Search

Transferability of knowledge from well-investigated areas to a new study region is gaining importance in landslide hazard research. Considering the time-consuming compilation of landslide inventories as a prerequisite for landslide susceptibility mapping, model transferability can be key to making hazard-related information available to stakeholders in a timely manner. In this paper, we compare and combine two important transfer-learning strategies for landslide susceptibility modeling: case-based reasoning (CBR) and domain adaptation (DA). Care-based reasoning gathers knowledge from previous similar situations (source areas) and applies it to solve a new problem (target area). Domain adaptation, which is widely used in computer vision, selects data from a source area that has a similar distribution to the target area. We assess the performances of single- and multiple-source CBR, DA, and CBR–DA strategies to train and combine landslide susceptibility models using generalized additive models (GAMs) for 10 study areas with various resolutions (1, 10, and 25 m) located in Austria, Ecuador, and Italy. The performance evaluation shows that CBR and combined CBR–DA based on our proposed similarity criterion were able to achieve performances comparable to benchmark models trained in the target area itself. Particularly the CBR strategies yielded favorable results in both single- and multi-source strategies. Although DA tended to have overall lower performances than CBR, it had promising results in scenarios where the source–target similarity was low. We recommend that future transfer-learning research for landslide susceptibility modeling can build on the similarity criterion we used, as it successfully helped to transfer landslide susceptibility models by identifying suitable source regions for model training. [ABSTRACT FROM AUTHOR]

In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important, as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (frequency ratio and evidence belief function) and two machine learning (ML) models (random forest and XGBoost; eXtreme Gradient Boosting) for LSM in the province of Belluno (region of Veneto, northeastern Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least "important" features by using a common threshold of 0.30 for statistical and 0.03 for ML algorithms. Conclusively, we found that removing the least important features does not impact the overall accuracy of LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least important ones, namely the aspect plan and profile curvature, topographic wetness index (TWI), topographic roughness index (TRI), and normalized difference vegetation index (NDVI) in the case of the statistical model and the plan and profile curvature, TWI, and topographic position index (TPI) for ML algorithms. This confirms that the requirement for the important conditioning factor maps can be assessed based on the physiography of the region. [ABSTRACT FROM AUTHOR]

Transferability of knowledge from well-investigated areas to a new study region is gaining importance in landslide hazard research. Considering the time-consuming compilation of landslide inventories as a prerequisite for landslide susceptibility mapping, model transferability can be key to making hazard-related information available to stakeholders in a timely manner. In this paper, we compare and combine two important transfer-learning strategies for landslide susceptibility modelling: case-based reasoning (CBR) and domain adaptation (DA). CBR gathers knowledge from previous similar situations (source areas) and applies it to solve a new problem (target area). DA, which is widely used in computer vision, selects data from a source area that has a similar distribution to the target area. We assess the performances of single- and multiple-source CBR, DA and CBR-DA strategies to train and combine landslide susceptibility models using generalized additive models (GAMs) for 10 study areas with various resolutions (1 m, 10 m and 25 m) located in Austria, Ecuador, and Italy. The performance evaluation shows that CBR and combined CBR-DA based on our proposed similarity criterion was able to achieve performances comparable to benchmark models trained in the target area itself. Particularly the CBR strategies yielded favourable results in both single- and multi-source strategies. DA tended to have overall lower performances than CBR; yet, it had promising results in scenarios when the source-target similarity was low. We recommend that future transfer learning research for landslide susceptibility modelling can build on the similarity criterion we used, as it successfully helped to achieve landslide susceptibility model transfers by discovering suitable training datasets from various regions. [ABSTRACT FROM AUTHOR]

In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (Frequency Ratio and Evidence Belief Function) and two machine learning (ML) models (Random Forest and XG-Boost) for LSM in the Belluno province (Veneto Region, NE Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors (features) in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least "important" features by using a common threshold. Conclusively, we found that removing the least "important" features does not impact the overall accuracy of the LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least "important" ones. This confirms that the requirement for the important factor maps can be assessed based on the physiography of the region. Based on the analysis of the three models, it was observed that most commonly available feature data can be useful for carrying out LSM at regional scale, eliminating the least available ones in most of the use cases due to data scarcity. Identifying LSMs at regional scale has implications for understanding landslide phenomena in the region and post-event relief measures, planning disaster risk reduction, mitigation, and evaluating potentially affected areas. [ABSTRACT FROM AUTHOR]

