Graph constrained label propagation on water supply networks

Abstract

In many real-world applications we have at our disposal a limited number of inputs in a theoretical database with full information, and another part of experimental data with incomplete knowledge for some of their features. These are cases that can be addressed by a label propagation process. It is a widely studied approach that may acquire complexity if new constraints in the new unlabeled data that should be taken into account are found. This is the case of the membership to a group or community in graphs. The proposal is to add the Laplacian matrix as well as another different similarity measures (may be not found in the original database) in the label propagation. A kernel embedding process together with a simple label propagation algorithm will be the main tools to achieve this approach by the use of all types of available information. In order to test the functionality of this new proposal, this work introduces an experimental study of biofilm development in drinking water pipes. Then, a label propagation through pipes belonging to a complete water supply network is approached. These pipes have their own properties depending on their network location and environmental co-variables. As a result, the proposal is a suitable and efficient way to deal with practical data, based on previous theoretical studies by the constrained label propagation process introduced.

Which method to use? An assessment of data mining methods in Environmental Data Science

“…Sometimes, prior expert knowledge can be introduced in the form of rules (Gibert et al, 2010b) or ontologies (Gibert et al, 2014) to introduce semantic information into the process, and get classes easier to interpret. Graph theory (Herrera et al, 2015;di Nardo et al, 2018) and social network theory (Campbell et al, 2016;Brentan et al, 2017aBrentan et al, , 2018a have also found applications in clustering. Density-based methods, like DBScan (Ester et al, 1996) or OPTICS (Ankerst et al, 1999) are computation-based methods detecting areas with higher concentration of objects and work well with non-globular clusters.…”

“…A hybrid combination SOM+k-Means Clustering was used to improve planning, operation and management of Water Distribution Systems in Brentan et al (2018b), which can be easily extended to other environmental problems, etc. Graph theory (Herrera et al, 2015;di Nardo et al, 2018) and social network theory (Campbell et al, 2016;Brentan et al, 2017aBrentan et al, ,2018a have been used to cluster a water distribution network into sectors so as to optimize these infrastructures' management. In Blanco et al (2018) SCADA data is used to identify health profiles of wind turbines.…”