Benchmarking dataset for leak detection and localization in water distribution systems

This paper presents a dataset with two hundred and eighty sensory measurements for leak detection and localization in water distribution systems. The data were generated via a laboratory-scale water distribution system that included (1) three types of sensors: accelerometer, hydrophone, and dy-namic pressure sensor; (2) four leak types: orifice leak, lon-gitudinal and circumferential cracks, gasket leak, and no-leak condition; (3) two network topologies: looped and branched; and (4) six background conditions with different noise and demand variations. Each measurement was 30 s long, and the measurement frequencies were 51.2 kHz for the ac-celerometer and dynamic pressure sensors, and 8 kHz for the hydrophone. This is the first publicly available dataset for ad-vancing leak detection and localization research, model vali-dation, and generating new data for faulty sensor detection in water distribution systems. (c) 2023 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )