Water distribution systems (WDSs) deliver water from sources to consumers. These systems are made of hydraulic elements such as reservoirs, tanks, pipes, valves, and pumps. A pump is characterized by curves which define the relationship of the pump’s head gain and efficiency with its flow. For a new pump, the curves are provided by the manufacturer. However, due to its operating history, the performance of a pump deteriorates, and its curves decline at an estimated rate of about 1% per year. Pump curves are key elements for planning and management of WDSs and for monitoring system efficiency, to determine when a pump should be rehabilitated or replaced. In practice, determining pump curves is done by field tests, which are conducted every few years. This leaves the pump’s performance unmonitored for long time periods. Moreover, these tests often cover only a small range of the curves. This study demonstrates that in the era of IoT and big data, the data collected by Supervisory Control And Data Acquisition (SCADA) systems can be used to continuously monitor pumps’ performance and derive updated pump characteristic curves. We present and demonstrate a practical methodology to estimate fixed and variable speed pump curves in pumping stations. The proposed method can estimate individual pump curves even when the measurements are given only for the pumping station as a whole (i.e., total flow, pumping station head gain). The methodology is demonstrated in a real-world case study of a pumping station in southern Israel.