A comparison of statistical and machine learning methods for debris flow susceptibility mapping
- PDF / 7,207,033 Bytes
- 21 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 219 Views
ORIGINAL PAPER
A comparison of statistical and machine learning methods for debris flow susceptibility mapping Zhu Liang1 • Chang-Ming Wang1 • Zhi-Min Zhang1 • Kaleem-Ullah-Jan Khan1
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Debris flows destroys the facilities and seriously threatens human lives, especially in mountainous area. Susceptibility mapping is the key for hazard prevention. The aim of the present study is to compare the performance of three methods including Bayes discriminant analysis (BDA), logistic regression (LR) and random forest (RF) for debris flow susceptibility mapping from three aspects: applicability, analyticity and accuracy. Nyalam county, a debris flow-prone area, located in Southern Tibet, was selected as the study area. Firstly, the dataset containing 49 debris flow inventories and 16 conditioning factors was prepared. Subsequently, divided the dataset into two groups with a ratio of 70/30 for training and validation purposes, and repeated 5 times to obtain 5 different groups. Then, 16 factors were involved in the modeling of RF, of which 11 factors with low linear correlation were for BDA and LR. Finally, receiver operating characteristic curves, the area under curve (AUC) and contingency tables were applied to evaluated the accuracy performance of the 3 models. The prediction rates were 74.6–81.8%, 74.6–83.6% and 80–92.7%, for the BDA, LR and FR, while the AUC values of three models were 0.72–0.78, 0.82–0.92 and 0.90–0.99, respectively. Compare to LR an BDA, RF not only effectively process and preserved dataset without priori assumption and the obtained susceptibility zoning map and major factors were reasonable. The conclusion of the current study is useful for risk mitigation and land use planning in the study area and provide related references to other researches. Keywords Debris flow Himalayas area Bayes discriminant analysis Logistic regression Random forest Susceptibility Abbreviations BDA Bayes discriminant analysis LR Logistic regression RF Random forest ROC Relative operating characteristic AUC Area under curve DFS Debris flow susceptibility GPS Global positioning systems GIS Geographic information systems RS Remote sensing DEM Digital elevation model SRTM Shuttle Radar Topography Mission Sig Significant parameter value OOB Out of bag AGMC Average gradient of main channel & Chang-Ming Wang [email protected] 1
MED MODIS ASA RED FL FD DTF NDVI MCL DD DTR VIF FR TP TN FP FN
Maximum elevation difference Moderate-resolution Imaging Spectroradiometer Average slope angle Relative cutting depth Fault length Fault density Distance to fault Normalized difference vegetation index Main channel length Drainage density Distance to road Variance inflation factor Frequency ratio True positives True negatives False positives False negatives
College of Construction Engineering, Jilin University, Changchun 130012, People’s Republic of China
123
Stochastic Environmental Research and Risk Assessment
1 Introduction Debris flow is geologically consider
Data Loading...
