Pasar al contenido principal

Resultados relacionados

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

Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

SOLDIER: SOLution for Dam behavior Interpretation and safety Evaluation with boosted Regression trees

  • Salazar González, Fernando
  • Irazábal González, Joaquín
  • Conde Vázquez, André
Decision making in dam safety is fundamentally based on the comparison between the predictions of a behavior model and the records of the monitoring system. Traditionally, simple linear regression models have been used. Recently, models based on machine learning are being explored, which generally offer greater precision –therefore, greater capacity for detecting anomalies –, higher flexibility and versatility. We have developed an interactive application based on R-Shiny to generate models based on boosted regression trees, evaluate their accuracy and analyze the effect of predictor variables on the system response. This allows for identifying changes in dam behavior, detecting potential anomalies and better understanding the effect of the loads on the structure. The availability of the software will contribute to the penetration of machine learning techniques in the dam engineering sector and will open the door to its use in structural health monitoring for other civil infrastructures., This work is funded by the Grant PID2021-122661OB-I00 funded by MCIN/AEI/ 10.13039/501100011033 and “ERDF A way of making Europe”. The publication is also associated to the grants: TED2021-129969B-C33, funded by MCIN/AEI/ 10.13039/ 501100011033 and the “European Union NextGenerationEU/PRTR”; CEX2018-000797-S funded by MCIN/AEI /10.13039/501100011033, and the Generalitat de Catalunya through the CERCA Program ., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Interpretation of a machine learning model for short-term high streamflow prediction

  • López Chacón, Sergio Ricardo
  • Salazar González, Fernando
  • Bladé i Castellet, Ernest
Machine learning models are increasingly used for streamflow prediction due to their promising performance. However, their data-driven nature makes interpretation challenging. This study explores the interpretability of a Random Forest model trained on high streamflow events from a hydrological perspective, comparing methods for assessing feature influence. The results show that the mean decrease accuracy, mean decrease impurity, Shapley additive explanations, and Tornado methods identify similar key features, though Tornado presents the most notable discrepancies. Despite the model being trained with events of considerable temporal variability, the last observed streamflow is the most relevant feature accounting for over 20% of importance. Moreover, the results suggest that the model identifies a catchment region with a runoff that significantly affects the outlet flow. Accumulated local effects and partial dependence plots may represent first infiltration losses and soil saturation before precipitation sharply impacts streamflow. However, only accumulated local effects depict the influence of the scarce highest accumulated precipitation on the streamflow. Shapley additive explanations are simpler to apply than the local interpretable model-agnostic explanations, which require a tuning process, though both offer similar insights. They show that short-period accumulated precipitation is crucial during the steep rising limb of the hydrograph, reaching 72% of importance on average among the top features. As the peak approaches, previous streamflow values become the most influential feature, continuing into the falling limb. When the hydrograph goes down, the model confers a moderate influence on the accumulated precipitation of several hours back of distant regions, suggesting that the runoff from these areas is arriving. Machine learning models may interpret the catchment system reasonably and provide useful insights about hydrological characteristics., This work is funded by the Grant PID2021-122661OB-I00 funded by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”. The publication is also associated to the grants: TED2021-129969B-C33, funded by MCIN/AEI/10.13039/501100011033 and the “European Union NextGenerationEU/PRTR”; CEX2018-000797-S funded by MCIN/AEI/10.13039/501100011033, and the Generalitat de Catalunya through the CERCA Program., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Predictive modeling of Enterococcus sp. removal with limited data from different advanced oxidation processes: a machine learning approach

  • Pascacio de los Santos, Pavel
  • Vicente González, David Jesús
  • Salazar González, Fernando
  • Guerra Rodríguez, Sonia
  • Rodríguez Chueca, Jorge
The removal of contaminants through Advanced Oxidation Processes (AOPs) is a complex task that demands the simultaneous consideration of multiple operating parameters, such as type and concentration of oxidant and catalyst, type and intensity of radiation, composition of aqueous matrix, etc. Designing efficient AOPs often requires expensive and time-consuming laboratory experiments. To improve this process, this study proposes a Machine Learning approach based on a Random Forest (RF) model, to predict Enterococcus sp. concentration in wastewater treated with various AOPs, even when dealing with limited data. To assess our approach under diverse conditions, a data partitioning methodology is used to categorize the different AOPs into three distinct study cases of increasing complexity, from Case I to Case III. The evaluation of the RF model’s performance, combined with the data partitioning methodology, demonstrated its usefulness in predicting missing or additional disinfection values at any instant during the AOPs. Specifically, in Case I, the model excels at generalizing predictions across various AOP treatments, followed by Case II and III, which achieve Root Mean Squared Error (RMSE) values below or comparable to the average RMSE of Case I (0.72) in 8 out of 15 and 2 out of 4 treatments, respectively. Moreover, the effects of imbalanced data on model performance are discussed. This highlights the potential of our approach to assess AOPs performance and facilitate the design of new experiments of the same treatment type without the need for additional laboratory trials, even in challenging conditions., The publication is part of Projects TED2021-129969A-C32 and TED2021-129969B-C33 funded by MCIN/AEI/ 10.13039/501100011033 and by “European Union NextGenerationEU/PRTR”. Sonia Guerra-Rodríguez acknowledges the Universidad Politécnica de Madrid (UPM) for the financial support provided through the predoctoral contract granted within the “Programa Propio”. Jorge Rodríguez-Chueca acknowledges Comunidad de Madrid by the pluriannual agreement with the Polytechnic University of Madrid in the line of action Programme of Excellence for University Teaching Staff (M190020074BJJRC). This work was also funded by the Spanish Ministry of Economy and Competitiveness through the “Severo Ochoa Programme for Centres of Excellence in R&D” (CEX2018-000797-S) and the Generalitat de Catalonia through the CERCA Program., Peer Reviewed, Postprint (published version)