Bruno Ferreira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bruno Ferreira has a total of 162 co-authors. Here are the top co-authors by number of shared publications:
- Nelson Carriço
Instituto Politécnico de Setúbal
16 shared publications - Dídia Covas
Universidade de Lisboa
8 shared publications - André Antunes
Sustain.RD, Escola Superior de Tecnologia de Setúbal, Instituto Politécnico de Setúbal, 2914-508 Setúbal, Portugal
7 shared publications - Raquel Barreira
Escola Superior de Tecnología de Setúbal, Instituto Politécnico de Setúbal 3 , Setúbal Municipality, Lisbon, Portugal
6 shared publications - João Caetano
Instituto Politécnico de Setúbal
5 shared publications - Maria Grazia Quarta
Univ. of Salento
2 shared publications
Latest Publications
- 16 August 2026
- Published by Taylor & Francis in Urban Water Journal
- p. 1-16
Practical framework for automatic pipe burst detection and location: application to a real case study
- 16 August 2026
- Published by Taylor & Francis in Urban Water Journal
- p. 1-16
Practical framework for automatic pipe burst detection and location: application to a real case study
- 1 October 2025
- Published by American Society of Civil Engineers (ASCE) in Journal of Water Resources Planning and Management
- Vol. 151 (10)
Battle of Water Demand Forecasting
- 1 October 2025
- Published by American Society of Civil Engineers (ASCE) in Journal of Water Resources Planning and Management
- Vol. 151 (10)
Battle of Water Demand Forecasting
- Open Access
- 17 September 2024
- Published by Springer Nature in Water Resources Management
- Vol. 39 (1) , 503-521
Near Real-time Leak Location by Inverse Analysis Integrating Measurement Uncertainty
This paper presents a novel model-based method for near real-time pipe burst location in water distribution networks by integrating measurement uncertainty into inverse analysis. The method accounts for expected errors between measured and computed values, providing a pipe burst location area whose size varies according to the expected error level and the burst size. The proposed method is demonstrated and compared with the traditional inverse approach using a real case study with artificial bursts of different sizes and with different pressure signal noise levels. The performance of both methods is also assessed and discussed considering the effect of seasonal water demands. The traditional inverse analysis fails to accurately locate the pipe burst events, and depending on the expected error level and pipe burst size, the obtained locations may be significantly further away from the real burst location. Conversely, the proposed method does not point to the exact burst location but provides an approximated area in which step-testing can be carried out to pinpoint the exact burst location; the size of this area can be larger or smaller depending on the burst flow rate and signal uncertainty.
- 17 September 2024
- Published by Springer Nature in Water Resources Management
- Vol. 39 (1) , 503-521
Open AccessNear Real-time Leak Location by Inverse Analysis Integrating Measurement Uncertainty
This paper presents a novel model-based method for near real-time pipe burst location in water distribution networks by integrating measurement uncertainty into inverse analysis. The method accounts for expected errors between measured and computed values, providing a pipe burst location area whose size varies according to the expected error level and the burst size. The proposed method is demonstrated and compared with the traditional inverse approach using a real case study with artificial bursts of different sizes and with different pressure signal noise levels. The performance of both methods is also assessed and discussed considering the effect of seasonal water demands. The traditional inverse analysis fails to accurately locate the pipe burst events, and depending on the expected error level and pipe burst size, the obtained locations may be significantly further away from the real burst location. Conversely, the proposed method does not point to the exact burst location but provides an approximated area in which step-testing can be carried out to pinpoint the exact burst location; the size of this area can be larger or smaller depending on the burst flow rate and signal uncertainty.
- Open Access
- 4 September 2024
- Published by MDPI AG in Engineering Proceedings
- Vol. 69 (1) , 48
Optimizing Short-Term Water Demand Forecasting: A Comparative Approach to the Battle of Water Demand Forecasting
The current paper presents a forecasting methodology for short-term water demand forecasting in the context of the Battle of Water Demand Forecasting. The methodology considers five distinct forecasting techniques, which are compared in terms of their forecasting ability for a preceding period, typically spanning a day or a week. The best-performing model is identified through error assessment between model predictions and actual measurements. This model is finally used to estimate the values for the forecasting horizon. This methodology directly considers the importance of tailoring the model to the specific case study and objectives. However, it is computationally intensive and relies on the fact that there will be not much variance between the preceding period and forecasting horizon results.
- 4 September 2024
- Published by MDPI AG in Engineering Proceedings
- Vol. 69 (1) , 48
Open AccessOptimizing Short-Term Water Demand Forecasting: A Comparative Approach to the Battle of Water Demand Forecasting
The current paper presents a forecasting methodology for short-term water demand forecasting in the context of the Battle of Water Demand Forecasting. The methodology considers five distinct forecasting techniques, which are compared in terms of their forecasting ability for a preceding period, typically spanning a day or a week. The best-performing model is identified through error assessment between model predictions and actual measurements. This model is finally used to estimate the values for the forecasting horizon. This methodology directly considers the importance of tailoring the model to the specific case study and objectives. However, it is computationally intensive and relies on the fact that there will be not much variance between the preceding period and forecasting horizon results.
