Unsupervised Feature Learning to Improve Transferability of Landslide Susceptibility Representations

Abstract

A landslide susceptibility map (LSM) is of vital importance for risk recognition and prevention. In the last decade, statistical methods have gradually exerted their impact on mapping the landslide susceptibility to locate the high-risk places of landslide. However, due to the complexity of getting full access to the thematic information in large scenarios, most of these statistical methods generally suffer from overfitting, inadequate representative power, and the inability to transfer the learned representation to other places. To solve these challenges, this study designed an unsupervised representation learning module, which features independence, compactness, robustness, and transferability. Specifically, we first stack restricted Boltzmann machines (RBMs) and denoising autoencoder (DAE) to unsupervised discover the underlying representations embedded in the thematic maps. Then we applied the transferring strategy in an adversarial manner to generalize the learned representations to the sample-scarce area. Experimental results and analyses using data in different regions have revealed that the proposed method can be generalized well between different LSM scenarios. In terms of precision, it outperforms other methods by a large margin, e.g. by around 7% compared to multilayer perceptrons (MLP) with the same configuration, and by 3%-4% to the state of art algorithm random forest (RF). Besides, compared to other methods, the landslide susceptibility map that is predicted by the proposed method featuring smoothness and stableness seems more reliable, and is more according to some prior knowledge that, for example, distance to the drainage, slope, stratum should exert dominant effects on the occurrence of a landslide.

Incorporating Landslide Spatial Information and Correlated Features among Conditioning Factors for Landslide Susceptibility Mapping

“…Of them, landslide susceptibility mapping (LSM) plays an important role in providing a thematic map for portraying where landslides are likely to occur and the probability of their occurrence. A landslide inventory consisting of landslide points and related conditioning factors is the basis of LSM, but the number of landslide points is usually restricted due to the time-consuming and labor-intensive collection process [33]. The motivation of this study is to capture more landslide representation from a limited dataset.…”

“…Moreover, small, labeled samples that refer to limited bodies of landslide points are a problem that may lead to overfitting in supervised methods. In practice, the determination of the landslide position generally needs expert knowledge or even costly on-site investigations [33]. The amount of samples in a landslide inventory in a certain region is, thus, generally limited and small.…”

Landslide Mapping Using Two Main Deep-Learning Convolution Neural Network Streams Combined by the Dempster–Shafer Model

“…[25] used an artificial neural network (ANN) as an automatic landslide detection methodology by multi-spectral Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images. An unsupervised feature learning method of a stochastic neural network of restricted Boltzmann machine was applied by [26] for landslide susceptibility assessment. [27] used spectral information together with morphometric characteristics and shape to separate landslides from non-landslide areas.…”

Joint Learning of Contour and Structure for Boundary-Preserved Building Extraction

“…With the development of DCNNs in recent years, many algorithms have been proposed for processing remote sensing images [25][26][27][28][29][30][31][32]. The fully convolutional network [33] (FCN) replaces the fully connected layers with convolutional layers, making it possible for large-scale dense prediction.…”