Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: application to the 2009 storm event in Messina (Sicily, southern Italy)

Risultato della ricerca: Article

63 Citazioni (Scopus)

Abstract

This study aims to compare binary logistic regression (BLR) and stochastic gradient treeboost (SGT) methods in assessing landslide susceptibility within the Mediterranean region for multiple-occurrence regional landslide events. A test area was selected in the north-eastern sector of Sicily (southern Italy) where thousands of debris flows and debris avalanches triggered on the first October 2009 due to an extreme storm. Exploiting the same set of predictors and the 2009 event landslide archive, BLR- and SGT-based susceptibility models have been obtained for the two catchments separately, adopting a random partition (RP) technique for validation. In addition, the models trained in one catchment have been tested in predicting the landslide distribution in the second, adopting a spatial partition (SP)-based validation. The models produced high predictive performances with a general consistency between BLR and SGT in the susceptibility maps, predictor importance and role. In particular, SGT models reached a higher prediction performance with respect to BLR models for RP-modelling, while for the SP-based models, the difference in predictive skills dropped, converging to equally excellent performances. However, analysing the precision of the probability estimates, BLR produced more robust models around the mean value for each pixel, indicating possible overfitting effects, which affect decision trees to a greater extent. The assessment of the predictor roles allowed identifying the activation mechanisms which are primarily controlled by steep south-facing open slopes located near the coastal area. These slopes are characterised by low/middle altitude downhill from mountain tops, having a medium-grade metamorphic bedrock, under grassland and cultivated (terraced) uses.
Lingua originaleEnglish
pagine (da-a)1621-1648
Numero di pagine28
RivistaNatural Hazards
Volume79
Stato di pubblicazionePublished - 2015

Fingerprint

landslide
logistics
catchment
debris avalanche
decision
debris flow
bedrock
pixel
grassland
mountain
prediction
modeling

All Science Journal Classification (ASJC) codes

  • Water Science and Technology
  • Atmospheric Science
  • Earth and Planetary Sciences (miscellaneous)

Cita questo

@article{4021646b1d3d49e0bc9e064e8e5e4326,
title = "Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: application to the 2009 storm event in Messina (Sicily, southern Italy)",
abstract = "This study aims to compare binary logistic regression (BLR) and stochastic gradient treeboost (SGT) methods in assessing landslide susceptibility within the Mediterranean region for multiple-occurrence regional landslide events. A test area was selected in the north-eastern sector of Sicily (southern Italy) where thousands of debris flows and debris avalanches triggered on the first October 2009 due to an extreme storm. Exploiting the same set of predictors and the 2009 event landslide archive, BLR- and SGT-based susceptibility models have been obtained for the two catchments separately, adopting a random partition (RP) technique for validation. In addition, the models trained in one catchment have been tested in predicting the landslide distribution in the second, adopting a spatial partition (SP)-based validation. The models produced high predictive performances with a general consistency between BLR and SGT in the susceptibility maps, predictor importance and role. In particular, SGT models reached a higher prediction performance with respect to BLR models for RP-modelling, while for the SP-based models, the difference in predictive skills dropped, converging to equally excellent performances. However, analysing the precision of the probability estimates, BLR produced more robust models around the mean value for each pixel, indicating possible overfitting effects, which affect decision trees to a greater extent. The assessment of the predictor roles allowed identifying the activation mechanisms which are primarily controlled by steep south-facing open slopes located near the coastal area. These slopes are characterised by low/middle altitude downhill from mountain tops, having a medium-grade metamorphic bedrock, under grassland and cultivated (terraced) uses.",
keywords = "Atmospheric Science, Earth and Planetary Sciences (miscellaneous), Forward logistic regression, Landslide susceptibility, Messina 2009 disaster, Prediction spatial transferability, Sicily, Stochastic gradient treeboost, Water Science and Technology",
author = "Edoardo Rotigliano and Luigi Lombardo and Christian Conoscenti and Mariaelena Cama and Lombardo and Michael M{\"a}rker",
year = "2015",
language = "English",
volume = "79",
pages = "1621--1648",
journal = "Natural Hazards",
issn = "0921-030X",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: application to the 2009 storm event in Messina (Sicily, southern Italy)

