Accurate early warning systems for landslides are a reliable risk-reduction strategy that may significantly reduce fatalities and economic losses. Several machine learning methods have been examined for this purpose, underlying deep learning (DL) models’ remarkable prediction capabilities. The long short-term memory (LSTM) and gated recurrent unit (GRU) algorithms are the sole DL model studied in the extant comparisons. However, several other DL algorithms are suitable for time series forecasting tasks. In this paper, we assess, compare, and describe seven DL methods for forecasting future landslide displacement: multi-layer perception (MLP), LSTM, GRU, 1D convolutional neural network (1D CNN), 2xLSTM, bidirectional LSTM (bi-LSTM), and an architecture composed of 1D CNN and LSTM (Conv-LSTM). The investigation focuses on four landslides with different geographic locations, geological settings, time step dimensions, and measurement instruments. Two landslides are located in an artificial reservoir context, while the displacement of the other two is influenced just by rainfall. The results reveal that the MLP, GRU, and LSTM models can make reliable predictions in all four scenarios, while the Conv-LSTM model outperforms the others in the Baishuihe landslide, where the landslide is highly seasonal. No evident performance differences were found for landslides inside artificial reservoirs rather than outside. Furthermore, the research shows that MLP is better adapted to forecast the highest displacement peaks, while LSTM and GRU are better suited to model lower displacement peaks. We believe the findings of this research will serve as a precious aid when implementing a DL-based landslide early warning system (LEWS).

The analysis of remote sensing data to assess geohazards is being improved by web-based platforms and collaborative projects, such as the Geohazard Exploitation Platform (GEP) of the European Space Agency (ESA). This paper presents the evaluation of a surface velocity map that is generated by this platform. The map was produced through an unsupervised Multi-temporal InSAR (MTI) analysis applying the Parallel-SBAS (P-SBAS) algorithm to 25 ENVISAT satellite images from the South of Spain that were acquired between 2003 and 2008. This analysis was carried out using a service implemented in the GEP called “SBAS InSAR”. Thanks to the map that was generated by the SBAS InSAR service, we identified processes not documented so far; provided new monitoring data in places affected by known ground instabilities; defined the area affected by these instabilities; and, studied a case where GEP could have been able to help in the forecast of a slope movement reactivation. This amply demonstrates the reliability and usefulness of the GEP, and shows how web-based platforms may enhance the capacity to identify, monitor, and assess hazards that are associated to geological processes.

Landslides in reservoir contexts are a well-recognised hazard that may lead to dangerous situations regarding infrastructures and people’s safety. Satellite-based radar interferometry is proving to be a reliable method to monitor the activity of landslides in such contexts. Here, we present a DInSAR (Differential Interferometric Synthetic Aperture Radar) analysis of Sentinel-1 images that exemplifies the usefulness of the technique to recognize and monitor landslides in the Rules Reservoir (Southern Spain). The integration of DInSAR results with a comprehensive geomorphological study allowed us to understand the typology, evolution and triggering factors of three active landslides: Lorenzo-1, Rules Viaduct and El Arrecife. We could distinguish between rotational and translational landslides and, thus, we evaluated the potential hazards related to these typologies, i.e., retrogression (Lorenzo-1 and Rules Viaduct landslides) or catastrophic slope failure (El Arrecife Landslide), respectively. We also observed how changes in the water level of the reservoir influence the landslide’s behaviour. Additionally, we were able to monitor the stability of the Rules Dam as well as detect the deformation of a highway viaduct that crosses a branch of the reservoir. Overall, we consider that other techniques must be applied to continue monitoring the movements, especially in the El Arrecife Landslide, in order to avoid future structural damages and fatalities.

