PREDIKSI SALINITAS AIR LAUT DENGAN DEEP NEURAL NETWORK

Research in the marine field is important to look at the state of the ocean's atmosphere and the biodiversity that can live in it. Based on the CalCOFI data set, seawater salinity correlates with the depth of the sea. Sea water salinity can be predicted based on its depth. The classic method that is often used is the least squares regression. Deep neural network is one of the machine learning methods that has been widely applied to regression problems. This study aims to find better predictive performance by comparing the least squares regression method and the deep neural network method. The research method is done first by making an equation model with the least squares regression method. Second, by training the deep neural network using the same data so that the network model is obtained. Furthermore, the results of both methods are compared by calculating MAE and MSE. The results showed that the network model with superior deep neural network was used to predict data outside the range of trained data compared to the least squares regression method