Development of a data-driven model for spatial and temporal shallow landslide probability of occurrence at catchment scale

AbstractA combined method was developed to forecast the spatial and the temporal probability of occurrence of rainfall-induced shallow landslides over large areas. The method also allowed to estimate the dynamic change of this probability during a rainfall event. The model, developed through a data-driven approach basing on Multivariate Adaptive Regression Splines technique, was based on a joint probability between the spatial probability of occurrence (susceptibility) and the temporal one. The former was estimated on the basis of geological, geomorphological, and hydrological predictors. The latter was assessed considering short-term cumulative rainfall, antecedent rainfall, soil hydrological conditions, expressed as soil saturation degree, and bedrock geology. The predictive capability of the methodology was tested for past triggering events of shallow landslides occurred in representative catchments of Oltrepò Pavese, in northern Italian Apennines. The method provided excellently to outstanding performance for both the really unstable hillslopes (area under ROC curve until 0.92, true positives until 98.8%, true negatives higher than 80%) and the identification of the triggering time (area under ROC curve of 0.98, true positives of 96.2%, true negatives of 94.6%). The developed methodology allowed us to obtain feasible results using satellite-based rainfall products and data acquired by field rain gauges. Advantages and weak points of the method, in comparison also with traditional approaches for the forecast of shallow landslides, were also provided.

Download Full-text

A data-drive model for the assessment of shallow landslides hazard with the integration of satellite soil moisture and rainfall data

10.5194/egusphere-egu2020-22240 ◽

2020 ◽

Author(s):

Valerio Vivaldi ◽

Massimiliano Bordoni ◽

Luca Lucchelli ◽

Beatrice Corradini ◽

Luca Brocca ◽

...

Keyword(s):

Soil Moisture ◽

Methodological Approach ◽

Return Time ◽

Shallow Landslides ◽

Predisposing Factors ◽

Data Driven ◽

Probability Of Occurrence ◽

Triggering Factors ◽

Triggering Events ◽

Spatio Temporal

Rainfall-induced shallow landslides are very dangerous phenomena, widespread all over the world, which could provoke significant damages to buildings, roads, facilities, cultivations and, sometimes, loss of human lives. For these reasons, it is necessary assessing the most prone zones in a territory which is particularly susceptible to these phenomena and the frequency of the triggering events, according to the return time of them, which generally correspond to intense and concentrated rainfalls. The most adopted methodologies for the determination of the susceptibility and hazard of a territory are physically-based models, that quantify the hydrological and the mechanical responses of the slopes according to particular rainfall scenarios. Whereas, these methodologies could be applied in a reliable way in little catchments, where geotechnical and hydrological features of the materials affected by shallow failures are homogeneous. Data-driven models could constraints these, even if they are generally built up taking into only the predisposing factors of shallow instabilities, allowing to estimate only the susceptibility of a territory, without considering the frequency of the triggering events. It is then required to consider also triggering factors of shallow landslides to allow these methods to estimate also the probability of occurrence and, then, the hazard. This work presents the development and the implementation of data-driven model able to assses the spatio-temporal probability of occurrence of shallow landslides in large areas by means of a data-driven technique. The model is based on Multivariate Adaptive Regression Technique (MARS), that links geomorphological, hydrological, geological and land use predisposing factors to triggering factors of shallow failures. These triggering factors correspond to&#160;soil saturation degree and rainfall amounts, which are available for entire a study area thanks to satellite measures. The methodological approach is testing in 30-40 km2 wide catchments of Oltrep&#242; Pavese hilly area (northern Italy), where detailed inventories of shallow landslides occurred during past triggering events and corresponding satellite soil moisture and rainfall maps are available. This work was made in the frame of the ANDROMEDA project, funded by Fondazione Cariplo.

