Detecting and Localizing Cyber-Physical Attacks in Water Distribution Systems without Records of Labeled Attacks.

Modern water distribution systems (WDSs) offer automated controls and operations to improve their efficiency and reliability. Nonetheless, such automation can be vulnerable to cyber-attacks. Therefore, various approaches have been suggested to detect cyber-attacks in WDSs. However, most of these approaches rely on labeled attack records which are rarely available in real-world applications. Thus, for a detection model to be practical, it should be able to detect and localize events without referring to a predetermined list of labeled attacks. This study proposes a semi-supervised approach that relies solely on attack-free datasets to address this challenge. The approach utilizes a reduction in dimensionality by using maximum canonical correlation analysis (MCCA) followed by support vector data description (SVDD). The developed algorithm was tested on two case studies and various datasets, demonstrating consistently high performance in detecting and localizing cyber-attacks.

Identifying barriers for nature-based solutions in flood risk management: An interdisciplinary overview using expert community approach.

The major event that hit Europe in summer 2021 reminds society that floods are recurrent and among the costliest and deadliest natural hazards. The long-term flood risk management (FRM) efforts preferring sole technical measures to prevent and mitigate floods have shown to be not sufficiently effective and sensitive to the environment. Nature-Based Solutions (NBS) mark a recent paradigm shift of FRM towards solutions that use nature-derived features, processes and management options to improve water retention and mitigate floods. Yet, the empirical evidence on the effects of NBS across various settings remains fragmented and their implementation faces a series of institutional barriers. In this paper, we adopt a community expert perspective drawing upon LAND4FLOOD Natural flood retention on private land network (https://www.land4flood.eu) in order to identify a set of barriers and their cascading and compound interactions relevant to individual NBS. The experts identified a comprehensive set of 17 barriers affecting the implementation of 12 groups of NBS in both urban and rural settings in five European regional environmental domains (i.e., Boreal, Atlantic, Continental, Alpine-Carpathian, and Mediterranean). Based on the results, we define avenues for further research, connecting hydrology and soil science, on the one hand, and land use planning, social geography and economics, on the other. Our suggestions ultimately call for a transdisciplinary turn in the research of NBS in FRM.

Characterization of Localities with a High Likelihood of Illicit Connections between Runoff and Sewage Systems.

Flooding of the sewage system is an environmental hazard often caused by illegal connections between drainage and sewage systems. The timely detection of such illicit connections, often done by property owners in an attempt to remove rainwater promptly from their private courtyards, is a complex task due to the high cost of field surveying and limited manpower of environmental law-enforcement authorities. This paper suggests an empirical approach to the identification and characterization of localities with an elevated likelihood of illegal connections between runoff and sewage systems. The proposed approach is implemented in three stages. First, the association between rainfall and the amount of wastewater arriving to sewage treatment facilities from different localities is analyzed. Next, regression residuals are investigated, to identify localities with an especially strong association between the amount of rainfall and sewage surplus. The identified localities are then analyzed, to determine their geographic location, physical and socioeconomic attributes. In the present study, the proposed approach is tested using data for 623 urban and rural localities in Israel. As the study shows, the probability of association between the amount of rainfall and sewage surplus, which we consider as an indicator of pirate connections between drainage and sewage systems, tends to increase as a function of socioeconomic welfare of the local residents, surface slope, and the level of urbanization. The proposed approach can help law-enforcement authorities to focus their efforts on specific locations and to reduce economic and environmental damages associated with illegal connections between drainage and sewage systems.

Model-based approach for cyber-physical attack detection in water distribution systems.

Modern Water Distribution Systems (WDSs) are often controlled by Supervisory Control and Data Acquisition (SCADA) systems and Programmable Logic Controllers (PLCs) which manage their operation and maintain a reliable water supply. As such, and with the cyber layer becoming a central component of WDS operations, these systems are at a greater risk of being subjected to cyberattacks. This paper offers a model-based methodology based on a detailed hydraulic understanding of WDSs combined with an anomaly detection algorithm for the identification of complex cyberattacks that cannot be fully identified by hydraulically based rules alone. The results show that the proposed algorithm is capable of achieving the best-known performance when tested on the data published in the BATtle of the Attack Detection ALgorithms (BATADAL) competition (http://www.batadal.net).

Integrating physically based simulators with Event Detection Systems: Multi-site detection approach.

The Fault Detection (FD) Problem in control theory concerns of monitoring a system to identify when a fault has occurred. Two approaches can be distinguished for the FD: Signal processing based FD and Model-based FD. The former concerns of developing algorithms to directly infer faults from sensors' readings, while the latter uses a simulation model of the real-system to analyze the discrepancy between sensors' readings and expected values from the simulation model. Most contamination Event Detection Systems (EDSs) for water distribution systems have followed the signal processing based FD, which relies on analyzing the signals from monitoring stations independently of each other, rather than evaluating all stations simultaneously within an integrated network. In this study, we show that a model-based EDS which utilizes a physically based water quality and hydraulics simulation models, can outperform the signal processing based EDS. We also show that the model-based EDS can facilitate the development of a Multi-Site EDS (MSEDS), which analyzes the data from all the monitoring stations simultaneously within an integrated network. The advantage of the joint analysis in the MSEDS is expressed by increased detection accuracy (higher true positive alarms and fewer false alarms) and shorter detection time.

