Displays

Water management in cities has come a long way since the inception of early infrastructure long time ago. The modern water systems provide safe and reliable service via effective supply of clean water and collection, disposal and recycling of wastewater. However, the increasing pressures arising from the climate change, population growth and urbanisation are posing further challenges that need to be addressed in the urban environment. The advancement of new technologies such as latest artificial intelligence and machine learning methods, intelligent sensors and actuators linked via internet of things and fast 5G communication networks (to name the few) provide an opportunity to manage water in cities in a fundamentally different way that is more sustainable and resilient but also less impactful on other infrastructure systems.

The talk will start by defining what is meant by a smart water system in the context of a smart city. This will be followed by the presentation of several advanced type technologies and solutions that have been developed for the improved management of water and wastewater in urban environment. This includes new data analytics type technology for the automated detection and location of pipe bursts/leaks, equipment failures and other failure events in a water distribution system. This technology detects failure events in these system by processing pressure, flow and other data in near real-time by using artificial intelligence and other methods. In addition to saving water, energy and other resources this technology has the potential to reduce or, in some cases, prevent the negative impact of WDS failures on other infrastructure systems (e.g. impact on a transport system via major road closure following a pipe burst).

Another example that will be presented is the new technology for automated asset condition assessment of sewers. This technology, currently being commercialised,  processes standard CCTV data by using image processing and machine learning techniques to identify and classify structural and other faults in these pipes. The increased reliability and consistency of detection of these faults has the potential to reduce or remove the negative impact of related sewer failures on other critical urban infrastructure systems, e.g. impact on traffic or energy systems due to urban flooding and/or pollution that may occur as a result of non-detection.  A number of other smart water technologies and solutions will be presented. Most of these were developed in collaboration with various water utilities hence are of direct relevance to engineering practice. The talk will end with the key message that digital water approach has a huge potential to improve things in the water and other sectors.

How to cite: Kapelan, Z.: Digital Water Approach for Smarter Water Management in Cities with Interconnected Infrastructure, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-7259, https://doi.org/10.5194/egusphere-egu2020-7259, 2020.

How to cite: Caradot, N., Seis, W., Angelescu, D., Huynh, V., Hausot, A., Goffin, A., Jehanno-Leroy, P., Tabuchi, J.-P., Fatone, F., Schwarzmüller, H., and Rouault, P.: Assessing the potential of digitalization by real-time monitoring of bacterial concentration in urban water systems, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-19909, https://doi.org/10.5194/egusphere-egu2020-19909, 2020.

Water resources management is a delicate, complex and challenging task. It involves monitoring quality, quantity, timing and distribution of water in order to meet the needs of the population’s usage demand. Nowadays these decisions have to be made in a continuously evolving landscape where quantity and quality of water resources change in time with uncertainty.

Throughout history, access to clean water has always been a huge desire from urban settlements. People built towns and villages close to water sources. In most cases, streams brought clean water in and washed away polluted water. Nowadays the largest strains on water quality typically occur within urban areas, with degradation coming from point and diffuse sources of pollutants and alteration of natural flow through built-up areas.

Municipalities are acting to reduce the impact of climate change on existing cities and meet the needs of the growing urban population. In many places around the world costal flood defences were built involving construction of barriers that lock the tide and keep the water coming from in-land rivers creating reservoirs close to the shore.

These man-made barriers stop the natural cleaning action of the tide on transitional waters. This causes severe water quality problems like eutrophication and high levels of bacteria. On the positive side, these water reservoirs are used as recreational water, drinking water, agricultural water. As many more people are moving to live in urban areas, its overall demand for clean water and discharge of polluted water is constantly growing. Hence monitoring and foreseeing water quality in these urban surface waters is fundamental in order to be able to meet the water demand in future scenarios.

Many cities have already successfully implemented smart water technologies in many types of the water infrastructures. Monitoring water quality has always been a challenging and costly task. It has been so far the most difficult water characteristic to monitor remotely in real time. Lack of high frequency and accurate data has always been one of the main challenges. Today, using information and communication technologies (ICT) is possible to set up a real time water quality monitoring system that will allow to deepen the understanding of water quality dynamics leading to a better management of urban water resources.

A case study will be presented where a real time water quality monitoring system for the surface water of Bristol Floating Harbour has been deployed in the UK and water quality data have been analysed using artificial intelligence algorithms in order to understand the link between ambient weather data (i.e., precipitation, temperature, solar radiation, wind, etc.) and surface water pollution. Preliminary results of a water quality prediction model will also be presented showing the capabilities of predicting water quality as a new tool in municipality’s decision-making processes and water resources management.

