Using Deep Learning to Backcast Hydrologic Response and Inform Landslide Early Warning Systems

dc.contributor.advisorRoering, Joshua
dc.contributor.authorSheppard, Jonathan
dc.date.accessioned2024-01-09T22:40:52Z
dc.date.available2024-01-09T22:40:52Z
dc.date.issued2024-01-09
dc.description.abstractLandslides are difficult to predict due to the influence of variable geologic and environmental factors, such as geomechanical properties, rainfall, ground saturation, topography, and earthquakes, exert on the probability of a slope failure. Deep learning (DL) models can accurately predict the site-specific hydrologic response on hillslopes using soil moisture, pore pressure, and rainfall monitoring data. Landslide early warning systems can utilize empirical thresholds from deep learning-derived soil hydrology properties to improve landslide hazard prediction accuracy. We study the possibility of improving a logistical regression-based landslide early warning system being used in Sitka, AK by incorporating pore pressure responses that correspond to past known landslide events. Because pore pressure records for past known events are nonexistent, we must backcast soil hydrology timeseries from weather records, without including antecedent soil hydrology as initial conditions. We assess the accuracy of predictions at various rainfall intensity thresholds made by a Long Short-Term Memory (LSTM) DL model trained on weather features compared to a model that includes antecedent soil hydrology conditions. We find that the average accuracy of our model decreases by up to 20% for important, high-intensity rainfall events.en_US
dc.identifier.urihttps://hdl.handle.net/1794/29137
dc.language.isoen_US
dc.publisherUniversity of Oregon
dc.rightsAll Rights Reserved.
dc.subjectBackcastingen_US
dc.subjectDeep Learningen_US
dc.subjectLandslide Early Warning Systemen_US
dc.subjectLandslidesen_US
dc.subjectPore Pressureen_US
dc.titleUsing Deep Learning to Backcast Hydrologic Response and Inform Landslide Early Warning Systems
dc.typeElectronic Thesis or Dissertation
thesis.degree.disciplineDepartment of Geological Sciences
thesis.degree.grantorUniversity of Oregon
thesis.degree.levelmasters
thesis.degree.nameM.S.

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Sheppard_oregon_0171N_13547.pdf
Size:
1.53 MB
Format:
Adobe Portable Document Format