Pasar al contenido principal

MEJORA DE LAS PREVISIONES DE INUNDACION GENERADAS CON MODELOS DE BASE FISICA MEDIANTE TECNICAS DE INTELIGENCIA ARTIFICIAL

PID2023-148074OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDADE DA CORUÑA

Resultados relacionados

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

RUC. Repositorio da Universidade da Coruña
Publicación Reseña (Review)

Recent Advances and Future Challenges in Urban Pluvial Flood Modelling

  • Cea, Luis
  • Sañudo, Esteban
  • Montalvo Montenegro, Carlos Israel
  • Farfán-Durán, Juan F.
  • Puertas, Jerónimo
  • Tamagnone, Paolo
[Abstract]: Urban pluvial floods are characterised by a number of features such as the high spatial and temporal resolution needed to capture their dynamics, the complexity of dual drainage systems and the lack of sewer data availability, which make them very different from other types of floods, like coastal or fluvial floods, and which increase the difficulty of modelling them. As a consequence, most flood management plans do not include a rigorous evaluation of urban pluvial flood risk. In this paper, we give a comprehensive view of the current state of urban pluvial flood modelling, not restricted to a mere description of the mathematical approaches, but also including the most relevant features that should be considered in their modelling, the validation studies that have been performed to date and our vision on the modelling challenges that should be addressed in the near future., This work was received financial support by the Spanish Ministry of Science and Innovation (MCIN/AEI/10.13039/501100011033) through the project “SATURNO: Early warning against pluvial flooding in urban areas” (PID2020-118368RB-I00) and the project “AI4FLOOD: Enhancing Physically-based Flood Forecasting with Artificial Intelligence” (PID2023-148074OB-I00), funded by MICIU/AEI/10.13039/501100011033 and FEDER, UE. Carlos Montalvo received funding from the FPI predoctoral grant awarded by the Spanish Ministry of Science, Innovation, and Universities (PRE2021-098425).
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Sewer Network Data Completeness: Implications for Urban Pluvial Flood Modelling

  • Montalvo Montenegro, Carlos Israel
  • Tamagnone, Paolo
  • Sañudo, Esteban
  • Cea, Luis
  • Puertas, Jerónimo
  • Schumann, G.
[Abstract]: 2D/1D dual drainage models are one of the most useful tools for studying urban pluvial flooding. However, the accuracy of these models depends on data quality and completeness. This study assesses the effects of sewer network data completeness on the results of the 2D/1D free distribution model Iber-SWMM. The research is conducted in two case studies: Differdange (Luxembourg) and Osuna (Spain), considering six different return period storms. Different scenarios of data completeness were generated by simplifying the original sewer network, based on two characteristics of the conduit segments: the Strahler Order number and the length. Each scenario was evaluated by comparing the maximum flood extent maps obtained. The results indicate that the lower the degree of data completeness, the higher the overestimation of the maximum flood extent. For 80% completeness, the False Alarm Ratio is less than 0.05, but it can increase exponentially to over 0.30 when network completeness drops to 20%. However, if the available information includes the most important conduits, such as the main collectors, errors are minimal. Furthermore, if the data on surface elements (inlets) is also complete, the accuracy of flood modeling is maintained compared to the complete data scenario. These results can contribute to the simplification of flood model setup in large urban areas, where not always complete sewer network data sets are available and information preprocessing can be complex and time-consuming, and the computation of the network in SWMM can become a bottleneck in the simulation., This project has received financial support from the Spanish Ministry of Science and Innovation (MCIN/AEI/10.13039/501100011033) within the project “SATURNO: Early Warning Against Pluvial Flooding in Urban Areas” (PID2020-118368RB-I00), as well as from the project “AI4FLOOD: Enhancing Physically-based Flood Forecasting with Artificial Intelligence (PID2023-148074OB-I00)”. Additionally, funding was provided by the FPI predoctoral grant from the Spanish Ministry of Science, Innovation, and Universities (PRE2021-098425). The work developed by Esteban Sañudo is funded initially by the project “DRAIN – Digital RAIN. An Integrated Urban Drainage Model” (CPP2021-008756), financed by MICIU/AEI/10.13039/501100011033 and the European Union NextGenerationEU/PRTR, and subsequently by the Postdoctoral Fellowship Programme of the Xunta de Galicia (Consellería de Educación, Ciencia, Universidades e Formación Profesional) (Ref. ED481B-2025/090). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED481B-2025/090, Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Integrating Net Rainfall Calculation in Deep Learning-Based Surrogate Modeling Frameworks for 2D Flood Prediction

  • Farfán-Durán, Juan F.
  • Montalvo Montenegro, Carlos Israel
  • Cea, Luis
  • Leitão, J. P.
[Abstract]: This study proposes a novel deep learning (DL)-based surrogate model that incorporates the calculation of net rainfall using the SCS-CN method, providing a flexible framework for evaluating the influence of rainfall events under different antecedent moisture conditions (AMC). The proposed framework involves establishing a ground truth model (Iber-SWMM) and defining the necessary terrain features and rainfall patterns for training the surrogate. A benchmark surrogate model using only gross rainfall, replicating methodologies from previous studies, is also developed for comparison. The trained models are then applied to predict water depth maps using test rainfall patterns under different scenarios, both with and without net rainfall. The results demonstrate that the proposed surrogate model reduces the computational times of Iber-SWMM by 2 to 4 orders of magnitude while outperforming the benchmark surrogate in all the measures. It presents satisfactory accuracy in water depth prediction, with 80% to 95% of predictions within a -0.2 to 0.2 m error range and hit ratios between 0.87 to 0.91 in terms of flooded pixels in the more extreme events. These outcomes are comparable to those achieved by a physics-based model on one of the test events. The study also suggests future lines for refinement., This project has received financial support from the Spanish Ministry of Science and Innovation (MCIN/AEI/10.13039/501100011033) within the project “SATURNO: Early Warning Against Pluvial Flooding in Urban Areas” (PID2020-118368RB-I00), as well as from the project “AI4FLOOD: Enhancing Physically-based Flood Forecasting with Artificial Intelligence (PID2023-148074OB-I00)”. Additionally, funding was provided by the FPI predoctoral grant from the Spanish Ministry of Science, Innovation, and Universities (PRE2021-098425). Funding for open access charge: Universidade da Coruña/CISUG., Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG