EGU21-15435
https://doi.org/10.5194/egusphere-egu21-15435
EGU General Assembly 2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Predicting drought-induced cracks in dikes with machine learning algorithms

Shaniel Chotkan1, Juan Pablo Aguilar-López1, Raymond van der Meij2, Phil Vardon3, Wouter Jan Klerk1, and Juan Carlos Chacon Hurtado4
Shaniel Chotkan et al.
  • 1Hydraulic Engineering, Delft Univerisity of Technology, Delft, The Netherlands
  • 2Deltares
  • 3Geo-Engineering, Delft Univerisity of Technology, Delft, The Netherlands
  • 4Water Management, Delft Univerisity of Technology, Delft, The Netherlands

During intense periods of drought, the development of cracks is observed in peat and clay dikes. Asset managers of the dikes increase the inspection frequency in times of drought to be able to monitor these cracks. Significant development of the cracks contributes to the development of different failure mechanisms. In this study, the occurrence of the cracks is predicted at a large spatial scale. An inspection database in which the observations from the last three years are stored is used as the basis. The database contains hundreds of observed cracks including the  location and time in which they were observed. The database was extended with attributes such as the precipitation deficit, the peat width at the surface, the orientation of the dike body, the subsidence of the dike body and the soil stiffness. Decision tree algorithms were then used to classify which circumstances will lead to cracks and which circumstances will not. From the resulting decision trees it was deduced that high precipitation deficits, low soil stiffness and the peat width can be used as the main predictors for the occurrence of cracks. Both subsidence of the foundation and the dike body being orientated to the sunny side are also contributors, although less prominent. Time-independent cracking criteria were then used to classify which regions are prone to cracking. Dikes which are rich in peat with a low stiffness were thus highlighted. The Mathews correlation coefficient was used as performance criteria resulting in a 0.3 value for the obtained tree. Application of a random forest increased the coefficient to 0.8. An important conclusion is that proper monitoring of the peat width, soil stiffness and precipitation may result in better asset management.

How to cite: Chotkan, S., Aguilar-López, J. P., van der Meij, R., Vardon, P., Jan Klerk, W., and Chacon Hurtado, J. C.: Predicting drought-induced cracks in dikes with machine learning algorithms, EGU General Assembly 2021, online, 19–30 Apr 2021, EGU21-15435, https://doi.org/10.5194/egusphere-egu21-15435, 2021.

Comments on the

to access the discussion