EUVIMEDEUVIMED entdecken
Crossref

Deep Learning and Mechanistic Framework Reveal Key Controls on Upper‐Slope Initiation of Rainfall‐Induced Shallow Landslides

Junyu Wu, Qing Lü, Zhongxuan Liao, Yang Yu, Jie Song, Lei Wang

Journal of Geophysical Research: Earth Surface · 2026-11 · 131 (11)

DOI: 10.1029/2026jf009303 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Geophysical Research: Earth Surface, online erschienen am 10.11.2026. Verfasst von Junyu Wu und 5 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Zhejiang Provincial Outstanding Youth Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rainfall‐induced shallow landslides often initiate near ridges, but why failure localizes at a particular upper‐slope position rather than elsewhere along the same hillslope remains unresolved. Terrain geometry, soil thickness, and transient pore‐water pressure are recognized controls, but how their spatially varying interactions along continuous slope profiles constrain initiation location remains insufficiently quantified. Here, we developed a deep‐learning‐based strategy to predict landslide initiation sites by analyzing continuous topography and soil thickness, capturing spatial dependencies ignored by using traditional cell‐based methods. Trained and validated on a landslide inventory from Zhuji, China, our approach achieves a mean normalized position error (MNPE) below 9%. Feature attribution ranked soil thickness, plan curvature, and slope angle as the three highest‐contributing predictors and showed that their contributions varied systematically along the profiles. To provide a process‐based interpretation of this localization pattern, we coupled a transient hydrologic model with a three‐dimensional slope‐stability model. The hydrologic model was calibrated using field observations from a monitored slope, and regional localization was evaluated against mapped initiation positions across 553 profiles. Modeled transient saturation exceeded the critical threshold at 85.0% of mapped initiation nodes, and the hydro‐mechanically estimated initiation positions yielded an MNPE of 14.9%. These results indicate that upper‐slope failures concentrate where rapid saturation development coincides with relatively low mechanical resistance, supporting a terrain‐conditioned hydro‐mechanical explanation for initiation in the Zhuji setting.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Zhejiang Provincial Outstanding Youth Science Foundation

Zitieren

APA

Wu, J., Lü, Q., Liao, Z., Yu, Y., Song, J., & Wang, L. (2026). Deep Learning and Mechanistic Framework Reveal Key Controls on Upper‐Slope Initiation of Rainfall‐Induced Shallow Landslides. Journal of Geophysical Research: Earth Surface, 131(11). https://doi.org/10.1029/2026jf009303

Vancouver

Wu J, Lü Q, Liao Z, Yu Y, Song J, Wang L. Deep Learning and Mechanistic Framework Reveal Key Controls on Upper‐Slope Initiation of Rainfall‐Induced Shallow Landslides. Journal of Geophysical Research: Earth Surface. 2026;131(11). doi:10.1029/2026jf009303

BibTeX
@article{Wu2026,
  author = {Wu, Junyu and Lü, Qing and Liao, Zhongxuan and Yu, Yang and Song, Jie and Wang, Lei},
  title = {Deep Learning and Mechanistic Framework Reveal Key Controls on Upper‐Slope Initiation of Rainfall‐Induced Shallow Landslides},
  journal = {Journal of Geophysical Research: Earth Surface},
  year = {2026},
  volume = {131},
  number = {11},
  doi = {10.1029/2026jf009303}
}
Kostenlos starten →