The aim of this project is to develop a digital twin for water pipe systems to predict performance of the pipe network.

ResilienTogether is a Defra initiative in the Pix Brook catchment. Its aim is to better monitor, respond and adapt to changing flood risks over the next six years.

The project will integrate a network of smart controls to monitor, control and report on catchment responses to rainfall, in real time, to manage flood frequency and impact, water and environmental quality, community resilience and wider engagement. It will also help develop an awareness and agreement of how understanding the catchment can benefit at risk communities.

The ResilienTogether project is made up of different organisations, including Hertfordshire County Council, The University of Exeter, Bedford Group of Draining Boards, Environment Agency, Anglian Water, Bedfordshire Rural Communities Charity, Friends of Norton Common, Letchworth Garden City Heritage Foundation, Affinity Water and North Herts Council.

Led by: Central Bedfordshire Council

Funder: Defra Flood and Coastal Resilience Innovation Programme

For further information, please contact Principle Investigator Dr Peter Melville-Shreeve or visit the dedicated ResilienTogether webpage.

Application of innovative statistical models to automate process control tools that manage water pipeline infrastructure.

The aqua3S project aims to create strategies and methods that will enable water facilities to easily integrate solutions regarding water safety, through a combination of novel technologies in water safety and the standardisation of existing sensor technologies.

Exposure of citizens to potential disasters has led to vulnerable societies that require risk reduction measures. Drinking water is one of the main risk sources when its safety and security are not ensured.

aqua3S combines novel technologies in water safety and security, aiming to standardize existing sensor technologies complemented by state-of-the-art detection mechanisms. aqua3S can propose innovative solutions to water facilities and responsible authorities in order to detect and tackle water-related crises in a timely manner.

On the one hand, sensor networks are deployed in water supply networks and sources, supported by complex sensors for enhanced detection; on the other hand, sensor measurements are supported by videos from Unmanned Aerial Vehicles (UAVs), satellite images and social media observations from citizens that report low-quality water in their area (e.g. by colorization); introducing this way a bottom-up approach which raises social awareness and, also, promotes interactive knowledge sharing.

The proposed technical solution is designed to offer a very effective detection system, taking into account the cost of the aqua3S platform and target at a very high return-on-investment ratio.

The main strategy for the integration of aqua3S’ solution into the market is designed on the standardization of the proposed technologies and the project’s secure platform.

Visit the aqua3s website for further information.

So far, individual water companies have been able to use open data and Artificial Intelligence to gradually improve their performance in delivering services. Through this initiative, Severn Trent are leading this cross-sector coalition to go much further, piloting an autonomous system to monitor an entire waste catchment. By bringing together extensive testing with emerging technologies, this approach can work through huge amounts of data to provide real-time insights to help water companies reduce the risk of flooding and sewerage pollution in a catchment: delivering benefits for both customers and the environment. 

Through this project, the delivery team will be developing a tried and tested blueprint for how this approach can be scaled across the UK. More broadly, the team hope that this project can be a catalyst for wider use of AI in the water sector, building trust and demonstrating the value of this important technology. 

Led by: Severn Trent Water

Partners: South West Water, Southern Water, Thames Water, Hafren Dyfrdwy Water, Northumbrian Water, Microsoft, Rockwell, British Telecom, Blackburn-Starling, 8power, National Cyber Security Centre, University of Exeter.

Funder: Ofwat Water Breakthrough Challenge

For further information, please visit the Ofwat website. 

The aim of this Knowledge Transfer Partnership (KTP) is to develop and embed a toolset utilising Bayesian Optimisation and CFD techniques in order to enable optimisation of product function and manufacturability, and accelerate the product development process.

This is the latest part of a long term collaboration between the University of Exeter (Prof Gavin Tabor, Prof Jonathan Fieldsend) and Hydro International Ltd, developing Computational Fluid Dynamics (CFD) and Machine Learning techniques for SUDs product design. Hydro International provides products and services in the water treatment and drainage sectors including wastewater, stormwater and industrial water treatment products, and flow controls for urban drainage systems. The objective of the project is to use Bayesian Optimisation to optimise the separation of particulate waste from water using a cyclone separator very similar in function to a Dyson vacuum cleaner, but for water rather than air. The aim is for the computer to "learn" better designs for the separator trays which are at the heart of the system, providing key new IP for the company as well as a design tool which can be applied to other products in their range.