How to cite: Coraggio, E., Han, D., Tryfonas, T., and Liu, W.: Monitoring and predicting water quality for smart urban water infrastructure, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-10954, https://doi.org/10.5194/egusphere-egu2020-10954, 2020.

The influence of stochastic water demand on model-based leak localization

Globally, water demand is rising and resources are diminishing. In the context of climate change and a growing world population, a further increase in water scarcity seems inevitable. Aiming towards a sustainable future, water should be used as efficient as possible by minimizing water losses, which can be higher than 50% in some drinking water networks.³ To minimize losses it is crucial to detect, localize and repair leaks as soon as possible.

Leaks cause changes in flow and pressure. By monitoring the network with pressure and flow sensors and coupling these measurements with hydraulic computer models, leaks can be detected and located. The success of this so-called model-based leak localization depends heavily on our knowledge of water demand, since every water consumption affects the pressure and flow in the network as well. Nowadays, demand is modelled based on water billing information and the network’s inflow. This study proposes a new strategy by modelling stochastic demands. Realistic residential demands are generated in high spatial and temporal resolution based on Dutch water use statistics with SIMDEUM⁴. Subsequently, the stochastic demands are used within hydraulic simulations. The influence of demand fluctuations on pressure in the system is analyzed using Monte-Carlo sampling and the corresponding effects on model-based leak detection and localization are investigated.

The proposed method is applied on a real Dutch water distribution network, containing inflow and six pressure measurements. Statistical information like the number of residents, households and annual billing information in the area is known. The corresponding hydraulic model is calibrated on pipe roughness by minimizing the mean squared error of the modelled and measured pressure at the sensor locations. Pressure driven simulations are performed and the resulting pressure changes at the sensors are simulated. Through the stochastic simulations in combination with Monte-Carlo sampling, confidence intervals for pressure changes at the sensor locations are determined and compared with the real measurements. The performance of leak detectability and localization is subsequently examined.  

This study shows that stochastic water demand simulations provide a better understanding on the reliability of model-based leak localization. By using these simulations, confidence intervals of demand related pressure changes at the sensor locations can be determined which affect the performance of leak detectability and localization under the variability of water demand. A better grip on the reliability of leak localization yields in a more efficient quest for leaks.

³_{EurEau 2017, Europe’s water in figures, an overview of European drinking water and waste water sectors, The European Federation of National Associations of Water Services}

⁴_{Blokker, E. J. M. (2010), Stochastic water demand modelling for a better understanding of hydraulics in water distribution networks, PhD thesis, Delft University of Technology}

How to cite: van Steen, J., Steffelbauer, D., Balkema, S., van der Hoek, J. P., and Abraham, E.: Fantastic leaks and where to find them, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-8305, https://doi.org/10.5194/egusphere-egu2020-8305, 2020.

Digital water and energy maps allow fast information retrieval, big data analysis and resources demand prediction for real time responses in 5-G networks. A regulatory systems framework is needed to enable and promote integrated actions grounded on map-based feedback information, to facilitate resources movements and knowledge transfer for water and energy security. At the same time, the proposed regulatory system needs to safeguard national security and personal privacy when general public and the private sectors have access to big databases.

The Guangdong-Hong Kong-Macao Greater Bay Area (GBA) in China is an initiative on regional economic development involving nine mainland cities and two Special Administrative Regions (SARs). As central policies cannot be efficiently executed in the whole regions, institutional fragmentation could be a prominent barrier to achieve regional water and energy optimum rather than individual city maxima for the water and energy nexus.

In this study, we propose a systems regulatory framework that integrates natural, urban and social systems across multiple scales in which the relevant laws, policies, decisions and actions are supported by digital maps. On a planning scale, our new regulatory system based on spatial map information promotes optimum uses of natural capitals and ecosystem services (ES). For linking different urban spatial processes on different scales, satellite images and Local Climate Zone (LCZ) maps are used to describe natural environment and urban characteristics from 200km to 10km resolutions for supporting land-use planning laws and estimating regional development carrying capacity to mitigate water and energy insecurity.

On an operational scale, smart meters and remote sensor systems provide real time water and energy information from a fast developing 5-G network for the proposed digital maps. Forecasted energy and water demands from the digital maps can be used for regional or local environment regulation reinforcement. Proposed spatial maps also improve transboundary collaboration by providing visualisation of legal targets and emission limits. Through digital maps, key agencies and sectors will have a capacity to share transboundary knowledge, information and responsibility, to foster smooth system flows in terms of culture, economy, policy and technology, by active participations and decentralized actions.

