Deep Neural Network to Classify Seabed Sediment Using MBES Multifrequency

Abstract

This study investigates the classification of sediment distribution and types in inland waters using Artificial Neural Network (ANN) models based on multibeam echosounder data. Multibeam Echosounder Technology (MBES) is an acoustic instrument that emits high-speed sound pulses to map the bottom of water bodies. Valuable information about sediment characteristics can be obtained by analyzing the backscattering phenomenon, which measures the acoustic intensity reflected from the water bottom. The angular response curve (ARC) method, developed by Fonseca and Calder, is employed to analyze the relationship between backscatter intensity and the angle of reflection. The ANN models in this study are trained and tested using intensity values and angular response curves obtained from multibeam echo sounders. The ANN model architecture consists of an input layer, three hidden layers, and an output layer. The sigmoid activation function is utilized in the output layer, while the ReLU activation function is applied to the input and hidden layers. Performance evaluation demonstrates that the ANN model using uncorrected data achieves remarkable accuracy, with 100% accuracy obtained in both the training and testing stages. The model exhibits a training loss value of 0.059443 and a testing loss value of 0.110030, indicating its effectiveness in capturing patterns and reducing errors. Visualizing the sediment distribution in Waduk Selorejo reveals a relatively balanced presence of Clavey sand and Sandy silt sediment types. However, noticeable differences arise between the corrected and uncorrected data, which can be attributed to the alterations made during the data correction process. The best-performing ANN model achieves a testing accuracy of 0.75, indicating that it does not perfectly predict the given data. Acknowledging the potential for prediction errors when using corrected data is important.