Landslide Classification from Synthetic Aperture Radar Images Using Convolutional Neural Network with Multichannel Information

Abstract

Detection of disaster-stricken areas using synthetic aperture radar (SAR) images is important in countries and regions with heavy rain and earthquakes. Although it is important to immediately find disaster-stricken areas when a disaster occurs, it takes time to read SAR images and also needs experience and expertise. Therefore, machine learning, especially deep learning, is expected to be applied to the classification of disaster-stricken areas. Classification using deep learning is often executed on patch images of local areas. However, patch-based classification would miss information on the surrounding areas such as topographic features. In this study, a convolutional neural network (CNN) is applied to the classification of SAR images using the following techniques. When making the images input to a CNN, two multichannel image generation methods, i.e, a zero-padding method and map-concatenation method, are used, where the target areas to be classified and their surrounding areas are combined to form multichannel images. In the experiments, the zero-padding method and map-concatenation method are evaluated by the classification performance of SAR images that cover the northern Kyushu area in Japan, where large-scale landslides due to heavy rain occurred in 2017. Through the experiments, we clarify the appropriate CNN structures with multichannel information for landslide classification.ters such as the metropolitan-area earthquake and the Nankai Trough earthquake are imminent; thus, detecting disaster-stricken areas by satellite remote sensing is extremely important. Earthquakes and torrential rain cause landslides, but finding the areas of landslides is difficult because they often occur in areas that are not easily accessed.Research on landslide detection using satellite remote sensing has been actively conducted [2]- [4]. Many methods detect landslides on the basis of the amount of change in the normalized difference vegetation index (NDVI) calculated from optical satellite images before and after the disaster [5], [6]. NDVI

Anomaly Detection Using Convolutional Adversarial Autoencoder and One-class SVM for Landslide Area Detection from Synthetic Aperture Radar Images

“…Synthetic aperture radar is an active image radar that synthesizes small antennas mounted on a platform, such as an aircraft or satellite, to realize large virtual antennas and generates high-resolution radar images [12][13][14]. Because SAR is an active sensor that emits microwaves, it is possible to observe the surface of the earth regardless of the presence or absence of sunlight and clouds.…”