erdirstats.github.io

BIO Erdi Myftaraga: geotechnical engineer at NGI, based in Oslo and working in marine geotechnics projects.

INTRO Posts mostly include application of data science, machine learning and data viz concepts in geotechnics, with focus on geotechnical site assessment. Other topics might also show up. Sometimes the code is included along the main text and sometimes it isn't. The work is almost exclusively done with R code.

NOTE The content (obviously) represent my personal opinions/views and not those of my employer and it comes with absolutely no warranty. Use at your own risk.

LICENSE The work licensed under a Creative Commons Attribution-NonCommercial 4.0 International License CC BY-NC 4.0.

04 SOIL BEHAVIOUR TYPE CHARTS
2022-03-15

It can be useful sometimes to create an idea on how the CPTU measurement points of a particular site or soil unit are distributed among different SBT (Soil Behavior Type) zones. I wrote a small function to categorize CPTU data points according to the zone they plot in a few SBT charts.

03 PREDICTING SHEAR MODULUS AT SMALL STRAIN FROM CPTU DATA
2021-04-26

Short post on predicting small-strain stiffness properties from CPTU measurements by ensembling several machine learning models. More specifically, we are going to predict the value of the shear modulus at small strain, Gmax.

02 APPLICATION FOR FILTERING DOWNHOLE CPTU DATA
2021-03-21

Small app for dealing with down-hole CPTU measurements. The basic idea of the app is to remove initial measurement points (“fake measurements”) within each down-hole CPTU stroke, which may not be representative of the real soil conditions.

01 MACHINE LEARNING TO PREDICT BLOWCOUNTS NEEDED FOR THE INSTALLATION OF JACKET PILES
2020-01-08

Building some machine learning models to predict blowcounts needed for the installation of jacket piles, located in North Sea soil, using CPTU data. This was part of the Data Science Prediction Event created under the framework of the ISFOG2020 conference.