Landslides are a major geohazard in hilly and mountainous environments. We focus on slow-moving, deep-seated landslides that are characterized by gradual, non-catastrophic deformations of millimeters to decimeters per year and cause extensive economic damage. To assess their potential impact and for the design of mitigation solutions, a detailed understanding of the slope processes is desired. Moreover, where landslide hazard mitigation is impossible, early warning systems are a valuable alternative to reduce landslide risk. Recent studies have demonstrated the effective application of machine learning for deformation forecasting to specific cases of slow-moving, non-catastrophic, deep-seated landslides. Machine learning, combined with satellite remote sensing products offers new opportunities for both local and regional monitoring of areas with unstable slopes and associated processes without costly and logistically challenging inspection of the landslide. To test to what extent data-driven machine learning techniques and remote sensing observations can be used for landslide deformation forecasting, we developed a machine learning based nowcasting model on the multi-sensor monitored, deep-seated Vögelsberg landslide, near Innsbruck, Tyrol, Austria. Our goal was to link the landslide deformation pattern to the conditions on the slope, and to produce a four-day, short-term forecast, a nowcast, of deformation accelerations. Changes in hillslope hydrology shift the balance between the shear strength of the soil and the shear (sliding) force applied by the gravitational forces acting on the landmass. Therefore, precipitation, snowmelt, soil moisture, evaporation, and air temperature were identified as hydro-meteorological variables with high potential for forecasting deformation dynamics. Time series of those variables were obtained from remote sensing sources where possible, and otherwise from reanalysis sources as surrogate for data that is likely to be available in the near future. Deformation, the result of slope instability, was monitored daily by a local, automated total station. Interferometric Synthetic Aperture Radar (InSAR) has shown to be a valuable resource of deformation information from space. However, due to the complex interaction with topography in mountainous environments, its potential is often questioned. We showed that 91% of the world’s slopes are observable by InSAR, given the presence of a coherent scatterer, i.e. a natural or man-made object that exhibits consistent radar reflection over time. A global map is provided to indicate the sensitivity of InSAR to assess downslope deformation on any particular slope. To quickly assess the presence of coherent scatterers, before further investigation, we developed an application in Google Earth Engine to estimate the presence and location of coherent scatterers on a slope. However, the current accuracy and temporal resolution of Sentinel-1 SAR acquisitions proved insufficient to identify the acceleration phases at Vögelsberg. The five years of daily deformation and hydro-meteorological observations at the Vögelsberg landslide is quite limited for a machine learning model. Therefore, a nowcasting model of low complexity was required. To limit the number of parameters to be optimized, the model was designed to mimic a bucket model, a simple hydrological model. A shallow neural network based on long short-term memory, was implemented in TensorFlow, as custom sequence of existing building blocks. Furthermore, a traditional neural network and recurrent neural network were tested for comparison. Thanks to the limited complexity of the model, the major contributors could be determined by trial-and-error of nearly 150 000 model variations. Models including soil moisture information are more likely to generate high quality nowcasts, followed by models based solely on precipitation or snowmelt. Although none of the shallow neural network configurations produced a convincing nowcast deformation, they provide important context for future attempts. The machine learning model was poorly constrained as only five years of observations were available in combination with the four acceleration events that occurred in these five years. Furthermore, standard error metrics, like mean squared error, are unsuitable for model optimization for landslide nowcasting. We showed that landslide deformation nowcasting is not a straightforward application of machine learning. The complexity of the machine learning model formulation at the Vögelsberg illustrates the necessity of expert judgement in the design and evaluation of a data-driven nowcast of slowly deforming slopes. Furthermore, to prepare for unexpected modelling developments, a high level of project level data organisation is recommended. There is a long road ahead for the large scale implementation of machine learning in landslide nowcasting and Early Warning Systems. However, a future, successful nowcasting system will require a simple, robust model and frequent, high quality and event-rich data to train upon.@en

Landslides are one of the major weather-related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope processes is required. Landslide modelling is typically based on data-rich geomechanical models. Recently, machine learning has shown promising results in modelling a variety of processes. Furthermore, slope conditions are now also monitored from space, in wide-area repeat surveys from satellites. In the present study we tested if use of machine learning, combined with readily available remote sensing data, allows us to build a deformation nowcasting model. A successful landslide deformation nowcast, based on remote sensing data and machine learning, would demonstrate effective understanding of the slope processes, even in the absence of physical modelling. We tested our methodology on the Vögelsberg, a deep-seated landslide near Innsbruck, Austria. Our results show that the formulation of such a machine learning system is not as straightforward as often hoped for. The primary issue is the freedom of the model compared to the number of acceleration events in the time series available for training, as well as inherent limitations of the standard quality metrics such as the mean squared error. Satellite remote sensing has the potential to provide longer time series, over wide areas. However, although longer time series of deformation and slope conditions are clearly beneficial for machine-learning-based analyses, the present study shows the importance of the training data quality but also that this technique is mostly applicable to the well-monitored, more dynamic deforming landslides.@en