- Open Access
- 5 May 2023
- Published by Taylor & Francis in Urban Water Journal
- Vol. 20 (6) , 738-750
NSGA-II parameterization for the optimal pressure sensor location in water distribution networks
The optimal location of pressure sensors is typicallysolved using heuristic algorithms. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is one of the most used algorithms in the water industry, requiring a preliminary parameter tuning process. The lack of guidelines on how to tune model parameters generally limits the use of these algorithms by researchers or practitioners and, as such, fails to be used in real-life problems. The current paper explores different NSGA-II parameterizations for the optimal location of pressure sensors by using a multi-objective optimization methodology applied to a real distribution network. Results show that (i) both the uniform and simulated binary crossover operators (depending on the internal parameters) produce the best results, being the former recommended since it does not require further parameter tuning; (ii) polynomial mutation with lower probability value should be chosen; and (iii) the distribution indices of polynomial mutation have a minor effect on NSGA-II performance.
- 5 May 2023
- Published by Taylor & Francis in Urban Water Journal
- Vol. 20 (6) , 738-750
Open AccessNSGA-II parameterization for the optimal pressure sensor location in water distribution networks
The optimal location of pressure sensors is typicallysolved using heuristic algorithms. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is one of the most used algorithms in the water industry, requiring a preliminary parameter tuning process. The lack of guidelines on how to tune model parameters generally limits the use of these algorithms by researchers or practitioners and, as such, fails to be used in real-life problems. The current paper explores different NSGA-II parameterizations for the optimal location of pressure sensors by using a multi-objective optimization methodology applied to a real distribution network. Results show that (i) both the uniform and simulated binary crossover operators (depending on the internal parameters) produce the best results, being the former recommended since it does not require further parameter tuning; (ii) polynomial mutation with lower probability value should be chosen; and (iii) the distribution indices of polynomial mutation have a minor effect on NSGA-II performance.
- 23 March 2023
- Published by IGI Global Scientific Publishing
- p. 41-55
The Challenge of the Digitalization of the Water Sector
The digitalization of the water sector is of utmost importance for improving the efficiency and sustainability of the managed systems. The digitalization process, however, can be seen as a ladder with several steps that the water utility must climb to become a smart utility. The reality is that many water utilities worldwide have not realized yet the benefits of digital transformation and, thus, the digitalization of the water sector lags behind other industries. This chapter presents the major challenges and the promising future that water utilities face in the journey of digitalization. Guidelines on how to choose the most adequate digital solution are also presented, as well as the trends for a smarter water utility.
- 23 March 2023
- Published by IGI Global Scientific Publishing
- p. 41-55
The Challenge of the Digitalization of the Water Sector
The digitalization of the water sector is of utmost importance for improving the efficiency and sustainability of the managed systems. The digitalization process, however, can be seen as a ladder with several steps that the water utility must climb to become a smart utility. The reality is that many water utilities worldwide have not realized yet the benefits of digital transformation and, thus, the digitalization of the water sector lags behind other industries. This chapter presents the major challenges and the promising future that water utilities face in the journey of digitalization. Guidelines on how to choose the most adequate digital solution are also presented, as well as the trends for a smarter water utility.
- Open Access
- 14 March 2023
- Published by MDPI AG in Journal of Imaging
- Vol. 9 (3) , 68
Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks
The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level.
- 14 March 2023
- Published by MDPI AG in Journal of Imaging
- Vol. 9 (3) , 68
Open AccessHyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks
The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level.
- Open Access
An Information System for Infrastructure Asset Management Tailored to Portuguese Water Utilities: Platform Conceptualization and a Prototype Demonstration
This paper describes a new information system developed as part of the Portuguese R&D project DECIdE. The project aimed at the development of a platform for infrastructure asset management tailored to Portuguese water utilities. The platform allows the integration of different data from several information systems of the water utilities and includes several tools for the performance assessment of the water supply systems in terms of water losses, energy efficiency and quality of service (i.e., water and energy balances and key performance indicators). The developed platform was tested with data from five small to medium size Portuguese water utilities with different maturity levels in terms of technological and human resources. The obtained results are very promising because the platform allows for periodic system performance assessment which constitutes an important part of the infrastructure asset management for small and medium-sized water utilities.
