intrepretation of cone penetration tests using a neural ...€¦ · romée kars bart meijninger jan...
TRANSCRIPT
![Page 1: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/1.jpg)
EGU 2020
Willem Dabekaussen
Renée de Bruijn
Romée Kars
Bart Meijninger
Jan Stafleu
TNO – Geological Survey of the Netherlands
![Page 2: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/2.jpg)
DIKE REINFORCEMENTS ALONG THE LEK RIVER
Sterke Lekdijk - EGU Sharing Geosciences Online 2020Source: Veiligheid Nederland in Kaart, 2014;
Brochure Sterke Lekdijk, Geodan, 2018
The Northern Lek River dike protects a large and
densely populated area of the Netherlands, including
the cities Utrecht and Amsterdam.
Water Authority Hoogheemraadschap De Stichtse
Rijnlanden (HDSR) maintains the dike and launched
the project ‘Sterke Lekdijk’ for large scale
reinforcements.
The strength and stability of the dike depends
• on its design
• the composition of the subsurface
![Page 3: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/3.jpg)
DIKE FAILURE MECHANISMS RELATED TO
SUBSURFACE CONDITIONS
Piping
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
Macro-instability
Detailed knowledge of the subsurface is
essential!
![Page 4: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/4.jpg)
REGIONAL MODEL FOR SHALLOW SUBSURFACE
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
Geological Survey of The Netherlands develops and
maintains GeoTOP model, based on ~ 580,000
boreholes.
![Page 5: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/5.jpg)
GEOTOP WORKFLOW
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
W-03
Lithostratigraphical
interpretation of
borehole logs
2D interpolation of
stratigraphical surfaces
layer-based model
3D interpolation of
lithological class within
each stratigraphical unit
voxel model
Stochastic simulation techniques allow
quantification of uncertainty
![Page 6: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/6.jpg)
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
GEOTOP 3D VOXEL MODEL
Extending the GeoTOP voxel model to the south-eastern Netherlands
50 m below surface level
~2/3 coverage of Dutch subsurface
Resolution 100 x 100 x 0.5 m
Each voxel contains information on:
Geological unit
Lithological class (sand, clay, peat)
Lithological class probability
Man-made ground
Clay
Peat
Fine sand
Medium sand
Coarse sand
Clayey sand
![Page 7: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/7.jpg)
COMPLEX HOLOCENE GEOLOGY
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
GeoTOP
Man-made ground
Clay
Peat
Fine sand
Medium sand
Coarse sand
Clayey sand
Erkens, G., 2009
Lek river dike built on complex Holocene geology
Regional GeoTOP model provides 100 m
horizontal resolution
Dike reinforcement projects require more detailed
subsurface model
dike
dike
![Page 8: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/8.jpg)
AVAILABLE BOREHOLE AND CONE PENETRATION
TESTS
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
![Page 9: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/9.jpg)
CONE PENETRATION TEST (CPT)
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
![Page 10: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/10.jpg)
sand
cleyey sand
claypeat
peat
Robertson (2010) classificatie schema
FROM CONE PENETRATION TEST TO LITHOLOGY
Lithological classification adapted from Robertson
(2010) classification chart to identify GeoTOP
lithological classes
Classification chart designed for geotechnical
classes
Lithological classes clayey sand and peat hard to
identify
Needs tuning based on local geology
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
![Page 11: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/11.jpg)
FROM CONE PENETRATION TEST TO LITHOLOGY:
ARTIFICIAL NEURAL NETWORK
Network design
• 2 Dense hidden layers
• Classify CPT parameters to lithological classes
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
cone resistance →
friction ratio →
(pore pressure) →
depth (msl) →
depth (surface)→
peat
clay
clayey sand
sand
Train with local data
• 231 pairs of closely spaced boreholes and CPT’s were
available
![Page 12: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/12.jpg)
CROSS VALIDATION RESULTS
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
Based on
Robertson (2010)
Artificial neural
network
precision recall
Single CPT – borhole pair
Confusion matrix
![Page 13: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/13.jpg)
HIGH-RESOLUTION SUBSURFACE MODELLING
Machine Learning techniques allow harmonization of multiple data types
Using cone penetration tests together with borehole information greatly increased data
density, justifying very detailed modelling
High-resolution subsurface models facilitate new applications that need detailed information
about local geology
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
‘normal’ GeoTOP (regional model) High resolution GeoTOP (local model)
Voxel size 100 x 100 x 0.5 m Voxel size 25 x 25 x 0.25 m
![Page 14: Intrepretation of Cone Penetration Tests using a neural ...€¦ · Romée Kars Bart Meijninger Jan Stafleu TNO –Geological Survey of the Netherlands. DIKE REINFORCEMENTS ALONG](https://reader035.vdocuments.site/reader035/viewer/2022081617/6085627a1f7c46480b6ffd9d/html5/thumbnails/14.jpg)
COMMUNICATION & CONCLUSIONS
Combining information above & below the surface
in Digital Twin environment
Sterke Lekdijk - EGU Sharing Geosciences Online 2020
• Machine learning can help getting more
out of available data
• More data enables detailed models
→ more specific for experts
→ brings geology closer to non-experts