Download Full-text

Modelling catchment-scale shallow landslide occurrence by means of a subsurface flow path connectivity index

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-9-4101-2012 ◽

2012 ◽

Vol 9 (3) ◽

pp. 4101-4134 ◽

Cited By ~ 3

Author(s):

C. Lanni ◽

M. Borga ◽

R. Rigon ◽

P. Tarolli

Keyword(s):

Water Table ◽

Hydrological Model ◽

Shallow Landslide ◽

Shallow Landslides ◽

Lateral Flow ◽

Necessary Condition ◽

Hydrological Connectivity ◽

Catchment Scale ◽

Topographic Index ◽

Infinite Slope Stability Model

Abstract. Topographic index-based hydrological models have gained wide use to describe the hydrological control on the triggering of rainfall-induced shallow landslides at the catchment scale. A common assumption in these models is that a spatially continuous water table occurs simultaneously at any point across the catchment. However, during a rainfall event isolated patches of subsurface saturation form above an impeding layer and hydrological connectivity of these patches is a necessary condition for lateral flow initiation at a point on the hillslope. Here, a new hydrological model is presented, which allows to account for the concept of hydrological connectivity while keeping the simplicity of the topographic index approach. A dynamic topographic index is used to describe the transient lateral flow that is established at a hillslope element when the rainfall amount exceeds a threshold value allowing for (a) development of a perched water table above an impeding layer, (b) hydrological connectivity between the hillslope element and its own upslope contributing area. A spatially variable soil depth is the main control of hydrological connectivity in the model. The hydrological model is coupled with the infinite slope stability model, and with a scaling model for the rainfall frequency-duration relationship to determine the return period of the critical rainfall needed to cause instability on three catchments located in the Italian Alps. The results show the good ability of our model in predicting observed shallow landslides. The model is finally used to determine local rainfall intensity-duration thresholds that may lead to shallow landslide initiation.

Download Full-text

Using satellite soil moisture and rainfall data for the monitoring and the prediction of natural hazards

10.5194/egusphere-egu21-14812 ◽

2021 ◽

Author(s):

Valerio Vivaldi ◽

Massimiliano Bordoni ◽

Luca Brocca ◽

Luca Ciabatta ◽

Claudia Meisina

Keyword(s):

Methodological Approach ◽

Shallow Landslides ◽

Predisposing Factors ◽

Data Driven ◽

Probability Of Occurrence ◽

Mechanical Responses ◽

Triggering Factors ◽

Physically Based ◽

Adaptive Regression ◽

Spatio Temporal

Rainfall-induced shallow landslides affect buildings, roads, facilities, cultivations, causing several damages and, sometimes, loss of human lives. It is necessary assessing the most prone zones in a territory where these phenomena could occur and the triggering conditions of these events, which generally correspond to intense and concentrated rainfalls. The most adopted methodologies for the determination of the spatial and temporal probability of occurrence are physically-based models, that quantify the hydrological and the mechanical responses of the slopes according to particular rainfall scenarios. Whereas, they are limited to be applied in a reliable way in little catchments, where geotechnical and hydrological characteristics of the materials are homogeneous. Data-driven models could constraints these, when the predisposing factors of shallow instabilities, allowing to estimate only the susceptibility of a territory, are combined with triggering factors of shallow landslides to allow these methods to estimate also the probability of occurrence and, then, the hazard. This work presents the implementation of a data-driven model able to assses the spatio-temporal probability of occurrence of shallow landslides in large areas by means of a data-driven techniques. The models are based on Multivariate Adaptive Regression Technique (MARS), that links geomorphological, hydrological, geological and land use predisposing factors to triggering factors of shallow failures. These triggering factors correspond to soil saturation degree and rainfall amounts, which are available thanks to satellite measures (ASCAT and GPM). The methodological approach is testing in different catchments of Oltrep&#242; Pavese hilly area (northern Italy), that is representative of Italian Apeninnes environment. This work was made in the frame of the project ANDROMEDA, funded by Fondazione Cariplo.