The aim of this fellowship is to develop novel technologies to facilitate the delivery of smart and resilient water systems.

The aim is to develop analytical tools to analyse big data from smart sensors at household and system levels, so as to identify vulnerabilities and inform infrastructure planning, design, operation and management decisions and thus improve resilience.

This project aimed to develop a flexible approach for water system planning and management that takes into account uncertainty and allows decision adjustments to be made as new information, new funds or new opportunities become available.

FIWARE is a smart solution platform, funded by the European Commission (2011-16) as a major flagship PPP, to support SMEs and developers in creating the next generation of internet services, as the main ecosystem for Smart City initiatives for cross-domain data exchange/cooperation and for the NGI initiative. So far little progress has been made on developing specific water-related applications using FIWARE, due to fragmentation of the water sector, restrained by licensed platforms and lagging behind other sectors (e.g. telecommunications) regarding interoperability, standardisation, cross-domain cooperation and data exchange.

Fiware4Water intends to link the water sector to FIWARE by demonstrating its capabilities and the potential of its interoperable and standardised interfaces for both water sector end-users (cities, water utilities, water authorities, citizens and consumers), and solution providers (private utilities, SMEs, developers). Specifically we will demonstrate it is non-intrusive and integrates well with legacy systems. In addition to building modular applications using FIWARE and open API architecture for the real time management of water systems, Fiware4Water also builds upon distributed intelligence and low level analytics (smart meters, advanced water quality sensors) to increase the economic (improved performance) and societal (interaction with the users, con-consensus) efficiency of water systems and social acceptability of digital water, by adopting a 2-Tier approach:

• Building and demonstrating four Demo Cases as complementary and exemplary paradigms across the water value chain (Tier#1);
• Promoting an EU and global network of followers, for digital water and FIWARE (cities, municipalities, water authorities, citizens, SMEs, developers) with three complementary Demo Networks (Tier#2).

The scope is to create the Fiware4Water ecosystem, demonstrating its technical, social and business innovative potential at a global level, boosting innovation for water.

Why Fiware4Water?

The prerequisite of Fiware4Water is to lever the barriers of the water digital sector that is facing a low level of maturity in the integration and standardization of ICT solutions, in the business processes of these solutions and relative implementation of legislative framework, as described by the ICT4Water cluster.

The related needs are how to exploit the value of data for the water sector, how to develop and test robust and cyber-secured systems, how to create water-smart solutions and applications how to ensure interoperability and higher information capacity and how to design tailored solutions addressing a real need such as optimisation, prediction, diagnosis, real-time monitoring.

For further information, please visit the Fiware4Water website.

The overall aim of the HOWS project was to develop a new approach for designing and managing improved, near-optimal and engineering-intuitive water systems by incorporating visual analytics, heuristic optimisation and feedback-informed learning.

Background

It is widely acknowledged that the water and wastewater infrastructure assets, which communities rely upon for health, economy and environmental sustainability, are severely underfunded on a global scale. For example, a funding gap of nearly $55 billion has been identified by the US EPA (ASCE, 2011). In England and Wales, the total estimated capital value of water utility assets is £254.8 billion (Ofwat, 2015), but between 2010 and 2015 only £12.9 billion was allocated for maintaining and replacing assets. Combined with the drive to reduce customers' bills, there will be even more pressure on water companies to find ways to bridge the gap between the available and required finances. As a result of this it is not surprising that optimisation methods have been extensively researched and applied in this area (Maier et al., 2014).

The inability of those methods to include into optimisation 'unquantifiable' or difficult to quantify, yet important considerations, such as user subjective domain knowledge, has contributed to the limited adoption of optimisation in the water industry. Many cognitive and computational challenges accompany the design, planning and management involving complex engineered systems. Water industry infrastructure assets (i.e., water distribution and wastewater networks) are examples of systems that pose severe difficulties to completely automated optimisation methods due to their size, conceptual and computational complexity, non-linear behaviour and often discrete/combinatorial nature. These difficulties have first been articulated by Goulter (1992), who primarily attributed the lack of application of optimisation in water distribution network (WDN) design to the absence of suitable professional software. Although such software is now widely available (e.g., InfoWorks, WaterGems, EPANET, etc.), the lack of user under-standing of capabilities, assumptions and limitations still restricts the use of optimisation by practicing engineers (Walski, 2001).

