Globally vs. Locally Trained Machine Learning Models for Landslide Detection: A Case Study of a Glacial Landscape

Abstract

Landslide risk mitigation is limited by data scarcity; however, this could be improved using continuous landslide detection systems. To investigate which image types and machine learning models are most useful for landslide detection in a Norwegian setting, we compared the performance of five different machine learning models, for the Jølster case study (30 July 2019), in Western Norway. These included three globally pre-trained models; (i) the continuous change detection and classification (CCDC) algorithm, (ii) a combined k-means clustering and random forest classification model, and (iii) a convolutional neural network (CNN), and two locally trained models, including; (iv) classification and regression Trees and (v) a U-net CNN model. Images used included Sentinel-1, Sentinel-2, as well as digital elevation model (DEM) and slope. The globally trained models performed poorly in shadowed areas and were all outperformed by the locally trained models. A maximum Matthew’s correlation coefficient (MCC) score of 89% was achieved with a CNN U-net deep learning model, using combined Sentinel-1 and -2 images as input. This is one of the first attempts to apply deep learning to detect landslides with both Sentinel-1 and -2 images. Using Sentinel-1 images only, the locally-trained deep-learning model significantly outperformed the conventional machine learning model. These findings contribute to developing a national continuous monitoring system for landslides.

Remote Sensing-Based 3D Assessment of Landslides: A Review of the Data, Methods, and Applications

“…These methods are considered data-driven approaches to learning data association and patterns through complex models. They have been intensively used in landslide studies for their remarkable performance [37,65,94,98,103,116]. They can process 3D data and extract relevant 3D geometric features to provide information about the terrain characteristics (i.e., topography) and surface conditions (e.g., precipitation patterns and land cover changes) [37,94,96].…”

“…Improved accuracy and precision of 3D data: Lidar collects 3D data using laser pulses, which are robust to varying acquisition conditions such as season, weather, and low-light conditions like night-time [87]. Therefore, they can provide more accurate 3D data, often used for validation as ground truth data for landslide-related research [37,[94][95][96][97][98] or for 3D modeling and reconstruction of terrains [24,27].…”

“…Transfer learning (by transferring knowledge from past experiences to new scenarios) is one of the most challenging tasks in model generalization using ML or DL models on landslide studies [114]. However, models trained on data from a specific area may not generalize well to other areas with different geological and environmental conditions [97,98,126]. Thus, developing a model that can transfer landslide knowledge across different geographical areas is a significant challenge.…”

Automatic Detection of Forested Landslides: A Case Study in Jiuzhaigou County, China

“…Existing landslide detection models rely on a singular data source type. The question of how to maximize the use of data from multiple sources remains unanswered [41]. This study proposes a multimodal fusion network for merging optical images, hillshade images, and DEM, which conducts feature-level fusion of multimodal remote sensing data, as a solution to the aforementioned problem.…”

“…With regard to the multimodal fusion models, optical remote sensing and radar are used to create landslide mapping [7,40]. Ganerød et al [41] used five existing machine learning models with Sentinel-1, Sentinel-2, DEM, and slope images to detect landslides. Bhuyan et al [42] proposed a transfer learning strategy with attention U-Net to generate a landslide inventory map from remote sensing images.…”