Shallow slopes in clayey colluvial covers are often involved in progressive downhill motion with discontinuous rate of movements, depending on fluctuations in pore-water pressure. In geotechnical engineering research on natural slopes, the main efforts have been concentrated on stability analysis, always with a rigid perfectly plastic body assumption. In case of slow slope movements, however, the notion of stability losses its sense, so the main question is not to evaluate a stability factor, but to model a velocity field and to define the kinematic and dynamic features of the movement (mobility analysis). Many authors, in their researches, deal with slow slope movements and for the complexity of the problem and the great number of parameters involved they agree about applying numerical techniques (FEM, FDM) and advanced material modelling (elastoviscoplasticity) and suggest to calibrate the involved parameters values with the help of "back analyses" of existing case histories. In this paper a mathematical model predicting the landslide body viscous deformations, is presented. The model has been implemented in a computer FDM code, and has been tested on some well known case histories. Here it is applied to the case of a landslide occurred at Gagliano Castelferrato (Sicily -- Italy), where a great number of field measurements was available. [ABSTRACT FROM AUTHOR]

On 10 March 2010, because of the heavy rainfall in the preceding days, the Montaguto landslide (Southern Italy) reactivated, affecting both state road 90 "Delle Puglie" and the Rome-Bari railway. A similar event occurred on May 2005 and on September 2009. As a result, the National Civil Protection Department (DPC) started an accurate monitoring and analysis program. A monitoring project using the GB-InSAR (ground-based interferometric synthetic aperture radar) system was emplaced to investigate the landslide kinematics, plan urgent safety measures for risk mitigation and design long-term stabilization work. Here, we present the GB-InSAR monitoring system results and its applications in the observational method (OM) approach. GB-InSAR is an established instrument for longterm campaigns aimed at early warning and monitoring during construction works. Our paper further develops these aspects in that it highlights how the OM based on the GBInSAR technique can produce savings in terms of cost and time in engineering projects without compromising safety. This study focuses on the key role played by the monitoring activities during the design and planning activities, with special reference to the emergency phase. [ABSTRACT FROM AUTHOR]

This study presents a landslide susceptibility map using an artificial intelligence (AI) approach based on standards set by the INSPIRE (Infrastructure for Spatial Information in the European Community) framework. INSPIRE is a European Union spatial data infrastructure (SDI) initiative to standardize spatial data across borders to ensure interoperability for management of cross-border infrastructure and environmental issues. However, despite the theoretical effectiveness of the SDI, few real-world applications make use of INSPIRE standards. In this study, we show how INSPIRE standards enhance the interoperability of geospatial data and enable deeper knowledge development for their interpretation and explainability in AI applications. We designed an ontology of landslides, embedded with INSPIRE vocabularies, and then aligned geology, stream network, and land cover datasets covering the Veneto region of Italy to the standards. INSPIRE was formally extended to include an extensive landslide type code list, a landslide size code list, and the concept of landslide susceptibility to describe map application inputs and outputs. Using the terms in the ontology, we defined conceptual scientific models of areas likely to generate different types of landslides as well as map polygons representing the land surface. Both landslide models and map polygons were encoded as semantic networks and, by qualitative probabilistic comparison between the two, a similarity score was assigned. The score was then used as a proxy for landslide susceptibility and displayed in a web map application. The use of INSPIRE-standardized vocabularies in ontologies that express scientific models promotes the adoption of the standards across the European Union and globally. Further, this application facilitates the explanation of the generated results. We conclude that public and private organizations, within and outside the European Union, can enhance the value of their data by making them INSPIRE-compliant for use in AI applications. [ABSTRACT FROM AUTHOR]