Monitoring the status of the vegetation is required for nature conservation. This monitoring task is time consuming as kilometers of area have to be investigated and classified. To make this task more manageable, remote sensing is used. The acquisition of airplane remote sensing data is dependent on weather conditions and permission to fly in the busy airspace above the Netherlands. These conditions make it difficult to get a new, dedicated acquisition every year. Therefore, alternatives for this dependency on dedicated airplane surveys are needed. One alternative is the use of optical satellite imagery, as this type of data has improved rapidly in the last decade both in terms of resolution and revisit time. For this study, 0.5 m resolution satellite imagery from the Superview satellite is combined with geometric height data from the Dutch national airborne LiDAR elevation data set AHN. Goal is to classify vegetation into three different classes: sand, grass and trees, apply this classification to multiple epochs, and analyze class transition patterns. Three different classification methods were compared: nearest centroid, random forest and neural network. We show that outcomes of all three methods can be interpreted as class probabilities, but also that these probabilities have different properties for each method. The classification is implemented for 11 different epochs on the Meijendel en Berkheide dunal area on the Dutch coast. We show that mixed probabilities (i.e. between two classes) agree well with class transition processes, and conclude that a shallow neural network combined with pure training samples applied on four different bands (RGB + relative DSM height) produces satisfactory results for the analysis of vegetation transitions with accuracies close to 100%.

@en

Landslides are a major geohazard in hilly and mountainous environments. In-situ inspection of downslope motion is costly, sometimes dangerous and, requires prior knowledge of the existence of a landslide. Remote sensing from space is a way to detect and characterize landslides systematically at large scale. Interferometric Synthetic Aperture Radar (InSAR) has shown to be a valuable resource of deformation information, but it requires expert knowledge and considerable computational efforts. Moreover, the successful application of InSAR for landslides requires a favorable acquisition geometry relative to the landslide deformation pattern. Consequently, there is a need for a widely applicable tool to assess the potential of InSAR at a particular location a priori. Here we present a novel, generic approach to assess the potential of InSAR-based deformation tracking, providing a standardised and automated method applicable on any slope. We define the detection potential as the sensitivity of InSAR to detect downslope displacement combined with the presence of coherently scattering surfaces. We show that deformation can be detected on at least 91% of the global landslide-prone slopes, and provide an open source Google Earth Engine tool for the quick assessment of the availability of potential coherent scatterers. This tool enables any person interested in applying InSAR to routinely assess the potential for monitoring landslide deformation in their region of interest.@en

The ambition of H2020 OPERANDUM project is to develop and document Nature Based Solutions (NBS) to mitigate risks associated with hydro-meteorological (HM) hazards. NBS mitigate risks by reducing the vulnerability of a particular system. The aim of this work is to demonstrate the use of multisource remote sensing data in documenting the impact of extreme HM events to advance knowledge on vulnerability and exposure. In particular the focus is to document past impacts due to extreme events selected from a characterization of recent (3 0 years) HM events in 11 Open Air Laboratories (OALs) where co-design, co-development and deployment of NBS are taking place. The impacts were documented by applying a wide spectrum of satellite image data and other, close - range, remote sensing techniques. A better understanding of the consequences due to extreme HM events in a particular area (OALs) is essential to identify elements at risk and expected to provide a reference to evaluate the reduction of vulnerability and mitigation of risks past the completion of NBS.@en

Continuous landslide monitoring is a crucial task for the management of natural hazards for identifying suitable mitigation measures, including nature-based solutions. In the present study, three monitoring techniques including (i) an automated tracking total station (ATTS), (ii) multi-temporal terrestrial laser scanning (TLS) and (iii) space-borne interferometric synthetic aperture radar (InSAR) are applied to monitor the spatio-temporal displacement patterns of the Vögelsberg landslide (Tyrol, Austria) between 2016/05 and 2020/06. The landslide shows spatially and temporally varying displacement rates with up to 12 cm/a and a mean annual displacement of 4 cm/a. The results show that only the ATTS provides sufficient temporal resolution and spatial accuracy for assessing the temporal behaviour of the landslide's movement. However, ATTS measurements are only available at the installed 53 retro-reflecting prisms. Multi-temporal TLS can provide additional insight into the spatial displacement pattern at various man-made and natural objects such as walls, fences, poles and tree stems. But the respective accuracy and data acquisition intervals do not allow to draw conclusions about the temporal dynamics of the landslide's movement. Results of the InSAR technique based on Sentinel-1 imagery show good agreement with ATTS measurements, but cannot provide real-time information on the landslide's acceleration and deceleration phases. However, in combination, the measurement techniques provide vital information in both the spatial and temporal domain.@en

Nowcasting and early warning systems for landslide hazards have been implemented mostly at the slope or catchment scale. These systems are often difficult to implement at regional scale or in remote areas. Machine Learning and satellite remote sensing products offer new opportunities for both local and regional monitoring of deep-seated landslide deformation and associated processes. Here, we list the key variables of the landslide process and the associated satellite remote sensing products, as well as the available machine learning algorithms and their current use in the field. Furthermore, we discuss both the challenges for the integration in an early warning system, and the risks and opportunities arising from the limited physical constraints in machine learning. This review shows that data products and algorithms are available, and that the technology is ready to be tested for regional applications.@en