Comparative performance assessment of landslide susceptibility models with presence-only, presence-absence, and pseudo-a
- PDF / 3,138,606 Bytes
- 21 Pages / 595.22 x 842 pts (A4) Page_size
- 35 Downloads / 225 Views
e-mail: [email protected]
Comparative
performance
susceptibility
models
with
http://jms.imde.ac.cn https://doi.org/10.1007/s11629-020-6277-y
assessment
of
landslide
presence-only,
presence-
absence, and pseudo-absence data
ZHAO Dong-mei
https://orcid.org/0000-0002-8453-1778; e-mail: [email protected]
JIAO Yuan-mei*
https://orcid.org/0000-0003-0913-688X;
WANG Jin-liang
https://orcid.org/0000-0001-7202-646X; e-mail: [email protected]
DING Yin-ping LIU Zhi-lin
e-mail: [email protected]
https://orcid.org/0000-0003-2749-4533; e-mail: [email protected]
https://orcid.org/0000-0003-2925-1121; e-mail: [email protected]
LIU Cheng-jing
https://orcid.org/0000-0003-0836-8443; e-mail: [email protected]
QIU Ying-mei
https://orcid.org/0000-0001-8996-3679; e-mail: [email protected]
ZHANG Juan
https://orcid.org/0000-0003-3688-4488; e-mail: [email protected]
XU Qiu-e
https://orcid.org/0000-0001-6558-7568; e-mail: [email protected]
WU Chang-run
https://orcid.org/0000-0003-2261-4946; e-mail: [email protected]
∗Correspondence author School of Tourism and Geography Sciences, Yunnan Normal University, No. 768 Juxian Street, Chenggong District, Kunming 650500, China. Citation: Zhao DM, Jiao YM, Wang JL, et al. (2020) Comparative performance assessment of landslide susceptibility models with presence-only, presence-absence, and pseudo-absence data. Journal of Mountain Science 17. https://doi.org/10.1007/s11629-020-6277-y
© Science Press, Institute of Mountain Hazards and Environment, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract: The quality of the data for statistical methods plays an important role in landslide susceptibility mapping. How different data types influence the performance of landslide susceptibility maps is worth studying. The goal of this study was to explore the effects of different data types namely, presence-only (PO), presence-absence (PA), and pseudo-absence (PAs) data, on the predictive capability of landslide susceptibility mapping. This was completed by conducting a case study in the landslide-prone Honghe County in the Yunnan Province of China. A total of 428 landslide PO data Received: 22-Jun-2020 Revised: 17-Jul-2020 Accepted: 25-Sep-2020
points were selected. An equivalent number of nonlandslide locations were generated as PA data by random sampling, and 10,000 sites were uniformly selected at random from each region as PAs data. Three landslide susceptibility models, namely the information value model (IVM), logistic regression (LR) model, and maximum entropy (MaxEnt) model, corresponding to the three data types were investigated. Additionally, the area under the receiver operating characteristic curves (ROC-AUC), seven statistical indices (i.e. accuracy, sensibility, falsepositive rate, specificity, precision, Kappa, and Fmeasure), and a landslide density analysis were used to evaluate model performance regarding landslide susceptibility mapping. Our results indicated that the
1
J. Mt. Sci. (2020) 17():
MaxEnt model using PAs data performed
Data Loading...
