 |
|||
| Url | https://cimne.com/sgp/rtd/Project.aspx?id=938 | ||
|
|||
| Acronym | DIGIT4WATER | ||
| Project title | Desarrollo de herramientas digitales basadas en modelos de Machine Learning para la predicción de niveles de eliminación de contaminantes en tratamientos terciarios avanzados Development of digital tools based on Machine Learning models for the prediction of removal levels of different pollutants in advanced tertiary treatments | ||
| Reference | TED2021-129969B-C33 | ||
| Principal investigator |
David Jesús VICENTE GONZÁLEZ - djvicente@cimne.upc.edu
Fernando SALAZAR GONZÁLEZ - fsalazar@cimne.upc.edu |
||
| Start date | 01/12/2022 | End date | 30/11/2024 |
| Coordinator | CIEMAT | ||
| Consortium members |
|
||
| Program | P.E. para Impulsar la Investigación Científico-Técnica y su Transferencia | Call | Proyectos Estratégicos Orientados a la Transición Ecológica y a la Transición Digital» 2021 |
| Subprogram | Subprograma Estatal de Generación de Conocimiento | Category | Nacional |
| Funding body(ies) | MICINN | Grant | $120,750.00 |
| Abstract | Reuse of treated wastewater can be considered a reliable water supply, quite independent from seasonal drought and weather variability and able to cover peaks of water demand specially in water scarcity areas. Wastewater reuse for irrigation in agriculture is by far the most established end-use for reclaimed water in arid and semi-arid areas. However, while solving water scarcity, wastewater reuse can generate public health risks if treatment, storage and piping are not adequate. In higher income level countries, concerns tend to shift from microbial risk to organic microcontaminants (OMCs) such as pesticides, pharmaceuticals, illicit drugs, synthetic and natural hormones, personal care products, disinfection by products (DBPs), and resistant microorganisms (i.e. antibiotic resistant bacteria and genes (ARB&ARGs)). Conventional treatment processes in Municipal Wastewater treatment plants (MWWTPs) are poorly effective to remove OMCs, constituting a particular concern when effluents are reused for crop irrigation. To be able to meet stringent limits for wastewater reuse as well as to effectively remove chemical and microbial contaminants, advanced treatment steps should be implemented in conventional MWWTPs. The DIGIT4WATER project aims to contribute to the implementation of these advanced treatments through the development of a digital tools for decision support and technology design based on machine learning models. In this sense, DIGIT4WATER will address: a) the creation of an open database, containing not only the physicochemical characterization of raw municipal wastewater, secondary and tertiary effluents from different WWTPs in central and south-eastern Spain, but also the concentration of OMC, DBP, pathogens, ARB and ARG, detected in these streams. Chronic toxicity data will also be included; b) the implementation of alternative and sustainable tertiary treatments based on UVC and solar processes to ensure compliance with the new European Regulation on minimum requirements for water reuse for agricultural irrigation (2020/741); c) the development of machine learning models, as a disruptive digital technology, which will be fed by the open database created and the data generated from the UVC- and solar-based technologies tested in DIGIT4WATER, as a starting point to design and define the best tertiary treatment to be implemented in specific areas of the country for the regeneration of water for crop irrigation; d) the design of an Early Warning System (EWS) for detecting events in which the quality of reclaimed water is below the minimum legal and sanitary requirements depending on the final reuse purposes. DIGIT4WATER will specifically start by ensuring the absence of DBPs and pathogens in reclaimed water. The digital solutions developed will be able to propose the actions to be taken in the tertiary treatment selected to eliminate DBPs and pathogens when they are detected in the output. | ||
| Ayuda TED2021-129969B-C33 del proyecto financiado por MCIN/AEI/10.13039/501100011033/ y por la Unión Europea NextGenerationEU/ PRTR | |||