Ocean warming, driven by human-induced greenhouse gas emissions, has accelerated over the past five decades, with Atmospheric Carbon dioxide (ACO2) and Sea Surface Temperatures (SSTs) rising at an alarming rate. This warming, primarily absorbed by the global ocean, disrupts ecosystems, weather patterns, and global carbon cycles. Rising ACO2 and SSTs contribute to the intensification of marine heatwaves, coral bleaching, and the migration of marine species, significantly impacting biodiversity and global fisheries. Moreover, warmer oceans lead to thermal expansion, contributing to rising sea levels and threatening coastal communities. In this study, ACO₂ from the Global Monitoring Laboratory (GML) of the National Oceanic and Atmospheric Administration and SST data from the Indian National Centre for Ocean Information Services (INCOIS) were the datasets adopted and applied on 1D-CNN model to predict warming trends. Additionally, the performance of conventional machine learning algorithms was explored and compared with the 1D-CNN model. It was identified that machine learning approaches offer superior accuracy and adaptability in forecasting ocean warming. Performance metrics such as Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE) for both ACO₂ and SST datasets were evaluated using the 1D-CNN model. The proposed 1D-CNN result demonstrated better prediction compared to the standard machine learning algorithms.