Digital twin technology is set to play a crucial role in the pre-emptive management of sewer flooding, argues John Hicklin from Iotics, a firm that specialises in this way of working with data.
The UK is investing heavily into smarter infrastructure for its water management. Currently in the initial phase of Ofwat’s seventh Asset Management Plan (AMP7), the industry is set to benefit from a £51bn investment in infrastructure development, of which £13bn is allocated for providing resilient services and improved environmental performance. The five-year plan that runs from 2020-2025 is focused on investing in the long-term strategic use of smarter assets and demand management.
It’s long overdue: the deterioration of the nation’s ageing water infrastructure means that events such as sewer flooding are becoming increasingly common. Described by the Ofwat and Water UK supported website Discoverwater as ‘unpleasant and distressing,’ water companies are spending millions every year to prevent sewer flooding. According to Discoverwater, in 2019 there were more than 3,250 homes affected (“internal events”) in England and Wales, with a further 23,500 “external events” on private land and gardens.
When flooding of towns and cities occurs due to excessive rainfall, storm surges, or the overloading of inadequate assets, the ensuing media and political reaction tends to present these events as “unexpected”. The reality is that most sewer flooding events, aren’t unexpected, and are caused by systemic failures in long-term planning and preparation.
Research shows that customers suffering from such domestic disasters tend to become housebound, and unwilling to leave their homes in case of further flooding. Despite there being plenty of guidance available to the general public related to how they can play their part in preventing sewer floods such as, “what not to flush down the toilet” and so on, the long-term responsibility clearly lies in the hands of the water industry.
A twin approach
A key technology poised to assist with meeting AMP7’s objectives – particularly in the operation of sewer networks – is digital twinning, an intelligent system that provides virtual representation of physical entities, data management and interactive feedback to the real-world process. This intelligence can help water utilities ensure regulatory compliance in areas such as sewer flooding, pollution management, and network capacity. And it can help address challenges such as legacy infrastructure, increasing usage demands and the effects of climate change. Much of this pressure can be mitigated by integrating digital twin technology into water networks. The cost of communications, sensors and data storage is coming down, while data analytics is becoming more sophisticated.
Digital twins can bring pre-emptive management to the water industry, connecting the physical and digital worlds to produce insights and outcomes in relation to areas such as usage and maintenance. Current models are often constrained by computing resources and cannot run in real-time, and so fall short of providing usable predictions on the location and frequency of flooding events.
A data-driven representation of assets, processes and systems, a twin can provide an evolving picture of an asset’s current performance and weaknesses, while helping to identify where investment needs to be prioritised. But the benefits of the technology extend beyond simply providing a model or visualisation. Twins convert data from physical assets into insights that can help operators to make strategic decisions and interventions, improve operations, and help shape plans and projects.
In the case of Arup’s digital twin solution, powered by its bespoke algorithm and Iotics’ platform, network operators are able to act pre-emptively, leading to reduced operational costs and greater efficiency. The digital twin models created by Arup and Iotics are abstractions of the complexity of an operator’s data estate, an approach that models data sources and allows interaction without costly, time-consuming integrations or re-architecting of internal data and systems. Virtualising the interaction has the further benefits of supporting up-scaling over time as operator needs grow, while being source- and system-agnostic.
Digital twins allow users to make data-driven predictions powered by machine learning (ML). For example, a digital twin under development at Arup uses ML to understand and learn from the behaviour of a specific system and predict the location of future flooding or pollution. Using sensors throughout the catchment, the algorithm learns the behaviours of each sensor, the relationships between the sensors, and the impact weather has on them. The algorithm trains a set of ML models that is optimised for every sensor.
As tools, digital twins work best when built on open, shared data standards, enabling as wide a range of information sources as possible to be interconnected within the system, allowing it to talk to other parts of an operator’s infrastructure. These principles enable an aligned approach to information management across the built environment, establishing agreed definitions and principles from the outset, making it easier to share data in the future.
Speaking more broadly about the technoloy’s promise, Arup’s Vikki Williams says: “All over the world regulators are raising standards for the built environment. So a major part of our work is developing digital twins for existing buildings and assets, retroactively bringing them into the data-intelligence era.”
“Soon a digital twin strategy will be an expectation when proposals are reviewed by investors, insurers and banks. Given the lifespan of assets this is both an urgent and exciting priority. Data is increasingly recognised as another asset on company balance sheets, one that historically has often gone unnoticed. The ability to review and interpret data – from seasonal changes in sales or changing demand on a nation’s energy network – strengthens an organisation’s ability to pivot its business model, develop new services or anticipate costs. Adopting a digital twin approach unlocks the value of your business data.”