Deep Learning as a tool to forecast hydrologic response for landslide-prone hillslopes

Geophysical Research Letters
By: , and 

Links

Abstract

Empirical thresholds for landslide warning systems have benefitted from the incorporation of soil‐hydrologic monitoring data, but the mechanistic basis for their predictive capabilities is limited. Although physically based hydrologic models can accurately simulate changes in soil moisture and pore pressure that promote landslides, their utility is restricted by high computational costs and nonunique parameterization issues. We construct a deep learning model using soil moisture, pore pressure, and rainfall monitoring data acquired from landslide‐prone hillslopes in Oregon, USA, to predict the timing and magnitude of hydrologic response at multiple soil depths for 36‐hr intervals. We find that observation records as short as 6 months are sufficient for accurate predictions, and our model captures hydrologic response for high‐intensity rainfall events even when those storm types are excluded from model training. We conclude that machine learning can provide an accurate and computationally efficient alternative to empirical methods or physical modeling for landslide hazard warning.

Study Area

Additional publication details

Publication type Article
Publication Subtype Journal Article
Title Deep Learning as a tool to forecast hydrologic response for landslide-prone hillslopes
Series title Geophysical Research Letters
DOI 10.1029/2020GL088731
Volume 47
Issue 16
Year Published 2020
Language English
Publisher American Geophysical Union
Contributing office(s) Geologic Hazards Science Center, National Cooperative Geologic Mapping and Landslide Hazards
Description e2020GL088731, 9 p.
Country United States
State Oregon
Google Analytic Metrics Metrics page
Additional metadata about this publication, not found in other parts of the page is in this table