PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 19, 2026Water0 citationsOpen Access

Evaluating Transferability of Landslide Run-out Prediction Models

Cross-Trigger Transferability of Run-out-Prediction Models for Rainfall- and Earthquake-Induced Landslides

View Full Paper

Authors

SZShudong ZhouDQDing QileYZYi Zhang

Discussion

Loading...

Member takes

Overview

Randomized trial examines prediction models' reliability across rainfall and earthquake-induced landslides, suggesting model adjustments are necessary.

Key Points

  • This study aims to evaluate the transferability and reliability of landslide run-out prediction models across different triggering mechanisms like rainfall and earthquakes.
  • Investigated a harmonized inventory of 10,158 rainfall-induced and 681 earthquake-induced landslides.
  • Utilized geometric descriptors for model comparison, including run-out distance and source volume.
  • Performed machine-learning prediction and uncertainty quantification.
  • Earthquake-induced landslides show larger geometric dimensions compared to rainfall-induced ones.
  • Asymmetric transfer degradation was observed, with overprediction in transferring from rainfall to earthquakes and underprediction from earthquakes to rainfall.
  • Prediction-interval reliability decreased significantly when models were applied cross-trigger.
Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zhou et al. (2026) studied this question.

synapsesocial.com/papers/6a34de4165a5b0777af2dc10https://doi.org/10.3390/w18121493
Ask AI
Helpful
Bookmark
Share
View Full Paper