On an evaluation scale, open map information increases the transparency of legal targets and pollution limits. By rapid information retrieval and big data analysis from digital maps, regulators can assess the performance of water and energy security practices.

In summary, the proposed framework based on LCZ maps for the GBA can be applied to other rapidly developing regions with emerging 5-G networks. The integrated regulatory framework also guides water and energy security practices and transfer central policies to local actions by rapid information retrieval, big data analysis and prediction of demand for real time responses based on digital water and energy maps.

How to cite: Fan, P., Chun, K. P., Mijic, A., and Mah, D. N.-Y.: Towards an integrated regulatory framework for water and energy security with digital maps: a case study of the Guangdong-Hong Kong-Macao Greater Bay Area, China, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-3180, https://doi.org/10.5194/egusphere-egu2020-3180, 2020.

In this work, the concept of the smart rain barrel (SRB) as an IoT solution for green infrastructure is presented. The SRB are real-time controlled micro-storages (200 litre) used for an advanced rainwater management. System states and high-resolution weather forecasts from the meteorological service are integrated into the control strategy to provide adequate rainwater for irrigation requirements and to reduce peak runoff in the drainage system. The integration into the smart water infrastructure and the exchange of control commands is done via LoRaWAN, a low-power radio network. For ease of development and to demonstrate the effectiveness of the SRB concept, a two-stage approach was chosen.

First, a prototype of the SRB was built, which is in operation at the university campus of Innsbruck (Austria) during the summer months since 2019. The campus area, also denoted Smart Campus, is part of a pilot project for a “Smart Water City”. This campus is used as both, demonstration object and experimental framework for smart applications in urban water management. The Smart Campus integrates water supply and urban drainage into a joint controlled system, in which natural and anthropogenic water inflows and outflows are measured in real-time. Current measurements encompass water consumptions and pressures in the distribution system, meteorological data at different locations, filling levels in the drainage system, as well as filling levels and soil moistures of decentralised stormwater retention and infiltration systems. The temporal resolution of the measurements is depending on the application between 1 and 15 minutes. By using these high-resolution measurement data, the Smart Campus is an ideal testing ground for smart applications such as the SRB.

In addition, numerical simulations were carried out to test different control strategies and to investigate the effects of a large-scale implementation of the SRBs at community level. The results show that the SRBs can significantly improve system performance (e.g. reduce potable drinking water demand and reduce the risk of flooding) despite their small storage volumes. But the results also demonstrate, that if a large number of SRBs are implemented, a coordinated control strategy to operate SRBs and urban water infrastructure is necessary to avoid a worsening of the system (e.g. generate a combined sewer overflow by simultaneous emptying the SRBs during dry weather flow).

How to cite: Oberascher, M., Kinzel, C., Schöpf, M., Kastlunger, U., Zingerle, C., Puschacher, S., Kleidorfer, M., Rauch, W., and Sitzenfrei, R.: Towards Smart Water Cities – opportunities arising from Smart Rain Barrels for urban drainage and water supply, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-4592, https://doi.org/10.5194/egusphere-egu2020-4592, 2020.

As several cities all over the world face the exacerbating challenges posed by climate change, population growth, and urbanization, it becomes clear how increased water security and more resilient urban water systems can be achieved by optimizing the use of water resources and minimize losses and inefficient usage. In the literature, there is growing evidence about the potential of demand management programs to complement supply-side interventions and foster more efficient water use behaviors. A new boost to demand management is offered by the ongoing digitalization of the water utility sector, which facilitates accurate measuring and estimation of urban water demands down to the scale of individual end-uses of residential water consumers (e.g., showering, watering). This high-resolution data can play a pivotal role in supporting demand-side management programs, fostering more efficient and sustainable water uses, and prompting the detection of anomalous behaviors (e.g., leakages, faulty meters). The problem of deriving individual end-use consumption traces from the composite signal recorded by single-point meters installed at the inlet of each household has been studied for nearly 30 years in the electricity field (Non-Intrusive Load Monitoring). Conversely, the similar disaggregation problem in the water sector - here called Non-Intrusive Water Monitoring (NIWM) - is still a very open research challenge. Most of the state-of-the-art end-use disaggregation algorithms still need an intrusive calibration or time- consuming expert-based manual processing. Moreover, the limited availability of large-scale open datasets with end- use ground truth data has so far greatly limited the development and benchmarking of NIWM methods.

