Predicting Landslides Using Locally Aligned Convolutional Neural Networks

Abstract

<jats:p>Landslides, movement of soil and rock under the influence of gravity, are common phenomena that cause significant human and economic losses every year. Experts use heterogeneous features such as slope, elevation, land cover, lithology, rock age, and rock family to predict landslides. To work with such features, we adapted convolutional neural networks to consider relative spatial information for the prediction task. Traditional filters in these networks either have a fixed orientation or are rotationally invariant. Intuitively, the filters should orient uphill, but there is not enough data to learn the concept of uphill; instead, it can be provided as prior knowledge. We propose a model called Locally Aligned Convolutional Neural Network, LACNN, that follows the ground surface at multiple scales to predict possible landslide occurrence for a single point. To validate our method, we created a standardized dataset of georeferenced images consisting of the heterogeneous features as inputs, and compared our method to several baselines, including linear regression, a neural network, and a convolutional network, using log-likelihood error and Receiver Operating Characteristic curves on the test set. Our model achieves 2-7% improvement in terms of accuracy and 2-15% boost in terms of log likelihood compared to the other proposed baselines.</jats:p>

A comparative study of heterogeneous ensemble-learning techniques for landslide susceptibility mapping

“…Specifically, we used the grid search procedure to adjust the hyperparameters of SVM and LR, and the search space was determined based on the previous studies (Ghorbanzadeh et al 2019, Yang andCervone 2019). As for the deep learning models of CNN and RNN, we used a common optimization process based on previous studies and the fine-tuning procedure (Hajimoradlou 2019, Mutlu et al 2019. For the stacking and blending methods, the LR model was the meta-classifier for final susceptibility prediction because simple linear models typically work well (Witten et al 2016).…”

“…Deep learning techniques outperform the other machine learning methods in the fields of natural language processing, object detection, and scene classification (Collobert and Weston 2008, Li et al 2010, Han et al 2018 and have shown success in spatial prediction of landslides. Successful examples include sparse autoencoders (Huang et al 2019), convolutional neural network (CNN) , Hajimoradlou 2019, Ullo et al 2019, Wang et al 2019b, Fang et al 2020, recurrent neural network (RNN) (Mutlu et al 2019, Wang et al 2020b and residual networks .…”

70 years of machine learning in geoscience in review

“…The learnings from the TGS Salt Identification challenge have been incorporated in production scale models that perform human-like salt interpretation ( Sen, Kainkaryam, Ong, & Sharma, 2020 ). In broader geoscience, U-nets have been used to model global water storage using GRAVE satellite data ( Sun et al, 2019 ), landslide prediction ( Hajimoradlou, Roberti, & Poole, 2019 ), and earthquake arrival time picking ( Zhu & Beroza, 2018 ). A more classical approach identifies subsea scale worms in hydrothermal vents ( Shashidhara, Scott, & Marburg, 2020 ), whereas Dramsch, Christensen, MacBeth, & Lüthje (2019) includes a U-net in a larger system for unsupervised 3D timeshift extraction from 4D seismic.…”

Land Deformation Prediction via Slope-Aware Graph Neural Networks

“…Two experimental studies (Wang, Fang, and Hong 2019;Ghorbanzadeh et al 2019) evaluate CNNs and typical machine learning methods on susceptibility detection and investigate the impact of spectral and topographic factors on LSM, indicating that CNNs are more practical for LSM and landslide prevention than conventional methods. Recently, (Hajimoradlou, Roberti, and Poole 2020) proposed locally aligned CNN filters to capture the orientation of each pixel at multiple resolutions for landslide identification. Previous works either study landslide susceptibility using 2D geospatial images (Wang, Fang, and Hong 2019;Ghorbanzadeh et al 2019;Hajimoradlou, Roberti, and Poole 2020) or convert the InSAR data into a 2D bird's view images and then apply statistical methods for landslide prediction (Dai et al 2016;Carlà et al 2019).…”

“…Landslides and mudslides are also significant threats for infrastructures and residents near hydropower stations. Therefore, monitoring and preventing such disasters have received considerable attention from both industry and academia (Bozzano et al 2011;Gao, Dai, and Chen 2020;Hajimoradlou, Roberti, and Poole 2020).…”