Vergleich von SVM und Boosted Regression Trees zur Abgrenzung von lakustrinen Sedimenten anhand von multispektralen ASTER Daten und topographischen Parametern im Einzugsgebiet des Manyara Sees

Bachofer, Felix; Quénéhervé, Geraldine; Maerker, Michael; Hochschild, Volker

doi:10.1127/pfg/2015/0251

Cited by 13 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose to exploit the spectral capabilities and spatial coverage of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite images, in order to calculate spatially distributed vegetation and mineral indices Yamaguchi and Naito, 2003;Mars and Rowan, 2010;Pour et al, 2011;Mulder et al, 2011;Bachofer et al, 2015a) to be included, together with DEM-derived topographic covariates and CORINE land cover data, into the set of predictors for landslide susceptibility purposes.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north‐eastern Sicily, Italy)

Lombardo

Bachofer

Cama

et al. 2016

Earth Surf Processes Landf

Self Cite

View full text Add to dashboard Cite

This study aims at evaluating the performance of the Maximum Entropy method in assessing landslide susceptibility, exploiting topographic and multispectral remote sensing predictors. We selected the catchment of the Giampilieri stream, which is located in the north‐eastern sector of Sicily (southern Italy), as test site. On 1 October 2009, a storm rainfall triggered in this area hundreds of debris flow/avalanche phenomena causing extensive economical damage and loss of life. Within this area a presence‐only‐based statistical method was applied to obtain susceptibility models capable of distinguishing future activation sites of debris flow and debris slide, which where the main source of failure mechanisms for flow or avalanche type propagation. The set of predictors used in this experiment comprised primary and secondary topographic attributes, derived by processing a high resolution digital elevation model, CORINE land cover data and a set of vegetation and mineral indices obtained by processing multispectral ASTER images. All the selected data sources are dated before the disaster. A spatially random partition technique was adopted for validation, generating 50 replicates for each of the two considered movement typologies in order to assess accuracy, precision and reliability of the models. The debris slide and debris flow susceptibility models produced high performances with the first type being the best fit. The evaluation of the probability estimates around the mean value for each mapped pixel shows an inverted relation, with the most robust models corresponding to the debris flows. With respect to the role of each predictor within the modelling phase, debris flows appeared to be primarily controlled by topographic attributes whilst the debris slides were better explained by remotely sensed derived indices, particularly by the occurrence of previous wildfires across the slope. The overall excellent performances of the two models suggest promising perspectives for the application of presence‐only methods and remote sensing derived predictors. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north‐eastern Sicily, Italy)

Lombardo

Bachofer

Cama

et al. 2016

Earth Surf Processes Landf

Self Cite

View full text Add to dashboard Cite

show abstract

“…8 the village of Makuyuni the so-called Manyara Beds are well exposed due to the incision of the Makuyuni River and gully erosion (Bachofer et al, 2015). They are divided in two sections: the Lower Members which are formed of lacustrine facies from the former paleolake Manyara (> 0.633 Ma) and the Upper Members formed by floodplain, channel and debris flow facies (Ring et al, 2005;Frost et al, 2012).…”

Section: Accepted Manuscriptmentioning

confidence: 97%

Morphotectonic interpretation of the Makuyuni catchment in Northern Tanzania using DEM and SAR data

et al. 2015

Self Cite

View full text Add to dashboard Cite

“…The SVM approach is implemented in R (R Core Team, 2018), within the e1071 package (Meyer et al, 2019). For further reading of the supervised classification approach based on SVMs, see Vapnik (1995Vapnik ( , 1999 or Bachofer et al (2015). For the SVM the same dataset divided into a 75% training dataset and a 25% test dataset was used.…”

Section: Modellingmentioning

confidence: 99%

Assessment of calanchi and rill–interrill erosion susceptibilities using terrain analysis and geostochastics: A case study in the Oltrepo Pavese, Northern Apennines, Italy

Bosino

Giordani

Quénéhervé

et al. 2020

Earth Surf Processes Landf

Self Cite

View full text Add to dashboard Cite

Soil erosion is one of the most important environmental problems distributed worldwide. In the last decades, numerous studies have been published on the assessment of soil erosion and the related processes and forms using empirical, conceptual and physically based models. For the prediction of the spatial distribution, more and more sophisticated stochastic modelling approaches have been proposed – especially on smaller spatial scales such as river basins. In this work, we apply a maximum entropy model (MaxEnt) to evaluate badlands (calanchi) and rill–interrill (sheet erosion) areas in the Oltrepo Pavese (Northern Apennines, Italy). The aim of the work is to assess the important environmental predictors that influence calanchi and rill–interrill erosion at the regional scale. We used 13 topographic parameters derived from a 12 m digital elevation model (TanDEM‐X) and data on the lithology and land use. Additional information about the vegetation is introduced through the normalized difference vegetation index based on remotely sensed data (ASTER images). The results are presented in the form of susceptibility maps showing the spatial distribution of the occurrence probability for calanchi and rill–interrill erosion. For the validation of the MaxEnt model results, a support vector machine approach was applied. The models show reliable results and highlight several locations of the study area that are potentially prone to future soil erosion. Thus, coping and mitigation strategies may be developed to prevent or fight the soil erosion phenomenon under consideration. © 2020 John Wiley & Sons, Ltd.

show abstract

Vergleich von SVM und Boosted Regression Trees zur Abgrenzung von lakustrinen Sedimenten anhand von multispektralen ASTER Daten und topographischen Parametern im Einzugsgebiet des Manyara Sees

Cited by 13 publications

References 24 publications

Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north‐eastern Sicily, Italy)

Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north‐eastern Sicily, Italy)

Morphotectonic interpretation of the Makuyuni catchment in Northern Tanzania using DEM and SAR data

Assessment of calanchi and rill–interrill erosion susceptibilities using terrain analysis and geostochastics: A case study in the Oltrepo Pavese, Northern Apennines, Italy

Contact Info

Product

Resources

About