Automatic methods that require a purely quantitative mathematical representation do not leverage human expertise and can only find solutions that are optimal with regard to an invariably over-simplified problem formulation. The focus of the past research in this area has almost exclusively been on algorithmic issues. However, this approach neglects many important human-computer interaction issues that must be addressed to provide practitioners with engineering-intuitive, practical solutions to optimisation problems. This project will develop new understanding of how engineering design, planning and management of complex water systems can be improved by creating a visual analytics optimisation approach that will integrate human expertise (through 'human in the loop' interactive optimisation), IT infrastructure (cloud/parallel computing) and state-of-the-art optimisation techniques to develop highly optimal, engineering intuitive solutions for the water industry.

The new approach will be extensively tested on problems provided by the UK water industry and will involve practicing engineers and experts in this important problem domain.

For further information, please visit the HOWS website. 

This project aimed to address the issue of efficient water and energy demand resources management for the Chilean mining industry through modelling of water supply system and optimisation of its operation.

The main aim of the project was to advance knowledge about water demand in mining industry in order to develop cost-effective methodologies and tools to manage water demand by reducing water wastage, energy demand and impact on environment. This was achieved by development of an integrated water management framework to demonstrate evidence based potential of reducing impact on water in the whole water cycle (starting from seawater source to mining processes and finally when the used water is released back to environment) of mining industry.

Objectives

With focus on co-development between EU and India ensuring exploitability of its outcomes, LOTUS brings a new ICT solution for India’s water and sanitation challenges in both rural and urban areas.

High-level objectives:

1. To co-design and co-produce, jointly with EU and Indian partners, an innovative multi-parameters chemical sensor as an advanced solution for water quality monitoring in India. It shall use advanced technologies (carbon nanotubes) capable of monitoring in real time multiple contaminants and adaptable to diversified use cases in India;
2. To develop a suite of tailor-made software tools, combined into a platform with cloud-based implementation. By integrating LOTUS new sensors to advanced ICT technologies, it shall improve water management according to the specific requirements of LOTUS Use Cases, representative of water challenges in India;
3. To demonstrate and showcase the LOTUS sensor and software solution in a wide variety of Indian use cases across the whole value chain of water (urban and rural areas, drinking and irrigation water quality, river and groundwater monitoring, treated wastewater quality). Across use cases, the common goal is to improve on water availability and quality by improving on existing infrastructures, thus answering a wide range of socio-economic and technical water challenges in India;
4. To investigate, co-design and plan the business model and market uptake of the LOTUS solution, with industrial production and further development and production of the sensor in India, ensuring an advanced but affordable, low cost product and solution for monitoring water quality, after the end of the project;
5. To promote social innovation, by introducing co-creation, co-design and co-development with Universities, Research Centres, SMEs, NGOs, Utilities and local stakeholders, bringing together social sciences and technology experts, as a paradigm of successful EU-India Cooperation in the water sector, with lasting social, technological and business impacts for water quality in India, leading to viable, affordable and (socially) acceptable products and solutions, capacity development, job creation, contribution to wider issues and initiatives and wide outreach activities.

Visit the LOTUS website for further information. 

NextGen evaluates and champions transformational circular economy solutions and systems around resource use in the water sector.

NextGen aims to boost sustainability and bring new market dynamics throughout the water cycle at the 10 demo cases and beyond. Three key areas of action are foreseen.

The project will asses, design and demonstrate a wide range of water-embedded resources, including:

Water

Itself with reuse at multiple scales supported by nature-based storage, optimal management strategies, advanced treatment technologies, engineered ecosystems and compact/mobile/scalable systems.

Energy

Combined water-energy management, treatment plants as energy factories, water-enabled heat transfer, storage and recovery for allied industries and commercial sectors.

Materials

Such as nutrient mining and reuse, manufacturing new products from waste streams, regenerating and repurposing membranes to reduce water reuse costs, and producing activated carbon from sludge to minimise costs of micro-pollutant removal.

