Photographs gathered by community groups have been used to train a new artificial intelligence model to “spot visual markers of river health.” The developers, who include the UK’s Water Research Centre (WRc), said they “hope that the tool can be rolled out across the UK.”
WRc, Rain++ and students at the National Taiwan University (NTU) said they have used 15,700 images submitted by members of the Friends of Bradford’s Becks community group to “test and train AI models” to recognise “visual markers of river health” — including the presence of wildlife, outfalls discharging into the river, rubbish, obstructions to fish passage, channel modifications and discolouration. Funding for the project was provided by Natural England.
WRc technical lead, Dr Amy Jones, said: “Using image recognition models to tackle environmental challenges is an approach that is starting to gain momentum but, as far as we are aware, using it to identify pollution in rivers from citizen photos is a world first.”
Jones said the chemical and physical monitoring equipment normally used by the Environment Agency and water industry was “expensive and complicated to set up and maintain,” while camera monitoring could offer “a cheaper, more accessible way to monitor river health, supplementing traditional methods.”
She added: “The AI model can be used to see what citizen photos tell us about the health of Bradford’s Becks. Maps of the results can then be used to identify hotspots, outfall locations or areas close to sewage litter, which could then be a priority for further investigation by the water company or local authority. “When applied alongside conventional monitoring, the model has the potential to be really powerful.”
She noted that the number of photographs required to train the AI model “made the analysis challenging”. She said that the six-month funding from Natural England has enabled the project team to build the initial model and with renewed funding for 2024, more manually labelled photos can be incorporated into the data set, improving the model’s accuracy.
Cameras will be installed on Bradford’s Becks to test the model’s ability to continually monitor for pollution events. Although it is still under development, the model and its documentation have already been made freely available on the online developer platform GitHub.
Natural England senior advisor, Dr Rachel Palfrey, said: “This innovative project, using technology to help us protect, restore and enhance water quality within the Bradford District forms part of our wider Nature Recovery Project across Bradford and the South Pennines. It also has the potential to revolutionise how we monitor river quality, making it easier to see what is happening, when it is happening and where, so we can act accordingly.”
Commentaires