Pipe failure modelling is an important tool for strategic rehabilitation planning of urban water distribution infrastructure. Rehabilitation predictions are mostly based on existing network data and historical failure records, both of varying quality. This paper presents a framework for the extraction and processing of such data to use it for training of decision tree-based machine learning methods. The performance of trained models for predicting pipe failures is evaluated for simple as well as more advanced, ensemble-based, decision tree methods. Bootstrap aggregation and boosting techniques are used to improve the accuracy of the models. The models are trained on 50% of the available data and their performance is evaluated using confusion matrices and receiver operating characteristic curves. While all models show very good performance, the boosted decision tree approach using random undersampling turns out to have the best performance and thus is applied to a real world case study. The applicability of decision tree methods for practical rehabilitation planning is demonstrated for the pipe network of a medium sized city.

The decisions taken in rehabilitation planning for the urban water networks will have a long lasting impact on the functionality and quality of future services provided by urban infrastructure. These decisions can be assisted by different approaches ranging from linear depreciation for estimating the economic value of the network over using a deterioration model to assess the probability of failure or the technical service life to sophisticated multi-criteria decision support systems. Subsequently, the aim of this paper is to compare five available multi-criteria decision-making (MCDM) methods (ELECTRE, AHP, WSM, TOPSIS, and PROMETHEE) for the application in an integrated rehabilitation management scheme for a real world case study and analyze them with respect to their suitability to be used in integrated asset management of water systems. The results of the different methods are not equal. This occurs because the chosen score scales, weights and the resulting distributions of the scores within the criteria do not have the same impact on all the methods. Independently of the method used, the decision maker must be familiar with its strengths but also weaknesses. Therefore, in some cases, it would be rational to use one of the simplest methods. However, to check for consistency and increase the reliability of the results, the application of several methods is encouraged.