Regional early warning systems for landslides rely on historic data to forecast future events and to verify and improve alarms. However, databases of landslide events are often spatially biased towards roads or other infrastructure, with few reported in remote areas. In this study, we demonstrate how Google Earth Engine can be used to create multi-temporal change detection image composites with freely available Sentinel-1 and -2 satellite images, in order to improve landslide visibility and facilitate landslide detection. First, multispectral Sentinel-2 images were used to map landslides triggered by a summer rainstorm in Jølster (Norway), based on changes in the normalised difference vegetation index (NDVI) between pre- and post-event images. Pre- and post-event multi-temporal images were then created by reducing across all available images within one month before and after the landslide events, from which final change detection image composites were produced. We used the mean of backscatter intensity in co- (VV) and cross-polarisations (VH) for Sentinel-1 synthetic aperture radar (SAR) data and maximum NDVI for Sentinel-2. The NDVI-based mapping increased the number of registered events from 14 to 120, while spatial bias was decreased, from 100% of events located within 500 m of a road to 30% close to roads in the new inventory. Of the 120 landslides, 43% were also detectable in the multi-temporal SAR image composite in VV polarisation, while only the east-facing landslides were clearly visible in VH. Noise, from clouds and agriculture in Sentinel-2, and speckle in Sentinel-1, was reduced using the multi-temporal composite approaches, improving landslide visibility without compromising spatial resolution. Our results indicate that manual or automated landslide detection could be significantly improved with multi-temporal image composites using freely available earth observation images and Google Earth Engine, with valuable potential for improving spatial bias in landslide inventories. Using the multi-temporal satellite image composites, we observed significant improvements in landslide visibility in Jølster, compared with conventional bi-temporal change detection methods, and applied this for the first time using VV-polarised SAR data. The GEE scripts allow this procedure to be quickly repeated in new areas, which can be helpful for reducing spatial bias in landslide databases.

No abstract

Multiple landslide events are common around the globe. They can cause severe damage to both human lives and infrastructures. Although a huge quantity of research has been shaped to address rapid mapping of landslides by optical Earth Observation (EO) data, various gaps and uncertainties are still present when dealing with cloud obscuration and 24/7 operativity. To address the issue, we explore the usage of SAR data over the eastern Iburi sub-prefecture of Hokkaido, Japan. In the area, about 8000 co-seismic landslides were triggered by an Mw 6.6 earthquake on 6 September 2018, at 03.08 local time (JST). In the following study, we modify a Deep Learning (DL) convolutional neural network (CNN) architecture suited for pixel-based classification purposes, the so-called Attention U-Net (Attn-U-Net) and we employ it to evaluate the potential of bi- and tri-temporal SAR amplitude data from the Sentinel-1 satellite and slope angle to map landslides even under thick cloud cover. Four different datasets, composed of two different band combinations per two satellite orbits (ascending and descending) are analyzed. Moreover, the impact of augmentations is evaluated independently for each dataset. The models’ predictions are compared against an accurate landslide inventory obtained by manual mapping on pre-and post-event PlanetScope imagery through F1-score and other common metrics. The best result was yielded by the augmented ascending tri-temporal SAR composite image (61% F1-score). Augmentations have a positive impact on the ascending Sentinel-1 orbit, while metrics decrease when augmentations are applied on descending path. Our findings demonstrate that combining SAR data with other data sources may help to map landslides quickly, even during storms and under deep cloud cover. However, further investigations and improvements are still needed, this being one of the first attempts in which the combination of SAR data and DL algorithms are employed for landslide mapping purposes.

Repeated temporal mapping of landslides is essential for investigating changes in landslide movements, legacy effects of the landslide triggering events, and susceptibility changes in the area. However, in order to perform such investigations, multi-temporal (MT) inventories of landslides are required. The traditional approach of visual interpretation from cloud-free optical remote sensing imageries is time consuming and expensive. Recent endeavours exploring Convolutional Neural Networks and deep learning models have made rapid and accurate mapping of landslides feasible but have not been applied for multi-temporal landslide mapping in the Himalayas, yet. Earlier models used a standard supervised learning approach, with a small landslide inventory over a limited area used for training , which is then utilized to predict landslides in nearby areas. We propose a new strategy, using geographically separate training samples to design a standard approach which can be utilized to create multi-temporal landslide inventories. RapidEye images of 5-metres spatial resolution are used to generate MT landslide inventories in the study area of Rasuwa district, Nepal. We test the effectiveness of the model by training with only 55 landslides and predicting for a different area. Then, using the weights attained from this first training phase, we use transfer learning to map landslides over a time period between 2013 and 2019 in the Rasuwa district. We also adopt data augmentation techniques to add more training samples, leading to higher overall accuracies ranging from 58% in 2015 to 80% in 2017. We also perform a spatial comparison between the manual (observed) and predicted inventories to evaluate the differences between landslide densities and overall landslide statistics of landslide area distribution. The benefit of a transfer learning-based model training is that it circumvents the need for generating annual inventories for training a deep learning. A single event based inventory is enough to generate landslide inventories over a number of years, at least until landslide preparatory conditions do not change significantly. This application can enable automated workflows to generate MT landslide inventories of particular areas as the basis for landslide evolution and movement change analysis.

Abstract. 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.