Open AccessAn Information System for Infrastructure Asset Management Tailored to Portuguese Water Utilities: Platform Conceptualization and a Prototype Demonstration
This paper describes a new information system developed as part of the Portuguese R&D project DECIdE. The project aimed at the development of a platform for infrastructure asset management tailored to Portuguese water utilities. The platform allows the integration of different data from several information systems of the water utilities and includes several tools for the performance assessment of the water supply systems in terms of water losses, energy efficiency and quality of service (i.e., water and energy balances and key performance indicators). The developed platform was tested with data from five small to medium size Portuguese water utilities with different maturity levels in terms of technological and human resources. The obtained results are very promising because the platform allows for periodic system performance assessment which constitutes an important part of the infrastructure asset management for small and medium-sized water utilities.
- Open Access
Computational Tools for Supporting the Operation and Management of Water Distribution Systems towards Digital Transformation
This paper presents a set of computational tools specially developed for supporting the operation and management of water distribution systems towards digital transformation of water services. These tools were developed in the scope of two R&D projects carried out in Portugal, DECIdE and WISDom, during 2018–2022. The DECIdE project focused on the development of tools for importing cadastral and operational data, as well as on the three operational tools for supporting the performance assessment: the first allows the calculation of different key performance indicators, both at a global and sectorial level, which is an annual requirement of the water regulator, and the other two allow the calculation of the water and the energy balances and a set of complementary indices. The WISDom project aimed at the implementation of applications that directly address specific water utility needs, namely, the flow rate data processing, the optimal location of pressure sensors, the identification of critical areas in the distribution network for pipe burst location, and the prioritization of pipes for rehabilitation. Implemented tools are useful to support water utilities in the daily operation and management of their systems, being a step forward towards digital transformation of the water sector.
Open AccessComputational Tools for Supporting the Operation and Management of Water Distribution Systems towards Digital Transformation
This paper presents a set of computational tools specially developed for supporting the operation and management of water distribution systems towards digital transformation of water services. These tools were developed in the scope of two R&D projects carried out in Portugal, DECIdE and WISDom, during 2018–2022. The DECIdE project focused on the development of tools for importing cadastral and operational data, as well as on the three operational tools for supporting the performance assessment: the first allows the calculation of different key performance indicators, both at a global and sectorial level, which is an annual requirement of the water regulator, and the other two allow the calculation of the water and the energy balances and a set of complementary indices. The WISDom project aimed at the implementation of applications that directly address specific water utility needs, namely, the flow rate data processing, the optimal location of pressure sensors, the identification of critical areas in the distribution network for pipe burst location, and the prioritization of pipes for rehabilitation. Implemented tools are useful to support water utilities in the daily operation and management of their systems, being a step forward towards digital transformation of the water sector.
- Open Access
- 6 June 2022
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 58 (6)
Flowrate Time Series Processing in Engineering Tools for Water Distribution Networks
The current paper presents a comprehensive methodology for processing unevenly (and evenly) spaced flowrate time series for subsequent use in engineering tools, such as the calibration of hydraulic models or the detection and location of leaks and bursts. The methodology is a four‐step procedure: (a) anomaly identification and removal, (b) short‐duration gap reconstruction, (c) time step normalization, and (d) long‐duration gap reconstruction. The time step normalization is carried out by a numerical procedure prior to the reconstruction process. This reconstruction process uses a pattern model coupled with regression techniques (i.e., autoregressive integrated moving average and exponential smoothing). The methodology is calibrated using Monte Carlo simulations applied to a water utility flowrate time series and validated with two additional time series from different water utilities. Obtained results demonstrate that the proposed methodology can process flowrate time series from water supply systems with different characteristics (e.g., consumption pattern, data acquisition system, transmission settings) both for normal operating conditions and during the occurrence of abnormal events (e.g., pipe bursts). This methodology is a very useful tool for the daily management of water utilities, preparing the time series to be used in different engineering tools, namely, hydraulic simulation, model calibration or online burst detection.
- 6 June 2022
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 58 (6)
Open AccessFlowrate Time Series Processing in Engineering Tools for Water Distribution Networks
The current paper presents a comprehensive methodology for processing unevenly (and evenly) spaced flowrate time series for subsequent use in engineering tools, such as the calibration of hydraulic models or the detection and location of leaks and bursts. The methodology is a four‐step procedure: (a) anomaly identification and removal, (b) short‐duration gap reconstruction, (c) time step normalization, and (d) long‐duration gap reconstruction. The time step normalization is carried out by a numerical procedure prior to the reconstruction process. This reconstruction process uses a pattern model coupled with regression techniques (i.e., autoregressive integrated moving average and exponential smoothing). The methodology is calibrated using Monte Carlo simulations applied to a water utility flowrate time series and validated with two additional time series from different water utilities. Obtained results demonstrate that the proposed methodology can process flowrate time series from water supply systems with different characteristics (e.g., consumption pattern, data acquisition system, transmission settings) both for normal operating conditions and during the occurrence of abnormal events (e.g., pipe bursts). This methodology is a very useful tool for the daily management of water utilities, preparing the time series to be used in different engineering tools, namely, hydraulic simulation, model calibration or online burst detection.