Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models
Tóm tắt
The objective of this study is to investigate and compare the results of three data mining approaches, the support vector machines (SVM), decision tree (DT), and Naïve Bayes (NB) models for spatial prediction of landslide hazards in the Hoa Binh province (Vietnam). First, a landslide inventory map showing the locations of 118 landslides was constructed from various sources. The landslide inventory was then randomly partitioned into 70% for training the models and 30% for the model validation. Second, ten landslide conditioning factors were selected (i.e., slope angle, slope aspect, relief amplitude, lithology, soil type, land use, distance to roads, distance to rivers, distance to faults, and rainfall). Using these factors, landslide susceptibility indexes were calculated using SVM, DT, and NB models. Finally, landslide locations that were not used in the training phase were used to validate and compare the landslide susceptibility maps. The validation results show that the models derived using SVM have the highest prediction capability. The model derived using DT has the lowest prediction capability. Compared to the logistic regression model, the prediction capability of the SVM models is slightly better. The prediction capability of the DT and NB models is lower.
Từ khóa
Tài liệu tham khảo
Sassa K., 2008, Landslides-Disaster Risk Reduction
Tien BuiD. PradhanB. LofmanO. RevhaugI. andDickO. B. Landslide susceptibility mapping at Hoa Binh province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS Computers & Geosciences. In press.
Miner A. S., 2010, Geologically Active
Bai S. B., 2008, GIS-Based landslide susceptibility mapping with comparisons of results from machine learning methods versus logistic regression in basin scale, Geophysical Research Abstracts, EGU, 10
Micheletti N., 2011, Landslide susceptibility mapping using adaptive Support Vector Machines and feature selection, Geophysical Research Abstracts, EGU, 13
Ratanamahatana C. A., 2003, Feature selection for the naive Bayesian classifier using decision trees, Applied Artificial Intelligence, 17, 475, 10.1080/713827175
Van T. T., 2006, Investigation and Assessment of the Current Status and Potential of Landslide in Some Sections of the Ho Chi Minh Road, National Road 1A and Proposed Remedial Measures to Prevent Landslide from Threat of Safety of People, Property, and Infrastructure
Vapnik V. N., 1998, Statistical Learning Theory
LinH.-T.andLinC.-J. A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods 2003 National Taiwan University Taipei Taiwan.
AliS.andSmithK. A. Automatic parameter selection for polynomial kernel Proceedings of the IEEE International Conference on Information Reuse and Integration (IRI ′03) Octobe 2003 243–249.
Mattera D., 1999, Advances in Kernel Methods, 211
Platt J., 2000, Probabilistic Outputs for Support Vector Machines and Comparison to Regularized Likelihood Methods
Zhuang L., 2006, Pricai 2006: Trends in Artificial Intelligence, Proceedings, 434, 10.1007/978-3-540-36668-3_47
Breiman L., 1984, Classification and Regression Trees
Michael J. A., 1997, Data Mining Technique: For Marketing, Sales and Customer Support
Quinlan J. R., 1993, C4.5: Programs for Machine Learning
Witten I. H., 2005, Data Mining: Practical Machine Learning Tools and Techniques
Cho J. H., 2011, Decision tree approach for classification and dimensionality reduction of electronic nose data, Sensors and Actuators B, 160, 542, 10.1016/j.snb.2011.08.027
XieZ. ZhangQ. HsuW. andLeeM. ZhouL. OoiB. andMengX. Enhancing SNNB with local accuracy estimation and ensemble techniques 3453 Proceedings of the 10th international conference on Database Systems for Advanced Applications (DASFAA ′05) April 2005 Beijing China Springer.