Download Full-text

Regional-scale susceptibility modelling of shallow landslides involving the weathered and fractured sub-surface bedrock

10.5194/egusphere-egu21-13474 ◽

2021 ◽

Author(s):

Enrico D'Addario ◽

Leonardo Disperati ◽

Josè Luis Zezerè ◽

Raquel Melo ◽

Sergio Cruz Oliveira

Keyword(s):

Slope Failure ◽

Regional Scale ◽

Shallow Landslide ◽

Shallow Landslides ◽

Data Driven ◽

Field Observations ◽

Rupture Surface ◽

Slope Deposits ◽

Physically Based ◽

Engineering Geological Properties

Landsliding is a complex phenomenon and its modelling aimed at predicting where the processes are most likely to occur is a tricky issue to be performed. Apart the chosen modelling approach, for both data-driven and physically-based models, paying adequate attention to the predisposing and triggering factors, as well as the input parameters is no less important. Generally, shallow landslides mobilize relatively small volumes of material sliding along a nearly planar rupture surface which is assumed to be roughly parallel to the ground surface. In the literature it is also widely accepted that shallow landslides involve only unconsolidated slope deposits (i.e., the colluvium), then the rupture surface corresponds to the discontinuity between the bedrock and the overlying loose soil. In this work, based on systematic field observations, we highlight that shallow landslides often involve also portions of the sub-surface bedrock showing different levels of weathering and fracturing. Then, we show that the engineering geological properties of slope deposits, as well as those related to the underlying bedrock, must be considered to obtain more reliable shallow landslides susceptibility assessment. As a first task, a multi-temporal shallow landslide inventory was built by photointerpretation of aerial orthoimages. Then, a new fieldwork-based method is proposed and implemented to acquire, process and spatialize the engineering geological properties of both slope deposits and bedrock. To support the regional scale approach, field observations were collected within, in the neighbour and far from the shallow landslide areas. Finally, both physically-based and data-driven methods were implemented to assess and compare shallow landslide susceptibility at regional scale, as well as to analyse the role of spatial distribution of rock mass quality for shallow slope failure development. The results highlight that, according to geology, structural setting and morphometric conditions, bedrock properties spatially change, defining clusters influencing both the distribution and characters of shallow landslides. As a consequence, the physically-based modelling provides better prediction accuracy when two possible rupture surfaces are analysed, the shallower one located at the slope deposit / bedrock discontinuity, and the deeper one located at the bottom of the fractured and weathered bedrock horizon. Even though the physically-based and data-driven models provide similar results in terms of ROC curves, the resulting susceptibility maps highlight quite substantial differences.

Download Full-text

Shallow landslide prediction in the Serra do Mar, São Paulo, Brazil

Natural Hazards and Earth System Science ◽

10.5194/nhess-10-1829-2010 ◽

2010 ◽

Vol 10 (9) ◽

pp. 1829-1837 ◽

Cited By ~ 45

Author(s):

B. C. Vieira ◽

N. F. Fernandes ◽

O. A. Filho

Keyword(s):

Sao Paulo ◽

Shallow Landslide ◽

Shallow Landslides ◽

Southeastern Brazil ◽

Mountain Range ◽

São Paulo ◽

Catchment Scale ◽

Landslide Prediction ◽

Serra Do Mar ◽

Number Of Cells

Abstract. Various methods are currently used in order to predict shallow landslides within the catchment scale. Among them, physically based models present advantages associated with the physical description of processes by means of mathematical equations. The main objective of this research is the prediction of shallow landslides using TRIGRS model, in a pilot catchment located at Serra do Mar mountain range, São Paulo State, southeastern Brazil. Susceptibility scenarios have been simulated taking into account different mechanical and hydrological values. These scenarios were analysed based on a landslide scars map from the January 1985 event, upon which two indexes were applied: Scars Concentration (SC – ratio between the number of cells with scars, in each class, and the total number of cells with scars within the catchment) and Landslide Potential (LP – ratio between the number of cells with scars, in each class, and the total number of cells in that same class). The results showed a significant agreement between the simulated scenarios and the scar's map. In unstable areas (SF≤1), the SC values exceeded 50% in all scenarios. Based on the results, the use of this model should be considered an important tool for shallow landslide prediction, especially in areas where mechanical and hydrological properties of the materials are not well known.

