A novel landslide susceptibility prediction framework based on contrastive loss

Recently, the positive unlabeled (PU) learning algorithms have proven highly effective in generating accurate landslide susceptibility maps. The algorithms categorize samples exclusively into positive samples (landslides) and unlabeled samples for training, eliminating random or subjective selection...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Shubing Ouyang, Weitao Chen, Hangyuan Liu, Yuanyao Li, Zhanya Xu
Format:	Artigo
Sprog:	Inglês
Udgivet:	Taylor & Francis Group 2024-12-01
Serier:	GIScience & Remote Sensing
Fag:	Landslide susceptibility prediction contrastive loss positive unlabeled learning remote sensing
Online adgang:	https://www.tandfonline.com/doi/10.1080/15481603.2024.2306740
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!