Skip to main content

NBS SERVICES PROMOTING LOCAL BIODIVERSITY, WELL-BEING AND SCALABLE SOLUTIONS

PCI2025-163161

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de Transferencia y Colaboración
Subprogram Subprograma Estatal para impulsar la Colaboración en y entre los Sectores Público y Privado
Call Proyectos Programación Conjunta Internacional
Call year 2025
State Plan 2024-2027 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A deep learning-based probabilistic framework for streamflow prediction and water quality assessment

  • Alberto|||0009-0008-5865-4994
  • Bergillos-Meca, Rafael Jesús|||0000-0001-8674-5043
  • Paredes Arquiola, Javier|||0000-0003-3198-2169
  • Solera Solera, Abel|||0000-0001-7464-3963
  • Andreu Álvarez, Joaquín|||0000-0001-5087-5014
  • Corzo, Gerald
[EN] This study presents an integrated modelling framework designed to support water quality assessment and regulatory compliance analysis in river basins. The proposed approach combines deep learning-based streamflow prediction, stochastic uncertainty propagation, hydrological spatial disaggregation, and process-based water quality modelling at the basin scale. The framework is applied to the Júcar River Basin (eastern Spain), a highly regulated Mediterranean system characterized by strong hydrological variability and significant water quality pressures. Streamflow is predicted using a Long Short-Term Memory (LSTM) network, and uncertainty is propagated through Monte Carlo simulations to generate ensemble inflow predictions. These inflows are spatially disaggregated using variation factors derived from an HBV hydrological model, providing distributed inputs to a water quality model that simulates concentrations of biochemical oxygen demand (BOD), phosphorus, and ammonium. The framework successfully reproduces the main spatial and temporal patterns of pollutant concentrations while explicitly quantifying the uncertainty associated with hydrological predictions. Water chemical status classifications show high agreements with observations, achieving accuracies of 90% for BOD, 84.4% for phosphorus, and 85.3% for ammonium. By providing probabilistic estimates of pollutant concentrations, the framework also enables identification of periods with elevated risk of regulatory threshold exceedance. Overall, the proposed approach offers a robust and transferable methodology for integrating probabilistic hydrological forecasting with water quality assessment, supporting risk-informed river basin management under uncertainty., This work was supported by the Spanish Ministry of Science, Innovation and Universities, the Spanish Research Agency, the European Biodiversity Partnership and the European Union (NBSPLUS project, PCI2025-163161, funded by MICIU/AEI/10.13039/501100011033/ EU). Alberto Mena was partially funded by MICIU/AEI/10.13039/ 501100011033 and by the FSE+ (research contract CEX2021-001242- M-20-1/PRE2022-102012). We thank two anonymous reviewers for their helpful suggestions to improve this work.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Deep learning for streamflow forecasting in semi-arid basins

  • Alberto|||0009-0008-5865-4994
  • Bergillos-Meca, Rafael Jesús|||0000-0001-8674-5043
  • Paredes Arquiola, Javier|||0000-0003-3198-2169
  • Andreu Álvarez, Joaquín|||0000-0001-5087-5014
  • Solera Solera, Abel|||0000-0001-7464-3963
[EN] Accurate streamflow forecasting is crucial for effective water resources management, particularly in semi-arid regions increasingly impacted by climate change. This study evaluated the performance of deep learning models for streamflow forecasting in two catchments in eastern Spain. The models were trained on historical data using a one-step-ahead forecasting approach and evaluated through temporal cross-validation. A recursive multi-step forecasting strategy was subsequently used to assess predictive performance across different forecasting horizons. The long short-term memory (LSTM) models generally outperformed the multilayer perceptron (MLP) models due to their ability to capture temporal dependencies, although they exhibited high sensitivity to the length of training data and model calibration. The MLP models performed better with simple preprocessing, whereas the LSTM models benefited from combining temporal features with deseasonalization techniques. The optimal configuration for each catchment consistently delivered robust performance and reasonable predictions across various forecasting horizons. This study highlights the potential of neural network models for streamflow forecasting and provides practical guidance for implementing deep learning models in semi-arid basins, thereby contributing to improved drought risk assessment and water resources management., This work was supported by the Spanish Research Agency and the European Biodiversity Partnership for NBSPLUS project (Grant No. PCI2025-163161) and the Spanish Research Agency (Contract No. PRE2022-102012).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A pressure-impact approach to assess contamination and risk in surface water bodies

  • Aydi, Siwar
  • Paredes Arquiola, Javier|||0000-0003-3198-2169
  • Bergillos-Meca, Rafael Jesús|||0000-0001-8674-5043
  • Solera Solera, Abel|||0000-0001-7464-3963
  • Andreu Álvarez, Joaquín|||0000-0001-5087-5014
[EN] This study assesses the chemical state of surface water bodies (SWBs) in the Júcar River Basin District (Spain), specifically focusing on contaminants such as nickel, lead, imazalil, and thiabendazole. To identify risky zones, the RREA model was combined with a Python-based subroutine to estimate the minimum non-compliance load (MNCL). The results show that many SWBs fail to meet water quality criteria due to point source pollution. The RREA (Rapid Response to Environmental status) model improves monitoring capacities by confirming SWB chemical statuses and detecting locations that have not been monitored or assessed thoroughly. The study also analyzes confidence levels by comparing MNCL to the current accumulated load (CAL), allowing for the identification and prioritization of important non-compliant SWBs and locations that require additional examination. This methodology not only enhances the accuracy of compliance evaluations but also serves as a useful tool for targeted water quality management initiatives. The results of this paper highlight the potential of the proposed pressure-impact approach to assess the chemical state of SWBs. This approach is useful to support sustainable management measures that mitigate water quality issues and preserve the environmental status of SWBs., This work was carried out in the framework of the NBSPLUS project (PCI2025-163161, MICIU/AEI/10.13039/501100011033/EU). This project was funded by Biodiversa+, the European Biodiversity Partnership, under the 2023 2024 BiodivNBS joint call. It was co-funded by the European Commission (GA No. 101052342) and the following funding organisations: The Swedish Research Council for Environment, Agricultural, Sciences, and Spatial Planning (Formas), Fundação para a Ciência e a Tecnologia, I.P., Research Council of Norway, Agencia Estatal de Investigación; Fundación Biodiversidad, Estonian Research Council, Fonds de Recherche du Québec (FRQ).