A similarity-based approach to sampling absence data for landslide susceptibility mapping using data-driven methods

Zhu，A. Xing1,2,3,4,5,6,8; Miao，Y.1,3,8; Liu，Junzhi1,3,8; Bai，Shibiao1,3,8; Zeng，Canying7; Ma，Tianwu1,3,8; Hong，Haoyuan1,3,8

2019-12-01

10.1016/j.catena.2019.104188

CATENA   影响因子和分区

0341-8162

1872-6887

The absence data (samples) for landslide susceptibility mapping using data-driven methods are not available directly and often approximated by locations where no landslides have occurred. The existing methods for generating absence data cannot quantify the reliability of candidate absence data and thus such data reduce the quality of prediction. In this paper, a new approach to absence data generation, referred to as similarity based sampling, was proposed for landslide susceptibility mapping using data-driven methods. First, the reliability of candidate absence data is quantified based on the dissimilarity in environmental conditions (covariate conditions) between the absence data and the presence data (which are the landslide occurrences). The absence data whose reliability value is higher than a given threshold were selected to be used. The proposed approach was validated through its application to three data-driven methods (i.e. logistic regression, support vector machine and random forest) for landslide susceptibility mapping. A case study was conducted in the Youfang catchment in southern Gansu Province of China. Ten groups of absence data were generated each corresponding to one of the ten different thresholds of reliability ranging from 0.0 to 0.9. The results show that the prediction accuracy of the data-driven methods rose when the threshold increased from 0.0 to 0.5, but the accuracy decreases as the threshold continues to increase after 0.5, that is, from 0.5 to 0.9. The best performance was obtained when the threshold was 0.5. The proposed method was compared with existing methods for absence data generation (i.e. buffer controlled and target space exteriorization). These results show that the similarity-based approach has a better performance than these existing methods for landslide susceptibility mapping using data-driven methods.

Data-driven methods Landslide absence data Landslide susceptibility mapping, similarity model, data mining and machine learning Sampling method

SCI

英语

其他

National Basic Research Program of China[2015CB954102]

Geology ; Agriculture ; Water Resources

Geosciences, Multidisciplinary ; Soil Science ; Water Resources

WOS:000488417700014

ELSEVIER

AGRICULTURAL SCIENCES

2-s2.0-85070208608

Scopus

1.Key Laboratory of Virtual Geographic EnvironmentNanjing Normal UniversityMinistry of Education,Nanjing,210023,China
2.State Key Laboratory of Resources and Environmental Information SystemInstitute of Geographical Sciences and Natural Resources ResearchChinese Academy of Sciences,Beijing,100101,China
3.Jiangsu Center for Collaborative Innovation in Geographic Information Resource Development and Application,Nanjing,210023,China
4.Department of GeographyUniversity of Wisconsin-Madison,Madison,53706,United States
5.University of Chinese Academy of Sciences,Beijing,100049,China
6.Center for Social SciencesSouthern University of Science and Technology,Guangzhou,Shenzhen,China
7.Institute of Land and Urban-rural DevelopmentZhejiang University of Finance & Economics,Zhejiang,310018,China
8.School of GeographyNanjing Normal University,Nanjing,210023,China

Zhu，A. Xing,Miao，Y.,Liu，Junzhi,et al. A similarity-based approach to sampling absence data for landslide susceptibility mapping using data-driven methods[J]. CATENA,2019,183.

Zhu，A. Xing.,Miao，Y..,Liu，Junzhi.,Bai，Shibiao.,Zeng，Canying.,...&Hong，Haoyuan.(2019).A similarity-based approach to sampling absence data for landslide susceptibility mapping using data-driven methods.CATENA,183.

Zhu，A. Xing,et al."A similarity-based approach to sampling absence data for landslide susceptibility mapping using data-driven methods".CATENA 183(2019).