Rainfall-runoff simulation is vital for planning and controlling flood control events. Hydrology modeling using Hydrological Engineering Center—Hydrologic Modeling System (HEC-HMS) is accepted globally for event-based or continuous simulation of the rainfall-runoff operation. Similarly, machine learning is a fast-growing discipline that offers numerous alternatives suitable for hydrology research’s high demands and limitations. Conventional and process-based models such as HEC-HMS are typically created at specific spatiotemporal scales and do not easily fit the diversified and complex input parameters. Therefore, in this research, the effectiveness of Random Forest, a machine learning model, was compared with HEC-HMS for the rainfall-runoff process. Furthermore, we also performed a hydraulic simulation in Hydrological Engineering Center—Geospatial River Analysis System (HEC-RAS) using the input discharge obtained from the Random Forest model. The reliability of the Random Forest model and the HEC-HMS model was evaluated using different statistical indexes. The coefficient of determination (R²), standard deviation ratio (RSR), and normalized root mean square error (NRMSE) were 0.94, 0.23, and 0.17 for the training data and 0.72, 0.56, and 0.26 for the testing data, respectively, for the Random Forest model. Similarly, the R², RSR, and NRMSE were 0.99, 0.16, and 0.06 for the calibration period and 0.96, 0.35, and 0.10 for the validation period, respectively, for the HEC-HMS model. The Random Forest model slightly underestimated peak discharge values, whereas the HEC-HMS model slightly overestimated the peak discharge value. Statistical index values illustrated the good performance of the Random Forest and HEC-HMS models, which revealed the suitability of both models for hydrology analysis. In addition, the flood depth generated by HEC-RAS using the Random Forest predicted discharge underestimated the flood depth during the peak flooding event. This result proves that HEC-HMS could compensate Random Forest for the peak discharge and flood depth during extreme events. In conclusion, the integrated machine learning and physical-based model can provide more confidence in rainfall-runoff and flood depth prediction.

Water cyber-physical systems (CPSs) have experienced anomalies from cyber-physical attacks as well as conventional physical and operational failures (e.g., pipe leaks/bursts). In this regard, rapidly distinguishing and identifying a facing failure event from other possible failure events is necessary to take rapid emergency and recovery actions and, in turn, strengthen system's resilience. This paper investigated the performance of machine learning classification models – support vector machine (SVM), random forest (RF), and artificial neural networks (ANNs) – to differentiate and identify failure events that can occur in a water distribution network (WDN). Datasets for model features related to tank water levels, nodal pressure, and water flow of pumps and valves were produced using hydraulic model simulation (WNTR and epanetCPA tools) for C-Town WDN under pipe leaks/bursts, cyber-attacks, and physical attacks. The evaluation of accuracy, precision, recall, and F1-score for the three models in failure type identification showed the variation of their performances depending on the specific failure types and data noise levels. Based on the findings, this study discussed insights into building a framework consisting of multiple classification models, rather than relying on a single best-performing model, for the reliable classification and identification of failure types in WDNs.

Urban water distribution networks (WDNs) are increasingly vulnerable to diverse disruptions, including pipe leaks/bursts and cyber–physical failures. A critical step in a resilience-based approach against these disruptions is the rapid and reliable identification of failures and their types for the timely implementation of emergency or recovery actions. This study proposes a framework for sensor placement and multiple failure type classification in WDNs. It applies a wrapper-based feature selection (recursive feature elimination) with Random Forest (RF–RFE) to find the best sensor locations and employs an Autoencoder–Random Forest (AE–RF) framework for failure type identification. The framework was tested on the C-town WDN using the failure type scenarios of pipe leakage, cyberattacks, and physical attacks, which were generated using EPANET-CPA and WNTR models. The results showed a higher performance of the framework for single failure events, with accuracy of 0.99 for leakage, 0.98 for cyberattacks, and 0.95 for physical attacks, while the performance for multiple failure classification was lower, but still acceptable, with a performance accuracy of 0.90. The reduced performance was attributed to the model’s difficulty in distinguishing failure types when they produced hydraulically similar consequences. The proposed framework combining sensor placement and multiple failure identification will contribute to advance the existing data-driven approaches and to strengthen urban WDN resilience to conventional and cyber–physical disruptions.