Modelling and prediction of spatially distributed data such as the secondary cassiterite mineral distributions are often affected by spatial autocorrelation (SAC); a phenomenon that violates attributes data independence in space, which leads to type1 errors in classical statistics and overfitting or underfitting in machine learning (ML) classification respectively. The concept of overfitting and underfitting of spatially distributed datasets in an ML classification has not been properly addressed by the traditional random holdout technique of model validation, and this is a challenge to the assessment of predictive spatial model performance in spatially distributed datasets.

These exercises have been made to fit the content of the book Pressure Control During Oil Well Drilling http://bookboon.com/no (a book that was revised and updated in 2011, mostly on basis of input from readers). Many of the exercises in present book have been solved by students in the corresponding course at the Department of Petroleum Engineering and Applied Geophysics at NTNU of Trondheim, Norway. It would be highly appreciated if you contacted me at pal.skalle@ntnu.no in case there is something unclear in this collection of exercises.

The enhancement of dissolution of quartz under the influence of clays has been recognized in sandstones for many years. It is well known that a grain of quartz in contact with a clay flake dissolves faster than when in contact with another grain of quartz. This phenomenon promotes silica transfer during the diagenesis of sandstones and is responsible of deformation and porosity variations. Here we make an attempt to explain the process of this rock deformation using a pressure solution mechanism.