TECHNICAL FEATURES
to be quickly captured with a picture quality sufficient to identify manhole covers and suggest the route of the sewer.
It is not as easy as a simple dot-to-dot exercise, however. Manhole covers grant engineers access to more than just the water network – they also give access to electricity, gas and internet cables. Our knowledge of the sewer system must therefore be used to interpret the images, combined with the types of houses and their known infrastructure, to infer a likely route. These inferred networks can then be overlayed on our street maps to gain a picture of these unseen systems.
At present, WRc has successfully completed a pilot programme for Thames Water to put this principle into practice. The team has mapped three 1 km2 areas of known pipework by studying aerial photography and applying knowledge and experience of the sewer systems to suggest what it believes to be the route of the networks. Through this process, the team has been able to demonstrate an 80–90% success rate of inferred sewers against what is known.
This research is showing that the technique does work in practice. But to drive this forward as a truly scalable solution that water companies can rely on to bring visibility to these unknown sections of sewer, technology is only taking us part of the way. There is still a great reliance on human knowledge and experience to turn these aerial photographs into usable references for the networks. That process is still intensive to truly scale this as a solution.
As the approach matures and technicians become more familiar with the process, could it be the case that AI can make this a viable solution? By harnessing the technical domain knowledge held by specialists, those who inform the creation of the inferred networks, WRc and its RSK partners are exploring how to train an AI solution to create the inferred networks according to the defined property age and type and then fitting this configured network to the identified drainage features such as manholes and soil vent pipes. This approach would use that same knowledge to automate the digitisation process, enabling the mapping operation to become much less
intensive. This would enable our WRc engineering and data specialists to focus on reviewing and ensuring the accuracy of networks, speeding up the process and improving its accuracy.
The technology is certainly there; we now need to venture into the unknown and make it a reality.
Peter Henley is a principal consultant at WRc with 36 years’ experience in the water industry. He specialises in sewer operations as the head of pollution and flooding reduction. He is a member of the Institute of Water and was recently awarded its Pride in the South-West Award for his work in promoting the 3Ps message (poo, pee and paper only) and reducing sewer blockages.
M A G A Z I N E
G E T I N VO LV E D !
22
| March 2025 |
draintraderltd.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80