An integral part of deploying NextGen solutions will be to define and cultivate the framework conditions for success:

• Involving and engaging citizens and other stakeholders - to give feedback on technology development, increase collective learning and shape solutions and behavioural change using communities of practice and living labs. Serious gaming and augmented reality will be immersive tools to explore the circular economy and behaviour change.
• Addressing social and governance challenges - to ensure long-term adoption and support for circular economy solutions. This includes social acceptability testing, policy and regulation support and development of a European Roadmap for Water in Circular Economy.

Last but not least, NextGen will explore new business models and support market creation with three key initiatives:

• A thorough analysis, profiling and sharing of business models and services for water solutions in the circular economy;
• An online marketplace allowing users to explore NextGen showcases and demo case technologies;
• Business and marketing support to exploit the extensive new opportunities revealed by adopting a circular economy approach.

For further information, please visit the NexTGen website.

This fellowship investigates how to develop smart water infrastructure systems using Information and Communication Technologies (ICT) and big data already available in the water industry in response to a changing environment including extreme weather.

There is a critical need to develop new advanced data and visual analytics to unlock the value of large-scale water utility databases for informed real time decision making on a wide variety of different problems including leakage, flooding, water pollution and energy efficiency. This fellowship offers exactly such an opportunity, through close collaboration with Northumbrian Water Ltd, to turn piecemeal techniques into integrated solutions for industry problems, thus is timely for major impact on large investments in water infrastructure in the next 50 years.

This fellowship aims to develop the next generation advanced analytics and tools that enable real time decision making for management and operation of smart water infrastructure systems. This fellowship will promote wider deployment of sensing and measurement technologies and informed, real time decision-making. It will improve operational automation and efficiency under standard design conditions and operational resilience under extreme conditions. This fellowship is particularly important to provide a step change towards a smart water system where the sensors and controllers are linked together for fully automated decision making in response to dynamic environments.

SIM4NEXUS searched for new scientific evidence on sustainable and integrated management of resources (water, land, energy and food) in Europe and elsewhere, and adopted the Nexus concept in testing pathways for a resource-efficient and low-carbon Europe.

SIM4NEXUS increased the understanding of how water management, food production and consumption, energy supply and land use policies are linked together, and how they relate to climate action. The research activities offered solid ground on the benefits of using a Nexus approach, primarily to exploit and create synergies between policies and avoid conflicts between policies. European policies for water-land-energy-food-climate sectors reckon with trade-offs in other sectors. However, opportunities for synergies are less explored and there is no institutionalised procedure for a comprehensive Nexus assessment of new policies. New integrating themes (e.g., circular and low-carbon economy related to resource efficiency and planetary boundaries) can stimulate a Nexus approach.

Our results and products contribute to the legacy of SIM4NEXUS, including knowledge and products to be used for training (i.e., universities, policy, business and civil society organisations). Commercial applications and training courses are planned to ensure follow-up actions. A combined for-profit and non-profit exploitation strategy is developed to ensure the largest project impact, among others to contribute to policy support and future assessments, including those of the Intergovernmental Panel on Climate Change (IPCC). Side-events were organised during COP23 (Bonn, November 2017) and COP24 (Katowice, December 2018) to present progress on the Nexus and climate action.

SIM4NEXUS will seek to partner with international fora in Europe and beyond (e.g. Nexus Project Cluster), to team up for increased and more impactful communication and dissemination of the Nexus concept.

Understanding the Nexus

SIM4NEXUS has a strong research dimension. SIM4NEXUS advanced in the understanding and assessment of the Nexus in various con- texts. A framework for the assessment of the Nexus is developed to facilitate future research assessing the impacts of interventions from

a Nexus perspective. Moreover, interlinkages between water, land, food, energy and climate are now made operational, identifying both the most influential and vulnerable resources. The degrees of interlinkages are defined, including direct and indirect pathways from one Nexus component to another. The Greek case study for example, proves the food sector is the one with the most influence on other Nexus dimen- sions, while water is the most affected and vulnerable resource (Laspidou et al., 2019).

Policy Analysis

Agriculture and Food are key sectors to increase the sustainability of natural resource use.

Climate change, climate change mitigation, and adaptation put pressure on agriculture and food security. At the same time, the agro-food chain can offer solutions for these problems, for example, by replacing animal with vegetable proteins in the diet and increasing resource efficiency in the agro-food chain.

