Jaap Mondt (Breakaway)
More and more Machine Learning will play a role not only in society in general but also in
the geosciences. Machine Learning resorts under the overall heading of Artificial
Intelligence. In this domain often the word “Algorithms” is used to indicate that computer
algorithms are used to obtain results. Also, “Big Data” is mentioned, indicating that these
algorithms need a fast amount of training data to produce useful results.
Many scientists mention “Let the data speak for itself” when referring to Machine Learning,
indicating that hidden or latent relationships between observations and classes of (desired)
outcomes can be derived using these algorithms. Examples are not only in seismic
acquisition, processing, and interpretation, but also in the non-seismic domain. When no
clear theoretical model, in the form of equations, can be formulated to describe a
geophysical phenomenon, Machine Learning might find useful statistical relationships.
From a range of labelled data, we can derive a linear/nonlinear relationship (model in ML
terminology) that predicts the label (supervised learning) of new data (instances in ML
terminology). But sometimes it is already useful if an algorithm can define separate clusters,
which then still need to be interpreted (unsupervised learning). Even more sophisticated is
Semi-supervised learning: labelled and unlabelled data together are clustered whereby the
unlabelled data receives the label of the dominant class present in the cluster.
video recording of lecture available on request