OGA Hackathon in London

Sponsors: Shell - Oil & Gas Authority - OGTC - PESGB

Lithograph

We trained two rock classification models and created a tool that allows users to upload and classify their own las file.

Data

We used 8 wells from the Poseidon survey (credits mentioned on our website). We quality controlled and filtered the petrophysical suite of logs down to: Gamma-Ray, Bulk-Density, Compressional Velocity, Neutron Porosity, Photoelectric Absorption, and Deep/Medium-Resistivity. We then manually labelled the lithology log based on the composite logs (pdf files) for the training.

Models

We trained two models: a gradient boosting algorithm (XGBoost) and a bi-directional LSTM. The latter is the deep learning approach for which we adapted a network which was used for linguistic translation. This model would account for typical spatial/temporal geological sequences.

Website

We implemented the trained models in a Flask web app where users are introduced with our project and then invite to upload their own .las file for classification. The plots are Bokeh interactive log displays where you can use synchronized zooming for inspection.

note:

The Website link leads to a reduced version of the final product: running the LSTM model is disabled because the necessary python library is too large for the (free) hosting space on pythonanywhere.com. If you want to see a (working) classified las file without uploading your own: check the relevant URL below. Uploading your own might not always work because for now the tool requires the log names to be identical to the ones from Poseidon.

The link to the data prep and training repository is also given below.

Website

URLs of relevant information
https://lithograph.pythonanywhere.com/classify-Pharos_1.las#logdisplay
https://github.com/roliveira/lithograph

Github repository

https://github.com/Gijsbertbas/lithograph-website