Accurate ocean wave prediction is pivotal for maritime operations, climate modeling, and coastal management. This research introduces an innovative approach employing Long Short-Term Memory (LSTM) neural networks to enhance the precision of predictions. Unlike conventional models that often rely on statistical or physical principles, LSTM networks excel in modeling ocean wave data’s intricate temporal dependencies and nonlinear dynamics. Our methodology involves the collection and rigorous preprocessing of historical ocean wave data, encompassing a comprehensive set of meteorological and oceanographic variables. LSTM neural networks are then deployed to train and validate the predictive model. Preliminary results are highly promising, with the LSTM model achieving exceptional accuracy. For the features we evaluated, the model demonstrated an accuracy of 90.06% for significant wave height (Hs), 86.70% for maximum wave height (Hmax), 95.97% for zero upcrossing wave period (Tz), 99.86% for wave period of maximum energy (Tp), and 98.73% for sea surface temperature. The implications of this research extend far beyond the academic sphere. Improved ocean wave prediction models hold the potential to revolutionize maritime navigation by ensuring safety and efficiency, aiding in disaster preparedness, and contributing to a deeper understanding of climate dynamics. This study represents a significant leap forward in the fields of oceanography and meteorology, harnessing the power of LSTM neural networks to provide accurate and reliable ocean wave predictions that are crucial for the safety and sustainability of maritime activities and coastal ecosystems.