@Article{ZhangFLLWHQCL:2022:MoLaSu,
author = "Zhang, Tingyu Y. and Fu, Quan and Li, Chao and Liu, Fangfang and
Wang, Huanyuan and Han, Ling and Quevedo, Renata Pacheco and Chen,
Tianqing and Lei, Na",
affiliation = "{Key Laboratory of Degraded and Unused Land Consolidation
Engineering} and {Shaanxi Provincial Land Engineering Construction
Group Land Survey Planning and Design Institute Co. Ltd} and
{Shaanxi Land Engineering Construction Group Co. Ltd} and {Shaanxi
Provincial Land Engineering Construction Group Land Survey
Planning and Design Institute Co. Ltd} and {Chang’an University}
and {Chang’an University} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Key Laboratory of Degraded and Unused Land
Consolidation Engineering} and {Key Laboratory of Degraded and
Unused Land Consolidation Engineering}",
title = "Modeling landslide susceptibility using data mining techniques of
kernel logistic regression, fuzzy unordered rule induction
algorithm, SysFor and random forest",
journal = "Natural Hazards",
year = "2022",
volume = "114",
number = "3",
pages = "3327--3358",
month = "Dec.",
keywords = "Landslide susceptibility, Kernel logistic regression, Fuzzy
unordered rule induction algorithm, Systematically developed
forest of multiple trees, Random forest.",
abstract = "This paper introduces four advanced intelligent algorithms, namely
kernel logistic regression, fuzzy unordered rule induction
algorithm, systematically developed forest of multiple decision
trees and random forest (RF), to perform the landslide
susceptibility mapping in Jian'ge County, China, as well as well
study of the connection between landslide occurrence and regional
geo-environment characteristics. To start with, 262 landslide
events were determined, and the proportion of randomly generated
training data is 70%, while the proportion of randomly generated
validation data is 30%, respectively. Then, through the
comprehensive consideration of local geo-environment
characteristics and relevant studies, fifteen conditioning factors
were prepared, such as slope angle, slope aspect, altitude,
profile curvature, plan curvature, sediment transport index,
topographic wetness index, stream power index, distance to rivers,
distance to roads, distance to lineaments, soil, land use,
lithology and NDVI. Next, frequency ratio model was utilized to
identify the corresponding relations for conditioning factors and
landslides distribution. In addition, four data mining techniques
were conducted to implement the landslide susceptibility research
and generated landslide susceptibility maps. In order to examine
and compare model performance, receiver operating characteristic
curve was brought for judging accuracy of those four models.
Finally, the results indicated that a traditional model, namely RF
model, acquired the highest AUC value (0.859). Last but gained a
lot of attention, the results can provide references for land use
management and landslide prevention.",
doi = "10.1007/s11069-022-05520-7",
url = "http://dx.doi.org/10.1007/s11069-022-05520-7",
issn = "0921-030X",
language = "en",
targetfile = "s11069-022-05520-7.pdf",
urlaccessdate = "30 jun. 2024"
}