Fusing physics-based and data-driven models to forecast and mitigate landslide collapse

Abstract

Deep-seated landslides represent one of the most devastating natural hazards on earth, typically creeping at inappreciable velocities over several years be- fore suddenly collapsing with catastrophic speeds. They can have detrimental consequences to society, causing fatalities and prone to affect transportation infrastructures. In this study, we validate that monitoring the basal temperature of a creeping landslide, and fusing it with physics-based modeling, can offer predictive and control capabilities for the landslide’s response. The study shows that physics-based models can be trained in the same phase-space, and has been applied to four case studies for its validity. We anticipate our results to be the starting point for a new era in monitoring, controlling, and forecasting deep-seated landslides, aiming at alleviating their devastating impact on society.

Authors 2

1. Carolina Seguí Aachen Institute of Geomechanics and Underground Technology

   RWTH Aachen University

   Affiliation as printed

   Institute of Geomechanics and Underground Technology , RWTH Aachen University , Mies-van-der-Rohe-Str. 1 , Aachen , 52074 , Germany

   Institute of Geomechanics and Underground Technology, RWTH Aachen University, Mies-van-der-Rohe-Str. 1, Aachen, 52074, Germany

2. Manolis Veveakis

   Duke University

   Affiliation as printed

   Civil and Environmental Engineering Department , Duke University , 100 Science Dr. , 121 Hudson Hall , Durham , NC 27708 , USA

   Civil and Environmental Engineering Department, Duke University, 100 Science Dr., 121 Hudson Hall, Durham, NC 27708, USA