A Convolutional Neural Network for Coastal Classification Based on ALOS and NOAA Satellite Data
Kinh Bac Dang, Van Bao Dang, Quang‐Thanh Bui, Vuong Van Nguyen, Thi Phuong Nga Pham, Ngô Văn Liêm
Abstract
Although coastal classification has been attended in recent years, it is still a complicated problem in quantitative geomorphological and hydrological sciences. Nowadays, the integration of deep learning in remote sensing and GIS analysis can quickly classify and detect different characteristics on both land and sea. Therefore, the authors proposed the use of a convolutional neural network (ConvNet) for coastal classification based on these technologies and geomorphic profile graphs. The primary input data is digital elevation/depth models obtained from ALOS and NOAA satellite. Eight hundred coastal samples representing eight types of coasts taken along the coastline in Vietnam were used for training and testing various ConvNets. As a result, three ConvNet models using three different optimizer functions were developed with the accuracies of about 98% and low values of the loss function. These models were used to classify 1029 in 1150 coasts (equal to 89%) in Vietnam. Nearly 11% of Vietnamese coasts could not be defined by three ConvNet models due to their complex geomorphic profile graphs, and require assessments of other natural components. The trained ConvNet models can potentially update new coastal types in different tropical countries towards coastal classification on national and global scales.