATS, was evaluated to predict seasurface temperature on a seasonal scale using the NOAA OISST v2 dataset. The predicted sea surfacetemperature data was then used to forecast the occurrence of Marine Heatwaves up to a year inadvance. The proposed models were tested across four historical Marine Heatwave events around theworld. The results showed that the models were able to capture the onset, trend, and extent of theextreme events accurately.