A fully AI-based system to automate water meter data collection in Morocco country

With the growing demand for water resources, the need for monitoring has become a necessity for rational and sustainable use of this resource. Water meter data collection is an essential step toward this goal. In Morocco, this task is performed manually at most once a month due to constraints related to the cost and time. In general, the consumption is estimated and calculated based on the average consumption recorded in the previous months. This causes many claims from customers because of higher invoices, which does not reflect reality. In this paper, we propose a fully AI-based system to automate water meter data collection, which is composed of a Recognition System (RS) and a web services platform. This framework offers multiple services for both customers and water service providers, such as consumption monitoring, detecting water leaks, visualizing water consumption, and potable water coverage in a geographic map. It also provides a powerful tool to help ensure accurate decision making with multiple reporting services. The main component of the RS is the Convolutional Neural Network model trained on a proposed MR-AMR (Moroccan Automatic Meter Reading) dataset. In the model test phase, we achieved an accuracy of 98.70%. Our system was tested and validated by experiments.