Self-organizing map–derived regimes as a basis for basin-integrated diagnostics of Baltic Sea hydrographic change (1993–2023)

Abstract

Abstract The Baltic Sea has experienced significant hydrographic changes over the past three decades, including long-term warming, increasing salinity, and intensified vertical stratification. While these trends are well established, their internal structure and temporal evolution remain less well understood. In this study, we use Self-Organizing Map, a neural network–based unsupervised classification approach, to assess monthly temperature and salinity profiles from a 1993–2023 physical ocean reanalysis. This approach identifies six distinct hydrographic regimes, representing a progression from colder and fresher to warmer and saltier states, interspersed with transitional phases. The timing of these regimes aligns with known episodes of major inflow from the North Sea and corresponding variations in surface outflow. We further quantify changes in internal heat and salt content, vertical stratification strength, and the relative roles of temperature and salinity in shaping density gradients. Results show that, alongside the long-term strengthening of stratification, salinity remains the primary control on density structure. However, recent regimes exhibit an increasing thermal contribution to the density gradient relative to earlier years. This pattern indicates a system that is still largely haline-controlled but trending toward greater temperature sensitivity, with important implications for the future functioning of the Baltic Sea.