EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Landslide displacement forecasting using deep learning and monitoring data under different slope conditions

Ascanio Rosi1, Lorenzo Nava1, Edoardo Carraro2, Cristina Reyes-Carmona3, Silvia Puliero1, Kushanav Bhuyan1,4, Oriol Monserrat5, Mario Floris1, Sansar Raj Meena1,4, Jorge Pedro Galve3, and Filippo Catani1
Ascanio Rosi et al.
  • 1Machine Intelligence and Slope Stability laboratory, Department of Geosciences, University of Padova, Padua, Italy
  • 2Geomorphological Systems and Risk Research, Department of Geography and Regional Research, University of Vienna, Universitätstraße 7, 1010 Wien, Austria
  • 3Departamento de Geodinámica, Universidad de Granada, Avda. del Hospicio, s/n, 18010 Granada, Spain
  • 4Centre for Disaster Resilience, Department of Applied Earth Sciences, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7514 AE Enschede, the Netherlands
  • 5Centre Tecnològic de Telecomunicacions de Catalunya (CTTC), Geomatics Research Unit, Barcelona, Spain

Accurate landslide early warning systems are a trustworthy risk-reduction method that may greatly minimize human and economic losses. Several machine learning algorithms have been investigated for this goal, underlying the impressive potential in prediction capability of Deep Learning (DL) models. Despite this, the only DL models evaluated so far are the long short-term memory (LSTM) and Gated Recurrent Unit (GRU) algorithms. Several alternative DL algorithms, however, are appropriate for time series forecasting problems. In this research, we evaluate, analyze, and present seven DL approaches for the forecasting of landslide displacement: LSTM, 2xLSTM, bidirectional LSTM (Bi-LSTM),Multilayer perception (MLP), 1D convolutional neural network (1D CNN), GRU, and an architecture build of 1D CNN and LSTM (Conv-LSTM). The study examines four different landslides with varying geographical locations, geological conditions, time step size, and measuring devices. Two landslides are placed in an artificial reservoir scenario, whereas the other two are affected only by rainfall. The findings show that the MLP, GRU, and LSTM models can produce accurate predictions in all four situations, with the Conv-LSTM model outperforming the others in the Baishuihe landslide, which is extremely seasonal. There are no discernible variations in performance between landslides within and outside constructed reservoirs. Furthermore, the study finds that MLP is better suited to forecasting the largest displacement peaks, whilst LSTM and GRU are better suited to forecasting smaller displacement peaks. We feel that the outcomes of this study will be extremely beneficial in developing a DL-based landslide early warning system (LEWS).

How to cite: Rosi, A., Nava, L., Carraro, E., Reyes-Carmona, C., Puliero, S., Bhuyan, K., Monserrat, O., Floris, M., Meena, S. R., Galve, J. P., and Catani, F.: Landslide displacement forecasting using deep learning and monitoring data under different slope conditions, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-12525,, 2023.