Deep neural network-based prediction of tsunami wave attenuation by mangrove forests
Didit Adytia
(School of Computing, Telkom University, Jalan Telekomunikasi No. 1 Terusan Buah Batu, Bandung 40257, Indonesia; Corresponding author.)
Dede Tarwidi
(School of Computing, Telkom University, Jalan Telekomunikasi No. 1 Terusan Buah Batu, Bandung 40257, Indonesia; Industrial and Financial Mathematics Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jalan Ganesha No. 10, Bandung 40132, Indonesia)
Deni Saepudin
(School of Computing, Telkom University, Jalan Telekomunikasi No. 1 Terusan Buah Batu, Bandung 40257, Indonesia)
Semeidi Husrin
(Research Center for Geological Disasters, BRIN, Indonesia)
Abdul Rahman Mohd Kasim
(Centre for Mathematical Sciences, Universiti Malaysia Pahang, Lebuhraya Tun Razak, Gambang 26300, Pahang, Malaysia)
Mohd Fakhizan Romlie
(Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, Malaysia)
Dafrizal Samsudin
(Program Studi Ilmu Komunikasi, Fakultas Ilmu Komunikasi, Universitas Islam Riau, Jalan Kaharuddin Nst No.113, Simpang Tiga, Kec. Bukit Raya, Kota Pekanbaru, Riau, Indonesia)
Journal: MethodsX
•
• Elsevier
• ISSN: 2215-0161
Abstract
The goal of this research is to develop a model employing deep neural networks (DNNs) to predict the effectiveness of mangrove forests in attenuating the impact of tsunami waves. The dataset for the DNN model is obtained by simulating tsunami wave attenuation using the Boussinesq model with a staggered grid approximation. The Boussinesq model for wave attenuation is validated using laboratory experiments exhibiting a mean absolute error (MAE) ranging from 0.003 to 0.01. We employ over 40,000 data points generated from the Boussinesq numerical simulations to train the DNN. Efforts are made to optimize hyperparameters and determine the neural network architecture to attain optimal performance during the training process. The prediction results of the DNN model exhibit a coefficient of determination (R2) of 0.99560, an MAE of 0.00118, a root mean squared error (RMSE) of 0.00151, and a mean absolute percentage error (MAPE) of 3 %. When comparing the DNN model with three alternative machine learning models— support vector regression (SVR), multiple linear regression (MLR), and extreme gradient boosting (XGBoost)— the performance of DNN is superior to that of SVR and MLR, but it is similar to XGBoost. • High-accuracy DNN models require hyperparameter optimization and neural network architecture selection. • The error of DNN models in predicting the attenuation of tsunami waves by mangrove forests is less than 3 %. • DNN can serve as an alternate predictive model to empirical formulas or classical numerical models.