European Common Agricultural Policy can support the transition to more resource-efficient agriculture, e.g., by encouraging farmers to grow less water-demanding or non-irrigated crops, to use technologies for precision irrigation and to reduce emissions of nutrients and pesticides. To protect and restore the soil, water, biodiversity, ecosystems and the landscape, Good Agricultural and Environmental Conditions (GAEC) and Greening measures should be stricter and better maintained, and direct payment should be linked to public services instead of agricultural land area.

Successful Nexus policy has many dimensions and is multi-scale. It concerns the whole policy cycle and depends on political will, mindset, a common vision, knowledge management and careful organisation of the process, which is complex and uncertain. Pilots and scenario analyses are helpful, and monitoring of progress and results is vital, as well as collaboration between researchers, stakeholders and policymakers from the start to end of the process. Long-term engagement and financing must be part of the deal, as no sector or sectoral institution feels responsible for the Nexus between sectors. Thematic approaches stimulate a Nexus approach, such as the European ‘From Farm to Fork’ and ‘Circular Economy’ initiatives.

The following policy briefs have been published:

• Coherence in EU policy on water, land, energy, food and climate: Climate change adaptation policies (2017)
• Policy coherence of the EU Common Agricultural Policy (CAP) within the Nexus between water, energy, land, food and climate depends on policy implementation (2019)
• Implementation of EU Water Policies may benefit from synergies within the nexus between water, energy, land, food and climate (2019)
• Eight Policy Coherence Recommendation to the European Green Deal (2020)
• Landscape restoration to mitigate and adapt to climate change in Central and Eastern Europe (2020)

Thematic Models and Integration

System Dynamics Modelling (SDM) is our methodology of integration, including the modelling of multiple feedback and interaction among resources in the Nexus. SDM dates back from the 1960s. Used for studying feedback problems in industrial processes, it aims to understand how a system behaves and responds to incentives and changes. It proved to be a strong innovative methodology to test the Nexus concept.

The project builds on well known and scientifically established existing models, each to simulate different themes of the Nexus, such as Capri. E3ME, IMAGE-GLOBIO, MAGNET, MagPIE, OSeMOSYS and SWIM.

System Dynamics Modelling is used, integrating public domain data and metadata for decision and policy making.

Serious Game

SIM4NEXUS has developed a Serious Game. The Serious Game is a computer game that aids learning about the Nexus by helping users to understand and explore the interactions between water, energy, land and food resources management under a climate change context, divides the problem into manageable interventions, and allows participants to learn by doing. The ultimate goal of game development is to create a fun and interactive capacity-building tool to be used in research, educational settings and management.

The SIM4NEXUS Serious Game provides impressive user experience and state of the art technology to allow users to learn about the Nexus concepts while playing. To that end, the game relies on four main elements: the Graphic User Interface, the Knowledge Elicitation Engine, the Game Logic and the Nexus repositories.

Case studies & stakeholder engagement

Methodologies and tools to integrate the Nexus components have been tested with real-life challenges in 12 case studies at regional, national, European and global scales. The SIM4NEXUS Partners worked in close collaboration with relevant stakeholders to:

• Specify the Nexus challenges they face
• Apply the tools developed by SIM4NEXUS
• Investigate the applicability and relevance of these tools for supporting decisions and raising awareness
• Develop effective policy adaptation and implementation that supports a resource-efficient Europe.
• The science-policy participatory and iterative process established has successfully led to policy recommendations.

An amazing wealth of data has been collected, both from local sources and thematic models, and connected through the specific System Dynamic Models. Policy interventions have been tested through the Serious Game and best possible combinations towards Nexus-compliance have been identified.

The project deals with the use of data mining techniques on the Royal Mail risk database. A sample database was supplied on which encouraging results were found. The data mining techniques employed here each attempt to find patterns and trends in a database with greater accuracy than standard statistical techniques. These are designed to find relationships between seemingly unrelated sets of data. The data in the risk database consists of several attributes of a Post Office and the number of incidents it has suffered in the past three years. The task of the data mining tool is to find what (if any) reasons there are behind an office being more prone to incident than another. Each technique had different errors on the Royal Mail database.