Download Full-text

A Data-Driven Method for the Temporal Estimation of Soil Water Potential and Its Application for Shallow Landslides Prediction

Water ◽

10.3390/w13091208 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1208

Author(s):

Massimiliano Bordoni ◽

Fabrizio Inzaghi ◽

Valerio Vivaldi ◽

Roberto Valentino ◽

Marco Bittelli ◽

...

Keyword(s):

Machine Learning ◽

Water Potential ◽

Soil Water ◽

Temporal Trends ◽

Soil Water Potential ◽

Shallow Landslides ◽

Water Dynamics ◽

Data Driven ◽

Machine Learning Techniques ◽

Physically Based

Soil water potential is a key factor to study water dynamics in soil and for estimating the occurrence of natural hazards, as landslides. This parameter can be measured in field or estimated through physically-based models, limited by the availability of effective input soil properties and preliminary calibrations. Data-driven models, based on machine learning techniques, could overcome these gaps. The aim of this paper is then to develop an innovative machine learning methodology to assess soil water potential trends and to implement them in models to predict shallow landslides. Monitoring data since 2012 from test-sites slopes in Oltrepò Pavese (northern Italy) were used to build the models. Within the tested techniques, Random Forest models allowed an outstanding reconstruction of measured soil water potential temporal trends. Each model is sensitive to meteorological and hydrological characteristics according to soil depths and features. Reliability of the proposed models was confirmed by correct estimation of days when shallow landslides were triggered in the study areas in December 2020, after implementing the modeled trends on a slope stability model, and by the correct choice of physically-based rainfall thresholds. These results confirm the potential application of the developed methodology to estimate hydrological scenarios that could be used for decision-making purposes.

Download Full-text

Modelling the probability of occurrence of shallow landslides and channelized debris flows using GEOtop-FS

Hydrological Processes ◽

10.1002/hyp.6886 ◽

2008 ◽

Vol 22 (4) ◽

pp. 532-545 ◽

Cited By ~ 140

Author(s):

Silvia Simoni ◽

Fabrizio Zanotti ◽

Giacomo Bertoldi ◽

Riccardo Rigon

Keyword(s):

Debris Flows ◽

Shallow Landslides ◽

Probability Of Occurrence

Download Full-text

Combining static and dynamic environmental factors at various scales to predict shallow landsliding in South Tyrol, Italy – The Proslide project

10.5194/egusphere-egu21-15606 ◽

2021 ◽

Author(s):

Robin Kohrs ◽

 Lotte de Vugt ◽

Thomas Zieher ◽

Alice Crespi ◽

Mattia Rossi ◽

...

Keyword(s):

Regional Scale ◽

Remote Sensing Data ◽

Predisposing Factors ◽

Physical Models ◽

Data Driven ◽

Catchment Scale ◽

Heterogeneous Model ◽

South Tyrol ◽

Daily Precipitation Data ◽

Spatio Temporal

Shallow landslides in alpine environments can constitute a serious threat to the exposed elements. The spatio-temporal occurrence of such slope movements is controlled by a combination of predisposing factors (e.g. topography), preparatory factors (e.g. wet periods, snow melting) and landslide triggers (e.g. heavy precipitation events). &#160;For large study areas, landslide assessments frequently focus either on the static predisposing factors to estimate landslide susceptibility using data-driven procedures, or exclusively on the triggering events to derive empirical rainfall thresholds. For smaller areas, dynamic physical models can reasonably be parameterized to simultaneously account for static and dynamic landslide controls. &#160;The recently accepted Proslide project aims to develop and test methods with the potential to improve the predictability of landslides for the Italian province of South Tyrol. It is envisaged to account for a variety of innovative input data at multiple spatio-temporal scales. In this context, we seek to exploit remote sensing data for the spatio-temporal description of landslide controlling factors (e.g. precipitation RADAR; satellite soil moisture) and to develop models that allow an integration of heterogeneous model inputs using both, data-driven approaches (regional scale) and physically-based models (catchment scale). This contribution presents the core ideas and methodical framework behind the Proslide project and its very first results (e.g. relationships between landslide observations and gridded daily precipitation data at regional scale).&#160;