AU - Rotigliano, Edoardo

AU - Lombardo, Luigi

AU - Conoscenti, Christian

AU - Cama, Mariaelena

AU - Lombardo, null

AU - Märker, Michael

PY - 2015

Y1 - 2015

N2 - This study aims to compare binary logistic regression (BLR) and stochastic gradient treeboost (SGT) methods in assessing landslide susceptibility within the Mediterranean region for multiple-occurrence regional landslide events. A test area was selected in the north-eastern sector of Sicily (southern Italy) where thousands of debris flows and debris avalanches triggered on the first October 2009 due to an extreme storm. Exploiting the same set of predictors and the 2009 event landslide archive, BLR- and SGT-based susceptibility models have been obtained for the two catchments separately, adopting a random partition (RP) technique for validation. In addition, the models trained in one catchment have been tested in predicting the landslide distribution in the second, adopting a spatial partition (SP)-based validation. The models produced high predictive performances with a general consistency between BLR and SGT in the susceptibility maps, predictor importance and role. In particular, SGT models reached a higher prediction performance with respect to BLR models for RP-modelling, while for the SP-based models, the difference in predictive skills dropped, converging to equally excellent performances. However, analysing the precision of the probability estimates, BLR produced more robust models around the mean value for each pixel, indicating possible overfitting effects, which affect decision trees to a greater extent. The assessment of the predictor roles allowed identifying the activation mechanisms which are primarily controlled by steep south-facing open slopes located near the coastal area. These slopes are characterised by low/middle altitude downhill from mountain tops, having a medium-grade metamorphic bedrock, under grassland and cultivated (terraced) uses.

AB - This study aims to compare binary logistic regression (BLR) and stochastic gradient treeboost (SGT) methods in assessing landslide susceptibility within the Mediterranean region for multiple-occurrence regional landslide events. A test area was selected in the north-eastern sector of Sicily (southern Italy) where thousands of debris flows and debris avalanches triggered on the first October 2009 due to an extreme storm. Exploiting the same set of predictors and the 2009 event landslide archive, BLR- and SGT-based susceptibility models have been obtained for the two catchments separately, adopting a random partition (RP) technique for validation. In addition, the models trained in one catchment have been tested in predicting the landslide distribution in the second, adopting a spatial partition (SP)-based validation. The models produced high predictive performances with a general consistency between BLR and SGT in the susceptibility maps, predictor importance and role. In particular, SGT models reached a higher prediction performance with respect to BLR models for RP-modelling, while for the SP-based models, the difference in predictive skills dropped, converging to equally excellent performances. However, analysing the precision of the probability estimates, BLR produced more robust models around the mean value for each pixel, indicating possible overfitting effects, which affect decision trees to a greater extent. The assessment of the predictor roles allowed identifying the activation mechanisms which are primarily controlled by steep south-facing open slopes located near the coastal area. These slopes are characterised by low/middle altitude downhill from mountain tops, having a medium-grade metamorphic bedrock, under grassland and cultivated (terraced) uses.

KW - Atmospheric Science

KW - Earth and Planetary Sciences (miscellaneous)

KW - Forward logistic regression

KW - Landslide susceptibility

KW - Messina 2009 disaster

KW - Prediction spatial transferability

KW - Sicily

KW - Stochastic gradient treeboost

KW - Water Science and Technology

UR - http://hdl.handle.net/10447/200989

UR - http://www.wkap.nl/journalhome.htm/0921-030X

M3 - Article

VL - 79

SP - 1621

EP - 1648

JO - Natural Hazards

JF - Natural Hazards

SN - 0921-030X

ER -