RT info:eu-repo/semantics/article
T1 Applying XAI based unsupervised knowledge discovery for operation modes in a WWTP. A real case: AQUAVALL WWTP
A1 Beneyto Rodríguez, Alicia
A1 Sáinz Palmero, Gregorio Ismael
A1 Galende Hernández, Marta
A1 Fuente Aparicio, María Jesús de la
A1 Cuenca de la Cruz, José María
K1 WWTP
K1 Operation modes
K1 Explainable artificial intelligence
K1 Knowledge extraction
K1 Dimensional data reduction
K1 33 Ciencias Tecnológicas
AB Water reuse is a key point when fresh water is a commodity in ever greater demand, yet also becoming moreaccessible. Furthermore, the return of clean water to its natural environment is also mandatory. Therefore,wastewater treatment plants (WWTPs) are essential in any policy focused on these serious challenges. WWTPsare complex facilities which need to operate at their best to achieve their goals. Nowadays, they are largelymonitored, generating large databases of historical data concerning their functioning over time. All this impliesa large amount of embedded information which is not usually easy for plant managers to assimilate, correlateand understand; in other words, for them to know the global operation of the plant at any given time. At thispoint, the intelligent and Machine Learning (ML) approaches can give support for that need, managing all thedata and translating them into manageable, interpretable and explainable knowledge about how the WWTPplant is operating at a glance. Here, an eXplainable Artificial Intelligence (XAI) based methodology is proposedand tested for a real WWTP, in order to extract explainable service knowledge concerning the operation modesof the WWTP managed by AQUAVALL, which is the public service in charge of the integral water cycle inthe City Council of Valladolid (Castilla y León, Spain). By applying well-known approaches of XAI and MLfocused on the challenge of WWTP, it has been possible to summarize a large number of historical databasesthrough a few explained operation modes of the plant in a low-dimensional data space, showing the variablesand facility units involved in each case
PB Elsevier
SN 2214-7144
YR 2026
FD 2026
LK https://uvadoc.uva.es/handle/10324/83810
UL https://uvadoc.uva.es/handle/10324/83810
LA eng
NO Journal of Water Process Engineering, 2026, vol. 86, p. 109915
NO Producción Científica
DS UVaDOC
RD 28-mar-2026