Managing Multiple Mandates: A System of Systems Model to Analyze Strategies for Producing Cellulosic Ethanol and Reducing Riverine Nitrate Loads in the Upper Mississippi River Basin.

Implementing public policies often involves navigating an array of choices that have economic and environmental consequences that are difficult to quantify due to the complexity of multiple system interactions. Implementing the mandate for cellulosic biofuel production in the Renewable Fuel Standard (RFS) and reducing hypoxia in the northern Gulf of Mexico by reducing riverine nitrate-N loads represent two such cases that overlap in the Mississippi River Basin. To quantify the consequences of these interactions, a system of systems (SoS) model was developed that incorporates interdependencies among the various subsystems, including biofuel refineries, transportation, agriculture, water resources and crop/ethanol markets. The model allows examination of the impact of imposing riverine nitrate-N load limits on the biofuel production system as a whole, including land use change and infrastructure needs. The synergies of crop choice (first versus second generation biofuel crops), infrastructure development, and environmental impacts (streamflow and nitrate-N load) were analyzed to determine the complementarities and trade-offs between environmental protection and biofuel development objectives. For example, the results show that meeting the cellulosic biofuel target in the RFS using Miscanthus x giganteus reduces system profits by 8% and reduces nitrate-N loads by 12% compared to the scenario without a mandate. However, greater water consumption by Miscanthus is likely to reduce streamflow with potentially adverse environmental consequences that need to be considered in future decision making.

An integrated logit model for contamination event detection in water distribution systems.

The problem of contamination event detection in water distribution systems has become one of the most challenging research topics in water distribution systems analysis. Current attempts for event detection utilize a variety of approaches including statistical, heuristics, machine learning, and optimization methods. Several existing event detection systems share a common feature in which alarms are obtained separately for each of the water quality indicators. Unifying those single alarms from different indicators is usually performed by means of simple heuristics. A salient feature of the current developed approach is using a statistically oriented model for discrete choice prediction which is estimated using the maximum likelihood method for integrating the single alarms. The discrete choice model is jointly calibrated with other components of the event detection system framework in a training data set using genetic algorithms. The fusing process of each indicator probabilities, which is left out of focus in many existing event detection system models, is confirmed to be a crucial part of the system which could be modelled by exploiting a discrete choice model for improving its performance. The developed methodology is tested on real water quality data, showing improved performances in decreasing the number of false positive alarms and in its ability to detect events with higher probabilities, compared to previous studies.

A dynamic thresholds scheme for contaminant event detection in water distribution systems.

In this study, a dynamic thresholds scheme is developed and demonstrated for contamination event detection in water distribution systems. The developed methodology is based on a recently published article of the authors (Perelman et al., 2012). Event detection in water supply systems is aimed at disclosing abnormal hydraulic or water quality events by exploring the time series behavior of routine hydraulic (e.g., flow, pressure) and water quality measurements (e.g., residual chlorine, pH, turbidity). While event detection raises alerts to the possibility of an event occurrence, it does not relate to origins, thus an event may be hydraulically-driven, as a consequence of problems like sudden leakages or pump/pipe malfunctions. Most events, however, are related to deliberate, accidental, or natural contamination intrusions. The developed methodology herein is based on off-line and on-line stages. During the off-line stage, a genetic algorithm (GA) is utilized for tuning five decision variables: positive and negative filters, positive and negative dynamic thresholds, and window size. During the on-line stage, a recursively Bayes' rule is invoked, employing the five decision variables, for real time on-line event detection. Using the same database, the proposed methodology is compared to Perelman et al. (2012), showing considerably improved detection ability. Metadata and the computer code are provided as Supplementary material.

Event detection in water distribution systems from multivariate water quality time series.

In this study, a general framework integrating a data-driven estimation model with sequential probability updating is suggested for detecting quality faults in water distribution systems from multivariate water quality time series. The method utilizes artificial neural networks (ANNs) for studying the interplay between multivariate water quality parameters and detecting possible outliers. The analysis is followed by updating the probability of an event, initially assumed rare, by recursively applying Bayes' rule. The model is assessed through correlation coefficient (R(2)), mean squared error (MSE), confusion matrices, receiver operating characteristic (ROC) curves, and true and false positive rates (TPR and FPR). The product of the suggested methodology consists of alarms indicating a possible contamination event based on single and multiple water quality parameters. The methodology was developed and tested on real data attained from a water utility.