Water leak detection using self-supervised time series classification

Leaks in water distribution networks cause a loss of that needs to be compensated ensure continuous supply for all customers. This compensation is achieved by increasing the flow network, which entails an undesirable economical expense as well negative consequences environment. For these reasons, detecting and fixing leaks relevant task companies. paper proposes leak detection method based on self-supervised classification time series. The aim detect providing low false positive rate. proposed applied two compared other methods literature, obtaining best balance between number positives detected leaks.