Machine Learning Applied to the Oxygen-18 Isotopic Composition, Salinity and Temperature/Potential Temperature in the Mediterranean Sea

This study proposed different techniques to estimate the isotope composition (?18O), salinity and temperature/potential temperature in Mediterranean Sea using five variables: (i–ii) geographic coordinates (Longitude, Latitude), (iii) year, (iv) month (v) depth. Three kinds of models based on artificial neural network (ANN), random forest (RF) support vector machine (SVM) were developed. According results, presents best prediction accuracy for querying phase can be used predict (mean absolute percentage error (MAPE) around 4.98%), (MAPE below 0.20%) 2.44%). These could useful research works that require use past data these variables.