This study assesses the usability of Weather Research and Forecasting (WRF) model simulated soil moisture for landslide monitoring in the Emilia Romagna region, northern Italy, during the 10-year period between 2006 and 2015. In particular, three advanced land surface model (LSM) schemes (i.e. Noah, Noah-MP, and CLM4) integrated with the WRF are used to provide detailed multi-layer soil moisture information. Through the temporal evaluation with the single-point in situ soil moisture observations, Noah-MP is the only scheme that is able to simulate the large soil drying phenomenon close to the observations during the dry season, and it also has the highest correlation coefficient and the lowest RMSE at most soil layers. It is also demonstrated that a single soil moisture sensor located in a plain area has a high correlation with a significant proportion of the study area (even in the mountainous region 141 km away, based on the WRF-simulated spatial soil moisture information). The evaluation of the WRF rainfall estimation shows there is no distinct difference among the three LSMs, and their performances are in line with a published study for the central USA. Each simulated soil moisture product from the three LSM schemes is then used to build a landslide prediction model, and within each model, 17 different exceedance probability levels from 1 % to 50 % are adopted to determine the optimal threshold scenario (in total there are 612 scenarios). Slope degree information is also used to separate the study region into different groups. The threshold evaluation performance is based on the landslide forecasting accuracy using 45 selected rainfall events between 2014 and 2015. Contingency tables, statistical indicators, and receiver operating characteristic analysis for different threshold scenarios are explored. The results have shown that, for landslide monitoring, Noah-MP at the surface soil layer with 30 % exceedance probability provides the best landslide monitoring performance, with its hit rate at 0.769 and its false alarm rate at 0.289. [ABSTRACT FROM AUTHOR]

In 1851, the region of Sicily experienced many rainstorm-induced landslides. On 13 March 1851, a rainstorm brought about a severe rockfall disaster near the small town of Sclafani (Madonie Mountains, northern-central Sicily, Italy). Rocks detached from the carbonate crest of Mt Sclafani (813m above sea level) and fell downslope, causing the collapse of the ancient hydrothermal spa (about 430m above sea level) and burying it. Fortunately, there were no injuries or victims. Given its geological, geomorphological and tectonic features, the calcareous-dolomitic and carbonate- siliciclastic relief of Mt Sclafani is extremely prone to landsliding. This study combines the findings of detailed geological and geomorphological field surveys and of a critical review of documentary data. A thorough analysis of documentary sources and historical maps made it possible to identify the location (previously unknown) of the ancient spa. The rockfall dynamics was reconstructed by comparing field reconnaissance data and documentary sources. The 1851 event reconstruction is an example of the application of an integrated methodological approach, which can yield a propaedeutic, yet meaningful picture of a natural disaster, paving the way for further research (e.g. slope failure susceptibility, future land-use planning, protection of thermal springs and mitigation of the impact of similar disasters in this area). Indeed, the intensification of extreme weather events, caused by global warming induced by climate change, has increased the risk of recurrence of a catastrophic event, like that of the ancient Sclafani spa, which is always a potential threat. [ABSTRACT FROM AUTHOR]

In the last years a research project aimed at the assessment of the landslide hazard and susceptibility in the high Cordevole river basin (Eastern Dolomites, Italy) have been carried out. The hazard map was made adopting the Swiss Confederation semi-deterministic approach that takes into account parameters such as velocity, geometry and frequency of landslides. Usually these parameters are collected by means of geological and morphological surveys, historical archive researches, aerophotogrammetric analysis etc. In this framework however the dynamics of an instable slope can be difficult to determine. This work aims at illustrating some progress in landslide hazard assessment using a modified version of the Swiss Confederation semi-deterministic approach in which the values of some parameters have been refined in order to accomplish more reliable results in hazard assessment. A validation of the accuracy of these new values, using GPS and inclinometric measurements, has been carried out on a test site located inside the high Cordevole river basin. [ABSTRACT FROM AUTHOR]

We present the results of the application of a recently proposed model to determine landslide hazard. The model predicts where landslides will occur, how frequently they will occur, and how large they will be in a given area. For the Collazzone area, in the central Italian Apennines, we prepared a multi-temporal inventory map through the interpretation of multiple sets of aerial photographs taken between 1941 and 1997 and field surveys conducted in the period between 1998 and 2004. We then partitioned the 79 square kilometres study area into 894 slope units, and obtained the probability of spatial occurrence of landslides by discriminant analysis of thematic variables, including morphology, lithology, structure and land use. For each slope unit, we computed the expected landslide recurrence by dividing the total number of landslide events inventoried in the terrain unit by the time span of the investigated period. Assuming landslide recurrence was constant, and adopting a Poisson probability model, we determined the exceedance probability of having one or more landslides in each slope unit, for different periods. We obtained the probability of landslide size, a proxy for landslide magnitude, by analysing the frequency-area statistics of landslides, obtained from the multi-temporal inventory map. Lastly, assuming independence, we determined landslide hazard for each slope unit as the joint probability of landslide size, of landslide temporal occurrence, and of landslide spatial occurrence. [ABSTRACT FROM AUTHOR]