In this work, we comparatively test the suitability of different machine learning algorithms to perform NIWM. First, we formulate the NIWM problem both as a regression problem, where water consumption traces are processed as continuous time-series, and a classification problem, where individual water use events are associated to one or more end use labels. Second, a number of algorithms based on the last trends in Artificial Intelligence and Machine Learning are tested both on synthetic and real-world data, including state-of-the-art tree-based and Deep Learning methods. Synthetic water end-use time series generated with the STREaM stochastic simulation model are considered for algorithm testing, along with labelled real-world data from the Residential End Uses of Water, Version 2, database by the Water Research Foundation. Finally, the performance of the different NIWM algorithms is comparatively assessed with metrics that include (i) NIWM accuracy, (ii) computational cost, and (iii) amount of needed training data.

How to cite: Cominola, A., Becker, M.-P., and Taormina, R.: Benchmarking machine learning algorithms for Non-Intrusive Water Monitoring, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-16119, https://doi.org/10.5194/egusphere-egu2020-16119, 2020.

Residential water demands vary with a diurnal pattern, and peak hour demands lead to inefficiencies in the operation and management of urban water distribution systems. Peak demands generate immediate costs due to the energy requirements of pumping large volumes of water. If peak demands are not mitigated, large investments in infrastructure expansion are needed to support urban growth and economic development. Through data collection and communication approaches available through advanced metering infrastructure (AMI), demand-side management approaches could reduce peak demands. AMI data can be disaggregated to identify end uses that contribute to peak demands, and feedback about hourly use can be used to encourage demand shifting behaviors. Demand-side management implements technical approaches, such as retrofitting households with smart and water-efficient devices, and social approaches, such as dynamic water pricing, mandatory restrictions, and persuasive games that encourage voluntary participation. A community of households that shift demands can distribute the volume of water provision evenly over the hours of a day and reduce peak demands. While demand-side management strategies can reduce energy requirements associated with water supply and the need for new infrastructure development, demand management relies on the behaviors and decision-making of individuals, creating uncertainty in the emergent cost savings and infrastructure impacts. This research develops an agent-based modeling methodology to simulate the performance of demand-management approaches to reduce peak water demands. A persuasive game is simulated that implements a leaderboard to encourage cooperation and competition within and among neighborhoods of water users. Household agents receive points for shifting end-uses, based on the difficulty and water savings associated with end-user behaviors. Opinion dynamics simulate agents’ information exchange using a leaderboard, which provides motivation for agents to increase individual and team scores. The methodology is applied for AMI data to test the effects of persuasive games on reducing peak demands.

How to cite: Pesantez, J. and Zechman Berglund, E.: Demand-side Management of Peak Water Demands using Advanced Metering Infrastructure and Persuasive Games, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-5876, https://doi.org/10.5194/egusphere-egu2020-5876, 2020.

Worldwide, water utilities face exceptional challenges as communities are running out of water and new resources are ill-equipped to meet rising water demands. Furthermore, in many cities, years of stringent financial constraints on water utilities, unoptimized operations and the unaffordability for utilities to maintain and replace their aging infrastructure has resulted in dramatically growing leakage levels, especially in places already under high water stress. Even in Europe, as a matter of fact, nearly one quarter of treated water is lost in the distribution systems before reaching the customers. As a result, the aging water infrastructure is challenged to become more efficient.

Nowadays, an increasing number of water utilities use hydraulic simulation software to design and operate water systems in a more efficient way. However, measurements in water distribution are scarce, which results in inaccurate computer models of real systems. Recently, smart meters have become available as a promising remedy. These smart meters measure water usage of households and transmit information to water utilities in real-time. Now is the time to make water distribution simulation software fit for the future, by exploiting this new Big-data source and start a new era in hydraulic modeling, aiming to increase the operational efficiency of our drinking water systems and save our precious water resources.

This work proposes an innovative new way of combining hydraulic models, data from smart meters and stochastic demand modelling to develop beyond state-of-the-art methods to simulate water distribution systems. It is shown how data science algorithms (e.g. dynamic time warping, clustering, demand disaggregation, household activity identification, …) can be used to extract high-level information from smart meter data (e.g. daily water use routines, work schedules, socio-economic characteristics). Such information is crucial for simulating water demand accurately. Hence, data science algorithms can be used to automatically parametrize stochastic demand models (e.g. SIMDEUM) based on smart meter data, and improve their accuracy. The improved demand models are coupled with hydraulic simulations, leading to a more realistic way of simulating real water systems. Examples on a wide range of real-world applications show how these novel modelling approaches can be used to increase the operational efficiency of drinking water systems. For instance, more accurate models enable faster detection and localization of leaks in water pipes and, thus, minimize distribution losses. This work is part of the project “DASH of Water”, which aims to develop advanced data-driven stochastic hydraulic (DASH) models of drinking water distribution systems.

