Robust weighted kernel logistic regression in imbalanced and rare events data
Computational Statistics & Data Analysis
| Hi-index | 0.00 |
A wide range of numerical models and tools have beendeveloped over the last decades to support the decisionmaking process in environmental applications, rangingfrom physical models to a variety of statistically-basedmethods. In general, the statistically-based methods andexpert systems are commonly used, although physicalmodels have and are being incorporated. In this paper wepresent the approaches for the analysis and modeling oflandslide data using logistic regression. This workdescribes the application of the method for the area ofBailongjiang River, in northwest China. The availableinformation includes the digital elevation model of theregion, geological map and land cover data obtainedfrom satellite imagery. The landslides were observed anddocumented during the field studies.