This work describes the set of tools developed, tested, and put into production in the context of the H2020 project Multi-scale Observation and Monitoring of Railway Infrastructure Threats (MOMIT). This project, which ended in 2019, aimed to show how the use of various remote sensing techniques could help to improve the monitoring of railway infrastructures, such as tracks or bridges, and thus, consequently, improve the detection of ground instabilities and facilitate their management. Several lines of work were opened by MOMIT, but the authors of this work concentrated their efforts in the design of tools to help the detection and identification of ground movements using synthetic aperture radar interferometry (InSAR) data. The main output of this activity was a set of tools able to detect the areas labelled active deformation areas (ADA), with the highest deformation rates and to connect them to a geological or anthropogenic process. ADAtools is the name given to the aforementioned set of tools. The description of these tools includes the definition of their targets, inputs, and outputs, as well as details on how the correctness of the applications was checked and on the benchmarks showing their performance. The ADAtools include the following applications: ADAfinder, los2hv, ADAclassifier, and THEXfinder. The toolset is targeted at the analysis and interpretation of InSAR results. Ancillary information supports the semi-automatic interpretation and classification process. Two real use-cases illustrating this statement are included at the end of this paper to show the kind of results that may be obtained with the ADAtools.

Coastal regions in Southwest Europe have experienced major interventions and transformations of the territory with unprecedented urban development, primarily related to growing tourism activity. The coast is the place where marine and terrestrial processes converge, making it highly vulnerable to the effects of climate change. However, the lack of information on the frequency of these extreme weather events and their impacts on the coast hampers an accurate analysis of the consequences of global change. This paper provides a detailed analysis of the extreme weather events (EWE) that have affected the Atlantic and Mediterranean coasts of Southwest Europe during the period from 1 January 2009 to 28 February 2020, as well as a quantification of their impacts: fatalities, injuries and economic damage. Official sources from France, Portugal and Spain were consulted, along with technical reports, scientific articles, etc., to generate a unified database. A total of 95 significant extreme events have caused 168 fatalities, 137 injuries and almost €4000 M in direct economic losses. Cyclone Xynthia (February 2010) on the French Atlantic coast stands out, having caused 47 fatalities, 79 injuries and substantial economic losses valued at €3000 M. The study shows a slight upward trend in the number of events recorded, especially during the last three years of the analysis, as well as in human losses and damages. The results reveal a higher exposure of the Mediterranean coast of Southwest Europe when compared to the Atlantic, especially the Spanish Mediterranean coast, with 61% of the fatalities recorded there during the study period. This is primarily due to a model of exponential tourism growth on the Mediterranean coast, with an enormous urban and infrastructure development during the last decades. Traditionally, the Mediterranean coast is less prepared to reduce the effects of marine storms, extreme events that are becoming more frequent and virulent in the context of climate and global change. This work highlights the need to create a continuous monitoring system–at the European level–of the impacts of extreme weather events on the coast, where 40% of the European population is concentrated. This observatory should serve as a source of information for risk mitigation policies (predictive, preventive and corrective), as well as for emergency management during disasters.

A rapidly growing population across mountain regions is pressuring expansion onto steeper slopes, leading to increased exposure of people and their assets to slow‐moving landslides. These moving hillslopes can inflict damage to buildings and infrastructure, accelerate with urban alterations, and catastrophically fail with climatic and weather extremes. Yet, systematic estimates of slow‐moving landslide exposure and their drivers have been elusive. Here, we present a new global database of 7,764 large (A ≥ 0.1 km²) slow‐moving landslides across nine IPCC regions. Using high‐resolution human settlement footprint data, we identify 563 inhabited landslides. We estimate that 9% of reported slow‐moving landslides are inhabited, in a given basin, and have 12% of their areas occupied by human settlements, on average. We find the density of settlements on unstable slopes decreases in basins more affected by slow‐moving landslides, but varies across regions with greater flood exposure. Across most regions, urbanization can be a relevant driver of slow‐moving landslide exposure, while steepness and flood exposure have regionally varying influences. In East Asia, slow‐moving landslide exposure increases with urbanization, gentler slopes, and less flood exposure. Our findings quantify how disparate knowledge creates uncertainty that undermines an assessment of the drivers of slow‐moving landslide exposure in mountain regions, facing a future of rising risk, such as Central Asia, Northeast Africa, and the Tibetan Plateau.