PREDIKSI SALINITAS AIR LAUT DENGAN  DEEP NEURAL NETWORK

Wiwien Widyastuti; J. B. Budi Darmawan

doi:10.33557/jurnalmatrik.v21i2.570

Wiwien Widyastuti Universitas Sanata Dharma
J. B. Budi Darmawan Universitas Sanata Dharma

DOI: https://doi.org/10.33557/jurnalmatrik.v21i2.570

Keywords: Deep Neural Network, CalCOFI,, regression

Abstract

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.

References

[1] Sohier, “California Cooperative Oceanic Fisheries Investigations (CalCOFI) data set,” Diakses Mei 2019. https://www.kaggle.com/sohier/calcofi
[2] Farifteh, J., van der Meer, F., Atzberger, C., & Carranza, E, ”Quantitative analysis of salt affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN),” Remote Sensing of Environment, 110, 59–78, 2007
[3] Weicheng Wu, et al, “Soil salinity prediction and mapping by machine learning regression in Central Mesopotamia, Iraq,” [Online] Available: wileyonlinelibrary.com/journal/ldr. Land Degrad Dev. 2018;29:4005–4014, 2018
[4] Hari K.C., Rammani Adhikari 2, Er. Sharan Thapa, “Feed-Forward Deep Learning Model for Data Analysis and Prediction,” International Journal of Computer Trends and Technology (IJCTT) – Volume 63 Number 1. 2018
[5] Coates A, Huval B, Wang T, Wu D J and Ng A Y., “Deep learning with COTS HPC Systems,” Proceedings of the International Conference on Machine Learning (ICML) (Atlanta, GA, USA) 1337, 2013
[6] Tan Y, Ding K, “ A Survey on GPU-based Implementation of Swarm Intelligence Algorithms,” IEEE Transactions on Cybernetics 46 2028, 2016.
[7] Darmawan J. B. B. and Mungkasi S, “Parallel Computations Using a Cluster of Workstations to Simulate Elasticity Problems,” Journal of Physics: Conference Series accepted. 2016
[8] Steven C. Chapra, Raymond P, Canale, “Numerical Methods for Engineers,”6th edition. McGraw Hill. New York.2010