Download Full-text

Parsing Expression Grammars and Their Induction Algorithm

Applied Sciences ◽

10.3390/app10238747 ◽

2020 ◽

Vol 10 (23) ◽

pp. 8747

Author(s):

Wojciech Wieczorek ◽

Olgierd Unold ◽

Łukasz Strąk

Keyword(s):

Genetic Programming ◽

Roc Curve ◽

Classification Performance ◽

Grammatical Inference ◽

Inference Algorithm ◽

Finite Sample ◽

Induction Method ◽

Grammar Learning ◽

Area Under Roc Curve ◽

Inference Methods

Grammatical inference (GI), i.e., the task of finding a rule that lies behind given words, can be used in the analyses of amyloidogenic sequence fragments, which are essential in studies of neurodegenerative diseases. In this paper, we developed a new method that generates non-circular parsing expression grammars (PEGs) and compares it with other GI algorithms on the sequences from a real dataset. The main contribution of this paper is a genetic programming-based algorithm for the induction of parsing expression grammars from a finite sample. The induction method has been tested on a real bioinformatics dataset and its classification performance has been compared to the achievements of existing grammatical inference methods. The evaluation of the generated PEG on an amyloidogenic dataset revealed its accuracy when predicting amyloid segments. We show that the new grammatical inference algorithm achieves the best ACC (Accuracy), AUC (Area under ROC curve), and MCC (Mathew’s correlation coefficient) scores in comparison to five other automata or grammar learning methods.

Download Full-text

Neonatal Sepsis-Early detection comparing Procalcitonin and CRP as Markers and Newer Tools

International Journal of Medical and Dental Sciences ◽

10.19056/ijmdsjssmes/2016/v5i1/83574 ◽

2016 ◽

Vol 5 (1) ◽

pp. 1048

Author(s):

Altaf Ahmad Bhat ◽

Anjum Shamim ◽

Sabeeha Gul ◽

Rukaya Akther ◽

Iqra Bhat

Keyword(s):

Early Detection ◽

Roc Curve ◽

Neonatal Sepsis ◽

Individual Performance ◽

Hematological Parameter ◽

Total Leukocyte Count ◽

P Value ◽

Predictive Values ◽

Maternal Risk ◽

Area Under Roc Curve

Background:Neonatal sepsis continues to be a major cause of morbidity and mortality in India, but is treatable if diagnosis is made in time.Objectives: The present study was undertaken to evaluate and highlight the importance of procalcitonin v\s CRP in early detection of neonatal sepsis.Materials and Methods: The prospective study enrolled 150 neonates who had maternal risk factors and clinically suspected of infection (study group). Abnormal total leukocyte count, abnormal total polymorphonuclear neutrophils (PMN) count, elevated immature PMN count, elevated immature: Total (I:T) PMN ratio, platelet count ≤150,000/mm3, and pronounced degenerative or toxic changes in PMN were noted by the pathologist who were blind for the clinical status of the baby in NICU. Blood culture was taken as a gold standard for septicemia. The perinatal history, clinical profile and laboratory data were recorded and correlated in each case. Each hematological parameter was assessed for its individual performance and also with the culture-proven sepsis. Sensitivity, specificity, positive and negative predictive values (NPVs) were calculated for each parameter and for different gestational ages. P value was also calculated for different parameters.Results: Among 150 babies evaluated for sepsis in NICU over a period of one year, Procalcitonin is observed as better early marker of neonatal sepsis over and CRP:- Procalcitonin in comparison with CRP: - Sensitivity was 97% Specificity was 59% PPV was 70% and NPV was 99.9%. With area under ROC curve being 0.915(p-value of 0.02) CRP in comparison with Procalcitonin: - Sensitivity was 75% Specificity was 75% PPV was 86% and NPV was 99%. With area under ROC curve being 0.769 (p- value 0.61).Conclusion: The sensitivities of the screening test namely C-reactive protein and Procalcitonin were found to be satisfactory in identifying neonatal sepsis. Comparing to Other test procalcitonin appears to be simple and feasible diagnostic tool although costly.

Download Full-text