A novel landslide susceptibility prediction framework based on contrastive loss

IF 6 2区地球科学 Q1 GEOGRAPHY, PHYSICAL

GIScience & Remote Sensing Pub Date : 2024-02-02 DOI:10.1080/15481603.2024.2306740

Shubing Ouyang, Weitao Chen, Hangyuan Liu, Yuanyao Li, Zhanya Xu

引用次数: 0

Abstract

Recently, the positive unlabeled (PU) learning algorithms have proven highly effective in generating accurate landslide susceptibility maps. The algorithms categorize samples exclusively into posit...

查看原文本刊更多论文

基于对比损失的新型滑坡易发性预测框架

最近，事实证明正向无标记（PU）学习算法在生成准确的滑坡易感性地图方面非常有效。这些算法将样本完全分为正向和非正向两类。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

GIScience & Remote Sensing 地学-遥感

CiteScore

11.20

自引率

9.00%

发文量

审稿时长

6 months

期刊介绍： GIScience & Remote Sensing publishes original, peer-reviewed articles associated with geographic information systems (GIS), remote sensing of the environment (including digital image processing), geocomputation, spatial data mining, and geographic environmental modelling. Papers reflecting both basic and applied research are published.