Title: Eigenvector Spatial Filtering-Based Logistic Regression for Landslide Susceptibility Assessment

Authors: Li, HF (Li, Huifang); Chen, YM (Chen, Yumin); Deng, SS (Deng, Susu); Chen, MJ (Chen, Meijie); Fang, T (Fang, Tao); Tan, HY (Tan, Huangyuan)

Source: ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION Volume: 8 Issue: 8 DOI: 10.3390/ijgi8080332 Published: AUG 2019

Abstract: Logistic regression methods have been widely used for landslide research. However, previous studies have seldom paid attention to the frequent occurrence of spatial autocorrelated residuals in regression models, which indicate a model misspecification problem and unreliable results. This study accounts for spatial autocorrelation by implementing eigenvector spatial filtering (ESF) into logistic regression for landslide susceptibility assessment. Based on a landslide inventory map and 11 landslide predisposing factors, we developed the eigenvector spatial filtering-based logistic regression (ESFLR) model, as well as a conventional logistic regression (LR) model and an autologistic regression (ALR) model for comparison. The three models were evaluated and compared in terms of their prediction capability and model fit. The ESFLR model performed better than the other two models. The overall predictive accuracy of the ESFLR model was 90.53%, followed by the ALR model (76.21%) and the LR model (74.76%), and the areas under the ROC curves for the ESFLR, ALR and LR models were 0.957, 0.828 and 0.818, respectively. The ESFLR model adequately addressed the spatial autocorrelation of residuals by reducing the Moran's I value of the residuals to 0.0270. In conclusion, the ESFLR model is an effective and flexible method for landslide analysis.

WOS: 000482985000017

Language: English

Document Type: Article

Key words of Author: landslide; logistic regression; spatial autocorrelation; eigenvector spatial filtering

Keywords Plus: MAPPING UNITS; GIS; AUTOCORRELATION; PREDICTION; DECISION; MODELS; HAZARD; ISLAND; RATIO; AREA

Addresses: [Li, Huifang; Chen, Yumin; Chen, Meijie; Fang, Tao; Tan, Huangyuan] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Hubei, Peoples R China.

[Deng, Susu] Zhejiang A&F Univ, Sch Environm & Resource, Hangzhou 311300, Zhejiang, Peoples R China.

Addresses of reprint authors: Chen, YM，Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Hubei, Peoples R China.

Email: ymchen@whu.edu.cn

Impact factor：1.84