Další formáty:
BibTeX
LaTeX
RIS
@article{1791657, author = {Liu, Mengmeng and Liu, Jiping and Xu, Shenghua and Zhou, Tao and Ma, Yu and Zhang, Fuhao and Konečný, Milan}, article_number = {4}, doi = {http://dx.doi.org/10.1080/19479832.2021.1961316}, keywords = {Landslide susceptibility mapping; fuzzy c-means; support vector machine; Shaanxi Province}, language = {eng}, issn = {1947-9832}, journal = {International Journal of Image and Data Fusion}, title = {Landslide susceptibility mapping with the fusion of multi-feature SVM model based FCM sampling strategy: A case study from Shaanxi Province}, url = {https://doi.org/10.1080/19479832.2021.1961316}, volume = {12}, year = {2021} }
TY - JOUR ID - 1791657 AU - Liu, Mengmeng - Liu, Jiping - Xu, Shenghua - Zhou, Tao - Ma, Yu - Zhang, Fuhao - Konečný, Milan PY - 2021 TI - Landslide susceptibility mapping with the fusion of multi-feature SVM model based FCM sampling strategy: A case study from Shaanxi Province JF - International Journal of Image and Data Fusion VL - 12 IS - 4 SP - 349-366 EP - 349-366 PB - Taylor and Francis Ltd. SN - 19479832 KW - Landslide susceptibility mapping KW - fuzzy c-means KW - support vector machine KW - Shaanxi Province UR - https://doi.org/10.1080/19479832.2021.1961316 N2 - The quality of "non-landslide' samples data impacts the accuracy of geological hazard risk assessment. This research proposed a method to improve the performance of support vector machine (SVM) by perfecting the quality of `non-landslide' samples in the landslide susceptibility evaluation model through fuzzy c-means (FCM) cluster to generate more reliable susceptibility maps. Firstly, three sample selection scenarios for `non-landslide' samples include the following principles: 1) select randomly from low-slope areas (scenario-SS), 2) select randomly from areas with no hazards (scenarioRS), 3) obtain samples from the optimal FCM model (scenario-FCM), and then three sample scenarios are constructed with 10,193 landslide positive samples. Next, we have compared and evaluated the performance of three sample scenarios in the SVM models based on the statistical indicators such as the proportion of disaster points, density of disaster points precision, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC). Finally, The evaluation results show that the `non-landslide' negative samples based on the FCM model are more reasonable. Furthermore, the hybrid method supported by SVM and FCM models exhibits the highest prediction efficiency. Scenario FCM produces an overall accuracy of approximately 89.7% (AUC), followed by scenario-SS (86.7%) and scenario-RS (85.6%). ER -
LIU, Mengmeng, Jiping LIU, Shenghua XU, Tao ZHOU, Yu MA, Fuhao ZHANG a Milan KONEČNÝ. Landslide susceptibility mapping with the fusion of multi-feature SVM model based FCM sampling strategy: A case study from Shaanxi Province. \textit{International Journal of Image and Data Fusion}. Taylor and Francis Ltd., 2021, roč.~12, č.~4, s.~349-366. ISSN~1947-9832. Dostupné z: https://dx.doi.org/10.1080/19479832.2021.1961316.
|