In this paper, a hybrid leak localization approach in WDNs is proposed, combining both model-based and data-driven modeling. Pressure heads of leak scenarios are simulated using a hydraulic model, and then used to train a machine-learning based leak localization model. A key element of the methodology is that discrepancies between simulated and measured pressures are accounted for using a dynamically calculated bias correction, based on historical pressure measurements. Data of in-field leak experiments in operational water distribution networks were produced to evaluate our approach on realistic test data. The results show that the leak localization model is able to reduce the leak search region in parts of the network where leaks induce detectable drops in pressure. When this is not the case, the model still localizes the leak but is able to indicate a higher level of uncertainty with respect to its leak predictions.
As Knowledge Graphs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modeling techniques. The original work proposed the Weisfeiler-Lehman kernel to improve the quality of the representations. However, in this work, we show that the Weisfeiler-Lehman kernel does little to improve walk embeddings in the context of a single Knowledge Graph. As an alternative, we examined five alternative strategies to extract information complementary to basic random walks and compare them on several benchmark datasets to show that research within this field is still relevant for node classification tasks.
As KGs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create taskagnostic numerical representations of the nodes in a KG by extending successful language modelling techniques. The original work proposed the Weisfeiler-Lehman (WL) kernel to improve the quality of the representations. However, in this work, we show both formally and empirically that the WL kernel does little to improve walk embeddings in the context of a single KG. As an alternative to the WL kernel, we propose five different strategies to extract information complementary to basic random walks. We compare these walks on several benchmark datasets to show that the n-gram strategy performs best on average on node classification tasks and that tuning the walk strategy can result in improved predictive performances.
Water loss due to persistent leakages in water distribution networks remains a substantive problem around the world, all the more so given noticeable trends of increasing global water scarcities. In this paper, we present a data-driven leak localization approach leveraging a connected Geographical Information System together with an autoencoder to perform anomaly detection on time-variable sensor data. Datadriven approaches are able to circumvent many of the uncertainty issues associated with model-based approaches, but they usually require significant amounts of highquality data, reflecting many different leak scenarios, to perform well. Our approach obviates this requirement by relying only on leakless data during model training. We examine the efficacy of this approach on 19 realistic leak experiments conducted in the field. Based on these evaluations, we were able to achieve average search costs as low as 2.2 kilometers, for a total network length of 215 kilometers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.