Abstract
Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
Highlights
L ANDSLIDES are one of the most common and destructive geological disasters worldwide
To fill the knowledge gap of landslide susceptibility prediction (LSP), this study aims to use a positive unlabeled (PU) learning method coupled with adaptive sampling and random forest (AdaPU-RF) to predict landslide susceptibility in the Three Gorges Reservoir area, China
RF, support vector machine (SVM), and logistic regression (LR) are popular and robust machine learning methods, which have been widely used for LSP [26], [47]
Summary
L ANDSLIDES are one of the most common and destructive geological disasters worldwide. According to the Emergency Events Database, 761 major landslide disasters occurred from 1900 to 2020, causing 67 058 deaths, approximately 14.6 million people affected and economic loss of about 10.9 billion dollars [1]. As a key step in landslide risk assessment, landslide susceptibility prediction (LSP) can predict where landslides are likely to occur and the likelihood of occurrence [2].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have