Gef-Modelsoil classification based on machine learning
NEN-TableDefines soil properties according to NEN9997-1 table 2b
PyGefReads GEF-files and interpret cpts with Robertson / Been & Jefferies + plot

CPT Core

CPT Core consists of a fully automated soil classification based on machine learning model. The model has been trained by comparing roughly 49.000 Cpts and 40.000 boreholes, from which 1800 pairs met the condition of being less than 6 meters apart. These have been used as labelled data for the first model training. The model is then retrained periodically whenever new data is available that meet the condition of being 6 meters apart.

The CPT model groups layers based on the signals of the cone resistance and friction ratio. The model includes a steering or penalty parameter which gives you the freedom of getting many of just a few layers.

Because actual data is used to train the model, it will include location characteristics to get a consistent interpretation of the measurements. After classification CPT Core can provide the soil parameters per layer based on table 2.b of NEN9997-1. These parameters can be used to get started with geotechnical calculations. CPT Core is used in all of ours API’s to give your calculations a flying start!

More information in these blogs:
The CPT MODEL (part 1)
Applications of the CPT MODEL (part 2)

Contact us

Go back

Site by Alsjeblaft!