Data Mining For Knowledge-Based Approach for Landslide Susceptibility Mapping

Data mining;Landslide susceptibility mapping;Kaixian area

Schuck, Aaron D.

University of Wisconsin

关键词: Data mining;    Landslide susceptibility mapping;    Kaixian area;   

Others  :  https://minds.wisconsin.edu/bitstream/handle/1793/78912/Schuck%20Aaron%202018.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: University of Wisconsin

【 摘 要 】

Statistical approaches to landslide susceptibility mapping can be an effective tool fordetermining areas of high risk, but have also had problems with portability, reliability, stability,and impracticality as they often require large amounts of data in order to be effective. Theknowledge based approach has been proven to address these issues, but the necessary preparationrequired for obtaining domain knowledge on landslide susceptibility and predisposing factorsdemands time and effort from the analyst. This paper proposes a knowledge based data miningapproach: data mining techniques for defining the knowledge on the relationship betweenlandslide susceptibility and predisposing factors and the knowledge based approach for mappinglandslide susceptibility. A set of environmental clusters were generated through fuzzyclassification of key environmental layers describing spatial variation of predisposing factors.These clusters were then hardened and later ranked according to density of landslides. Thecluster centroid values are ordered in the order of landslide density for hardened classes and usedas control points for the construction of fuzzy membership functions on knowledge ofrelationships between landslide susceptibility and predisposing factors. The fuzzy membershipfunctions are then used through a knowledge-based approach to map landslide susceptibility.The accuracy of the so generated map in the Kaixian area is comparable with that from a logisticregression model. However, the generated fuzzy membership functions are more portable thanthose in the logistic model. It was also found that the combination layer was correlated stronglywith landslide instances, and could serve as a useful input for future studies. The results of thisstudy provide a useful illustration for potential in the construction of fuzzy membership mapsfrom field observation data.