Deep blue artificial intelligence for knowledge discovery of the intermediate ocean

Oceans at a depth ranging from ~100 to ~1000-m (defined as the intermediate water here), though poorly understood compared sea surface, is critical layer of Earth system where many important oceanographic processes take place. Advances in ocean observation and computer technology have allowed science enter era big data (to be precise, for surface layer, small bottom sits between) greatly promoted our understanding near-surface phenomena. During past few decades, however, also undergoing profound changes because global warming, research prediction which are intensive concern. Due lack three-dimensional theories field observations, how remotely sense space becomes very attractive but challenging scientific issue. With rapid development next generation information technology, artificial intelligence (AI) has built new bridge marine (called Deep Blue AI, DBAI), acts powerful weapon extend paradigm modern oceanography metaverse. This review first introduces basic prior knowledge movement m vertical stratification within depths well resources provided by satellite remote sensing, observation, model reanalysis DBAI. Then, three universal DBAI methodologies, namely, associative statistical, physically informed, mathematically driven neural networks, elucidated context sensing. Finally, unique advantages potentials mining discovery demonstrated top-down way “surface-to-interior” via several typical examples physical biological oceanography.