Monitoring wastewater treatment plants with AI has been one of the most successful projects from the innovation area of Veolia group. For this purpose we build custom datasets of segmentation of different problems and test instance and semantic segmentation architectures until we find the more efficient models in external conditions monitoring water 24/7. Lighting changes conditions was a problem solved
Projects in external conditions need large collections of variate conditions to be aware of what can affect our predictions provoking false positives like fog, lighting, reflections of the sun, birds etc…
For green algae detection we are developing a very interesting project with hyperparametral cameras trying to detect the presence of chlorophyll but it’s not easy to put it in production out of the laboratory and we still working on it.
