Landslide Detection from Open Satellite Imagery Using Distant Domain Transfer Learning
| Autor: | Lingshuai Zhang, Shengwu Qin, Yanqing Zhang, Jingbo Sun, Qiushi Cheng, Jingyu Yao, Xu Guo, Qiao Shuangshuang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
remote sensing scene classification
business.industry Computer science Science Landslide Pattern recognition Convolutional neural network Domain (software engineering) Set (abstract data type) Identification (information) satellite optical imagery landslide detection distant domain transfer learning General Earth and Planetary Sciences Satellite Satellite imagery attention mechanism Artificial intelligence business Transfer of learning |
| Zdroj: | Remote Sensing, Vol 13, Iss 3383, p 3383 (2021) Remote Sensing; Volume 13; Issue 17; Pages: 3383 |
| ISSN: | 2072-4292 |
| DOI: | 10.3390/rs13173383 |
| Popis: | Using convolutional neural network (CNN) methods and satellite images for landslide identification and classification is a very efficient and popular task in geological hazard investigations. However, traditional CNNs have two disadvantages: (1) insufficient training images from the study area and (2) uneven distribution of the training set and validation set. In this paper, we introduced distant domain transfer learning (DDTL) methods for landslide detection and classification. We first introduce scene classification satellite imagery into the landslide detection task. In addition, in order to more effectively extract information from satellite images, we innovatively add an attention mechanism to DDTL (AM-DDTL). In this paper, the Longgang study area, a district in Shenzhen City, Guangdong Province, has only 177 samples as the landslide target domain. We examine the effect of DDTL by comparing three methods: the convolutional CNN, pretrained model and DDTL. We compare different attention mechanisms based on the DDTL. The experimental results show that the DDTL method has better detection performance than the normal CNN, and the AM-DDTL models achieve 94% classification accuracy, which is 7% higher than the conventional DDTL method. The requirements for the detection and classification of potential landslides at different disaster zones can be met by applying the AM-DDTL algorithm, which outperforms traditional CNN methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|