Typically, the error was around 20-25% depending on the technique used. The inclusion of the postcode information in the South West database, late on in the project has yielded errors of less than 1%. Each of the techniques has a very different output and the collation of this information is one of the difficult points of the project. Generally, these techniques output a set of rules in IF?AND?.THEN format. These are understandable, but if there are large numbers of them it can be tedious applying these rules to new cases. The use of the results of these data mining techniques requires some automation, especially with rulesets of 50 rules or more. To enable this, an easy-to-use program was developed to allow users to test a new Post Office against the results from the data mining techniques. It is hoped that this flexible piece of software will allow the inclusion of the results of any of the techniques and to test any office regardless of how much information about it is known.

The objective identified in the proposal was the investigation of potential applications for genetic programming (GP) that would be of benefit to the water industry. The proposal also stressed that the project would develop a novel algorithm and that the investigation would not simply consist of applying the existing genetic programming (Koza, 1992; 1994) algorithm to selected problems. The importance of comparing the new method with existing techniques was also identified. In recent years many methods for creating "black box" mathematical models have been reported in the engineering literature. The methods include artificial neural networks, polynomial networks and genetic programming.

Research literature has tended to emphasise the benefits of these new methods, particularly the ability to automatically create mathematical models without having to specify the form of an equation in advance, as many older regression methods require. However, the literature has tended to downplay one of the major disadvantages of the new methods, the inability to determine confidence limits on predictions. Measures of error or uncertainty are often critical for models used in engineering applications where the consequences of error may include damage to property or loss of life. After preliminary examination the original method of genetic programming (i.e., Koza-style GP and symbolic regression in particular) was found to be deficient in a number of aspects in addition to the inability to provide confidence limits. These include:

• Resulting models are not necessarily smooth and can have peculiar discontinuities or spikes. These result from the use of conditionals (if ? then statements) and a mathematical exception used to force closure under division. To avoid division overflow errors the exception is made that division by zero produces zero rather than infinity.
• Resulting models are often very complex and difficult to interpret. There is no comprehensive method to determine if models are overfit or underdetermined.

Solutions are generally not very good.

It was concluded that in the original form, genetic programming had been largely oversold and was not suitable for real-world civil engineering applications.

The first phase of the project was to develop an improved GP methodology by incorporating classical statistical methods for parameter optimisation into symbolic regression. Classical parameter optimisation would both improve the quality of solutions and allow for estimation of confidence limits. The development of a method that automatically generates (evolves) mathematical models that are amenable to statistical inference represents the best aspects of both approaches, provided that the resulting models are competitive in terms of accuracy with other methods. A new technique of this type would have much wider applications than water resources engineering alone. The technique could be used in any field where predictive or simulation models are used and minimising computational effort or the accurate assessment of uncertainty in predictions is critical.

References

• Davidson, J. W., D. A. Savic and G. A. Walters (2001a) Prediction error in rainfall-runoff models part 1: Overfitting, Water Resources Research, in preparation.
• Davidson, J. W., D. A. Savic and G. A. Walters (2001b) Prediction error in rainfall-runoff models part 2: Probability density function of error, Water Resources Research, in preparation.
• Davidson, J. W., D. A. Savic and G. A. Walters (2000a) Symbolic and numerical regression: experiments and applications. Accepted for publication in Journal of Information Sciences.
• Davidson, J. W., D. A. Savic and G. A. Walters (2000b) Rainfall Runoff Modelling Using a New Polynomial Regression Method. 4th International Conference on Hydroinformatics, University of Iowa, Iowa City, USA.
• Davidson, J. W., D. A. Savic and G. A. Walters (2000c) Approximators for the Colebrook-White Formula Obtained through a Hybrid Regression Method. XIII International Conference on Computational Methods in Water Resources, University of Calgary, Calgary, Canada.
• Davidson, J. W., D. A. Savic and G. A. Walters (2000d) Symbolic and numerical regression: experiments and applications. Proceedings of Recent Advances in Soft Computing 2000, De Montfort University, Leicester, 175-182.
• Davidson, J. W., D. A. Savic and G. A. Walters (1999a) Symbolic and numerical regression: a hybrid technique for polynomial approximators. Proceedings of Recent Advances in Soft Computing ?99, De Montfort University, Leicester: 111-116.
• Davidson, J. W., D. A. Savic and G. A. Walters (1999b) Method for the identification of explicit polynomial formulae for the friction in turbulent pipe flow. Journal of Hydroinformatics 1(2) 115-126.
• Savic, D. A., G. A. Walters and J. W. Davidson (1999) A genetic programming approach to rainfall-runoff modelling, Water Resources Management, 13 (1999) 219-231.

