Data Mining, Knowledge Discovery and Data-driven Modelling

• to study and select existing data mining, knowledge discovery and data-driven techniques, and apply them to solve practical problems posed;
• in particular, to investigate applicability of data-driven methods in CPT analysis, sedimentation modelling, prediction of North Sea surge water levels, optimal control of regional water systems in the Netherlands;
• design and develop prototypes of data mining, knowledge discovery and data-driven modelling tools, and to make components available on the Internet, as a part of DC?s Knowledge Management Platform.
• through practical use, to introduce these procedures and tools into research and engineering practice of DC organisations and external partners; and
• to conduct PhD and MSc studies into specialised data mining and data-driven modelling techniques and their practical applications.

Data mining, knowledge discovery and data-driven modelling (DDM) complement the so-called physically-based modelling traditionally used in civil engineering.

In some instances they may present an alternative to the latter. Instead of using physical description and relevant (differential) equations, DDM is based on the analysis of historical data sets describing the system and often aims at establishing functional relationships between input and output and at various ways of analysing time series.

DDM draws on the results achieved in computer science and areas such as database systems, statistics, machine learning, wavelets, non-linear dynamics (chaos theory), data visualisation, pattern recognition, artificial neural networks, fuzzy logic and global optimization (e.g., genetic algorithms).

A large set of data analysis methods have been developed in statistics, and machine learning has also contributed significantly to classification and induction problems.

Neural networks have shown their effectiveness in classification, prediction, and clustering analysis tasks.

Lately, chaos theory allowed to deal with predictions of natural and human-generated processes (such as geophysical processes, precipitation, etc.) with unprecedented accuracy.

Activities and Outputs: The development of an algorithm based on machine learning for the interpretation of cone penetration tests in geophysical studies forms part of the outputs, while a study of using neural network in modelling the sedimentation processes in Rotterdam harbour has been initiated.

Additionally, new machine learning algorithms for optimal control of regional water systems were built. Project Outputs include:

• Project reports;
• Research results reported in publications in the peer-reviewed journals and conferences;
• Software prototypes; and
• MSc and PhD theses publications.

Several publications were also prepared and published in peer-reviewed journals.