How to cite: Steffelbauer, D., Blokker, M., Knobbe, A., and Abraham, E.: DASH of Water – water distribution system modelling in the age of smart water meters, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-13439, https://doi.org/10.5194/egusphere-egu2020-13439, 2020.

Emergent threats in the water sector have the form of cyber-physical attacks that target SCADA systems of water utilities. Examples of attacks include chemical/biological contamination, disruption of communications between network elements and manipulating sensor data. RISKNOUGHT is an innovative cyber-physical stress testing platform, capable of modelling water distribution networks as cyber-physical systems. The platform simulates information flow of the cyber layer’s networking and computational elements and the feedback interactions with the physical processes under control. RISKNOUGHT utilizes an EPANET-based solver with pressure-driven analysis functionality for the physical process and a customizable network model for the SCADA system representation, which is capable of implementing complex control logic schemes within a simulation. The platform enables the development of composite cyber-physical attacks on various elements of the SCADA including sensors, actuators and PLCs, assessing the impact they have on the hydraulic response of the distribution network, the quality of supplied water and the level of service to consumers. It is envisaged that this platform could help water utilities navigate the ever-changing risk landscape of the digital era and help address some of the modern challenges due to the ongoing transformation of water infrastructure into cyber-physical systems.

How to cite: Nikolopoulos, D., Moraitis, G., Bouziotas, D., Lykou, A., Karavokiros, G., and Makropoulos, C.: RISKNOUGHT: Stress-testing platform for cyber-physical water distribution networks, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-19647, https://doi.org/10.5194/egusphere-egu2020-19647, 2020.

Water Distribution Systems (WDSs) are critical infrastructures that supply drinking water from water sources to end-users. Smart WDSs could be designed by integrating physical components (e.g. valve and pumps) with computation and networking devices. As such, in smart WDSs, pumps and valves are automatically controlled together with continuous monitoring of important systems' parameters. However, despite its advantage of improved efficacy, the automated control and operation through a cyber-layer can expose the system to cyber-physical attacks. One-Class classification technique is proposed to detect such attacks by analyzing collected sensors' readings from the system components. One-class classifiers have been found suitable for classifying "normal" and "abnormal" conditions with unbalanced datasets, which are expected in the cyber-attack detection problem. In the cyber-attack detection problem, typically, most of the data samples are under the "normal" state, and only small fraction of the samples can be suspected as under-attack (i.e. "abnormal" state). The results of this study demonstrate that one-class classification algorithms can be suitable for the cyber-attack detection problem and can compete with existing approaches. More specifically, this study examines the Support Vector Data Description (SVDD) method together with a tailored features selection methodology, which is based on the physical understanding of the WDS topology. The developed algorithm is examined on BATADAL datasets, which demonstrate a quasi-realistic case study and on a new case study of a large-scale WDS.

How to cite: Housh, M., Kadosh, N., and Frid, A.: Detecting Cyber-Physical Attacks in Water Distribution Systems: One-class Classifier Approach, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-22511, https://doi.org/10.5194/egusphere-egu2020-22511, 2020.

Simulation-based optimization is widely used for designing and managing water distribution networks. The process involves the use of accurate computational models, such as EPANET, which represent the physical processes taking place in the water network and reproduce the control logic governing its operations. Unfortunately, running such models requires expensive computations, which, in turn, may hinder the application of simulation-based optimization to large and complex problems. This issue can be overcome by resorting to surrogate models, that is, simplified data-driven models that accurately mimic the behaviours of physical-based models at a fraction of the computational costs. In this work, we explore the potential of Deep Learning Neural Networks (DLNN) for building surrogate models for water distribution systems. Different DLNN architectures, including feed-forward and recurrent neural networks, are trained and validated on datasets generated through EPANET simulations. The DLNN models are then used in lieu of the original EPANET model to speed-up the evaluation of the objective function employed in a simulation-based optimization problem. The effectiveness of the proposed technique is assessed on a realistic case-study involving cyber-attacks on a water network. In particular, the DLNN surrogate models are employed by an evolutionary optimization algorithm that schedules the operations of hydraulic actuators in order to best respond to the attacks and facilitate the recovery process.

How to cite: Taormina, R., Ashrafi, M., Murillo, A., and Galelli, S.: Deep Learning-based Surrogate Models for Water Distribution Systems, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-22576, https://doi.org/10.5194/egusphere-egu2020-22576, 2020.