Neural Network Modelling of Temperature and Salinity in the Venice Lagoon

This study applies an artificial neural networks (ANN) to simulate monthly tempera-ture and salinity variations at three stations in the Venice lagoon, which have been se-lected to represent different regimes (marine, riverine and intermediate) in terms of relevance of local processes and exchanges with the open sea. Four key predictors are shown to paly a major role: mean offshore sea level, 2-meter air temperature, precipi-tation for the lagoon water temperature, integrated with offshore surface salinity for the lagoon water salinity. The development of the ANN is based on only 4 years of ob-servations, taken irregularly in time with an approximately monthly frequency. De-spite this, the ANN achieves an accurate reproduction of both variables with large R2 and reasonably small, normalized root-mean-square errors at all stations, except for the salinity at the marine station, where the model presents a spurious variability, which is absent in observations. Sensitivity analysis shows that the 2-meter air tem-perature is the dominant predictor for water temperature while sea-level and sea sur-face salinity are the principal drivers of salinity fluctuations, with precipitation exert-ing a relevant role mainly at the riverine station. The ANN has been used for a set of synthetic climate change analyses considering 1.5, 2 and 3°C global warming levels with respect to preindustrial. It is expected an overall warming of lagoon water with maximum increase in summer (up to 6°C in the 3°C global warming level) resulting in an amplification of the annual cycle amplitude. The expected increases of salinity have a strong gradient across the lagoon, are largest at the riverine station, and (analogously to the changes of temperature) amplify the salinity annual cycle amplitude.