Against the backdrop of severe leakage issue in water distribution systems (WDSs), numerous researchers have focused on the development of deep learning-based acoustic leak detection technologies. However, these studies often prioritize model development while neglecting the importance of data. This research explores the impact of data augmentation techniques on enhancing deep learning-based acoustic leak detection methods. Five random transformation-based methods—jittering, scaling, warping, iterated amplitude adjusted Fourier transform (IAAFT), and masking—are proposed. Jittering, scaling, warping, and IAAFT directly process original signals, while masking operating on time-frequency spectrograms. Acoustic signals from a real-world WDS are augmented, and the efficacy is validated using convolutional neural network classifiers to identify the spectrograms of acoustic signals. Results indicate the importance of implementing data augmentation before data splitting to prevent data leakage and overly optimistic outcomes. Among the techniques, IAAFT stands out, significantly increasing data volume and diversity, improving recognition accuracy by over 7%. Masking enhances performance mainly by compelling the classifier to learn global features of the spectrograms. Sequential application of IAAFT and masking further strengthens leak detection performance. Furthermore, when applying a complex model to acoustic leakage detection through transfer learning, data augmentation can also enhance the effectiveness of transfer learning. These findings advance artificial intelligence-driven acoustic leak detection technology from a data-centric perspective towards more mature applications.

The authors regret the implementation order of data augmentation and data splitting was incorrectly stated. Data augmentation should be implemented after data splitting. While the correct implementation order and its impacts on leakage detection performance were accurately discussed in Section 3.2 “Biased results caused by data leakage”, there were errors in the highlights, abstract, and conclusions sections. The corrections are as follows: 1. The second highlight should be corrected to “Data augmentation after splitting prevents biased results due to data leakage.”2. In the abstract, the corresponding sentence should be corrected to “Results indicate the importance of implementing data augmentation after data splitting to prevent data leakage and overly optimistic outcomes.”3. In the second paragraph of the conclusions, the first sentence should be corrected to “It is recommended to implement data augmentation after data splitting to avoid data leakage, which could lead to biased and overly optimistic results.”The authors would like to apologise for any inconvenience caused.