Evaluating the generalizability and transferability of water distribution deterioration models

Small utilities often lack the required amount of data to train machine learning-based models to predict pipe failures, and hence are unable to harness the possibilities and predictive power of machine learning. This study evaluates the generalizability and transferability of a machine learning model to see if small utilities can benefit from...

Variable importance measures for random forests

Measuring variable importance is often a difficult task: among others models can be complex and covariates can interact with each other and can be correlated. This study focuses on two questions: First, what should be the theoretical measure of variable importance under a given data-generating model? And second, what are the best estimates of...

Data poor environments: Uncertainty propagation in hydrodynamic modelling

The objective of this study is to propose a method that is able to deal with data poor environments within coastal studies. Numerical models are useful tools to get insight in the coastal processes of the system being modelled. Inaccurate or poor input data leads to inaccurate or even incorrect model results. By stochastic modelling insight is...

Mining the forest: Interpretable classification models in biology with application to scale-space signals

High-throughput data has become an indispensable resource for the study of biology and human disease. Due to the sheer size and complexity of these datasets, machine-learning approaches, such as predictive models, play an important role in the extraction of knowledge from these datasets. Most biological research is however not primarily...