Multiple landslide events occur often across the world which have the potential to cause significant harm to both human life and property. Although a substantial amount of research has been conducted to address mapping of landslides using Earth observation (EO) data, several gaps and uncertainties remain with developing models to be operational at the global scale. The lack of a high-resolution globally distributed and event-diverse dataset for landslide segmentation poses a challenge in developing machine learning models that can accurately and robustly detect landslides in various regions, as the limited representation of landslide and background classes can result in poor generalization performance of the models. To address this issue, we present the High-Resolution Global landslide Detector Database (HR-GLDD), a high-resolution (HR) satellite dataset (PlanetScope, 3 m pixel resolution) for landslide mapping composed of landslide instances from 10 different physiographical regions globally in South and South-East Asia, East Asia, South America, and Central America. The dataset contains five rainfall-triggered and five earthquake-triggered multiple landslide events that occurred in varying geomorphological and topographical regions in the form of standardized image patches containing four PlanetScope image bands (red, green, blue, and NIR) and a binary mask for landslide detection. The HR-GLDD can be accessed through this link: https://doi.org/10.5281/zenodo.7189381 (Meena et al., 2022a, c). HR-GLDD is one of the first datasets for landslide detection generated by high-resolution satellite imagery which can be useful for applications in artificial intelligence for landslide segmentation and detection studies. Five state-of-the-art deep learning models were used to test the transferability and robustness of the HR-GLDD. Moreover, three recent landslide events were used for testing the performance and usability of the dataset to comment on the detection of newly occurring significant landslide events. The deep learning models showed similar results when testing the HR-GLDD at individual test sites, thereby indicating the robustness of the dataset for such purposes. The HR-GLDD is open access and it has the potential to calibrate and develop models to produce reliable inventories using high-resolution satellite imagery after the occurrence of new significant landslide events. The HR-GLDD will be updated regularly by integrating data from new landslide events.

Automatic landslide mapping is crucial for a fast response in a disaster scenario and improving landslide susceptibility models. Recent studies highlighted the potential of deep learning methods for automatic landslide segmentation. However, only a few works discuss the generalization capacity of these models to segment landslides in areas that differ from the ones used to train the models. In this study, we evaluated three different locations to assess the generalization capacity of these models in areas with similar and different environmental aspects. The model training consisted of three distinct datasets created with RapidEye satellite images, Normalized Vegetation Index (NDVI), and a digital elevation model (DEM). Here, we show that larger patch sizes (128 × 128 and 256 × 256 pixels) favor the detection of landslides in areas similar to the training area, while models trained with smaller patch sizes (32 × 32 and 64 × 64 pixels) are better for landslide detection in areas with different environmental aspects. In addition, we found that the NDVI layer helped to balance the model’s results and that morphological post-processing operations are efficient for improving the segmentation precision results. Our research highlights the potential of deep learning models for segmenting landslides in different areas and is a starting point for more sophisticated investigations that evaluate model generalization in images from various sensors and resolutions.

Landslide susceptibility studies are a common type of landslide assessment. Landslides are one of the most frequent hazards in Brazil, resulting in significant economic and social losses (e.g., deaths, injuries, and property destruction). This paper presents a literature review of susceptibility mapping studies in Brazil and analyzes the methods and input data commonly used. The publications used in this analysis were extracted from the Web of Science platform. We considered the following aspects: location of study areas, year and where the study was published, methods, thematic variables, source of the landslide inventory, and validation methods. The susceptibility studies are concentrated in Brazil’s south and southeast region, with the number of publications increasing since 2015. The methods commonly used are slope stability and statistical models. Validation was performed based on receiver operating characteristic (ROC) curves and area under the curve (AUC). Even though landslide inventories constitute the most critical input data for susceptibility mapping, the criteria used for the creation of landslide inventories are not evident in most cases. The included studies apply various validation techniques, but evaluations with potential users and information on the practical applicability of the results are largely missing.

Landslides are among the most frequent hazards in Latin America and the world. In Brazil, they occur every year and cause economic and social loss. Landslide inventories are essential for assessing susceptibility, vulnerability, and risk. Over the decades, a variety of mapping approaches have been employed for the detection of landslides using Earth observation (EO) data. Object-based image analysis (OBIA) is a widely recognized method for mapping landslides and other morphological features. In Brazil, despite the high frequency of landslides, methods for inventory construction are poorly developed. The aim of this study is to semi-automatically recognize shallow landslides in Itaóca (Brazil) and evaluate the transferability of the approach within different areas in Brazil. RapidEye satellite images (5 m) and the derived normalized difference vegetation index (NDVI), as well as a digital elevation model (DEM) (12.5 m) and morphological data, were integrated into the classification. The results show that the method is suitable for the recognition of this type of hazard in Brazil. The overall accuracy was 89%. The main challenges were the identification of small landslides and the exact delineation of scars. The findings validate the applicability of the approach in Brazil, although additional adjustments to the primary rule set might lead to better results.