AQUATOR® is a commercial software for developing and running simulation models of natural rivers, water resources and water supply systems, using different operational rules, constraints and priorities. Developed by Oxford Scientific Software, it is being used by several water companies in the UK. The Centre for Water Systems has undertaken the task of linking AQUATOR to a Multiobjective Genetic Algorithms optimisation module.

Initially GANetXL, an add-in for Microsoft Excel®, developed by the Centre for Water Systems was linked to AQUATOR, for the optimization of reservoir operation.

However due to the excessive computational time required, AQUATOR-GA, a new GA application was developed, using distributed computing, which has been integrated within the AQUATOR environment.

It has already been applied to two case studies, both reservoirs operated by United Utilities.

For more information see:

• Reservoir optimisation-Aquator-GaNetXL (poster)
• Seminar GA-AQUATOR-presentation Dec 2008 (presentation)

Contact

• Professor Dragan Savic
• Dr Lydia Vamvakeridou-Lyroudia

Funding body: ERASMUS scheme (European Community)

This project presents an application of Neural Networks (NNs) to rainfall-runoff modelling. Applications of the neural network technique in this domain of hydrology have so far provided accurate results for small storm events on theoretical catchments (Minns & Hall, 1995). The aim of the research presented in this report was to investigate the application of NNs, as 'black-box' models of rainfall-runoff processes, on real catchments. The NN approach is tested and compared to optimised conceptual hydrological models applied to a catchment over a period of several years. At the same time, all tests and experiments were done in parallel with a Genetic Programming technique (Cousin, 1997).

Thus, the performance of both data-driven methods could be compared to the model-driven approach (conceptual models). This report demonstrates how a NN and GP can be set up to obtain the best results given the necessary input data. The study revealed that the choice and preparation of calibration data sets are more important than the fine-tuning of the NN (choice of optimal parameters). Both GP and NN had similar behaviours and the final results were quite close to the model-driven approach results in terms of correlation and possible evaluation parameters.

References

• Jacq, F. and D.A. Savic, (1997), Rainfall-Runoff Modelling Using Neural Networks, Centre For Systems And Control Engineering, Report No. 97/02, School of Engineering, University of Exeter, Exeter, United Kingdom, p.66.
• Cousin, N. and D.A. Savic, (1997), A Rainfall-Runoff Model Using Genetic Programming, Centre For Systems And Control Engineering, Report No. 97/03, School of Engineering, University of Exeter, Exeter, United Kingdom, p.70.

Funding body: ERASMUS scheme (European Community)

Data driven modelling techniques have gained in popularity in the last 20 years. They are more cost effective compared to the development of mechanistic models. Furthermore, those mechanistic models are highly non-linear and complex, which makes them difficult to identify and use. Currently, the majority of data driven modelling methods can be categorised under two headings: artificial neural networks and statistical and regression analysis. Neural networks can usually provide models that are capable of good predictions, but they don't give any insight into the structure of the process. They are commonly called black boxes, one puts the data in and gets results from the model, but does not know anything about the underlying relationships between input and output data. It is usually desirable to gain some insight into the underlying process structures, as well as make accurate numeric predictions. The aim of this work is to develop a computer software, that uses genetic operations in order to find a symbolic equation describing the relationship between input and output data.

The structure and hence the complexity of the model or the equation is not specified like in the conventional regression, which seeks to find the best set of parameters for a pre-specified model. This new technique is called symbolic regression. Standard, bit-coded genetic algorithms are inadequate to represent varying sizes and shapes, hence the genetic programming technique is used.

References

• Pyhnen, H.O. and D.A. Savic, (1996), Symbolic Regression Using Object-Oriented Genetic Programming (in C++), Centre For Systems And Control Engineering, Report No. 96/04, School of Engineering, University of Exeter, Exeter, United Kingdom, p.72.