Deep-learning-based surrogate models represent a powerful alternative to numerical models for speeding up flood mapping while preserving accuracy. In particular, solutions based on hydraulic-based graph neural networks (SWE-GNNs) enable transferability to domains not used for training and allow the inclusion of physical constraints. However, these models are limited due to four main aspects. First, they cannot model rapid differences in flow propagation speeds; secondly, they can face instabilities during training when using a large number of layers, needed for effective modelling; third, they cannot accommodate time-varying boundary conditions; and fourth, they require initial conditions from a numerical solver. To address these issues, we propose a multi-scale hydraulic-based graph neural network (mSWE-GNN) that models the flood at different resolutions and propagation speeds. We include time-varying boundary conditions via ghost cells, which enforce the solution at the domain’s boundary and drop the need for a numerical solver for the initial conditions. To improve generalization over unseen meshes and reduce the data demand, we use invariance principles and make the inputs independent from coordinates' rotations. Numerical results applied to dike-breach floods show that the model predicts the full spatio-temporal simulation of the flood over unseen irregular meshes, topographies, and time-varying boundary conditions, with mean absolute errors in time of 0.05 m for water depths and 0.003 m2 s−1 for unit discharges. We further corroborate the mSWE-GNN in a realistic case study in the Netherlands and show generalization capabilities with only one fine-tuning sample, with mean absolute errors of 0.12 m for water depth, a critical success index for a water depth threshold of 0.05 m of 87.68 %, and speed-ups of over 700 times. Overall, the approach opens up several avenues for probabilistic analyses of realistic configurations and flood scenarios.@en

The steady state of a water distribution system abides by the laws of mass and energy conservation. Hydraulic solvers, such as the one used by EPANET approach the simulation for a given topology with a Newton-Raphson algorithm. However, iterative approximation involves a matrix inversion which acts as a computational bottleneck and may significantly slow down the process. In this work, we propose to rethink the current approach for steady state estimation to leverage the recent advancements in Graphics Processing Unit (GPU) hardware. Modern GPUs enhance matrix multiplication and enable memory-efficient sparse matrix operations, allowing for massive parallelization. Such features are particularly beneficial for state estimation in infrastructure networks, which are characterized by sparse connectivity between system elements. To realize this approach and tap into the potential of GPU-enhanced parallelization, we reformulate the problem as a diffusion process on the edges of a graph. Edge-based diffusion is inherently related to conservation laws governing a water distribution system. Using a numerical approximation scheme, the diffusion leads to a state of the system that satisfies mass and energy conservation principles. Using existing benchmark water distribution systems, we show that the proposed method allows parallelizing thousands of hydraulic simulations simultaneously with very high accuracy.

@en

Current research on riverine macrolitter does not yet provide a theoretic framework on the dynamics behind its accumulation and distribution along riverbanks. In an attempt to better understand these dynamics a detailed field survey of three months was conducted in which location of macrolitter items within a single groyne field along the Waal riverbanks was tracked. The data provided insight into the daily changing patterns of spatial item distribution with respect to the waterline. Furthermore, the rates of item uptake and deposition were monitored and related to hydrologic fluctuations. Uptake was initiated by rising water levels and was generally higher when the water level increased faster. Deposition occurred continuously, despite hydrologic fluctuations. This caused the riverbank macrolitter budget to be positive during stable or dropping water levels and negative during rising water levels. Although the results show clear patterns an extended monitoring duration is required to fully understand the fate of plastic objects.

@en

In recent years, a number of evasion attacks for Industrial Control Systems have been proposed. During an evasion attack, the attacker attempts to hide ongoing process anomalies to avoid anomaly detection. Examples of such attacks range from replay attacks to adversarial machine learning techniques. Those attacks generally are applied to existing datasets with normal and anomalous data, to which the evasion attacks are added post-hoc. This represents a very strong attacker, who is effectively able to observe and manipulate data from anywhere in the system, in real-time, with zero processing delay, and no computational constraints. Prior work has shown that such strong attackers are theoretically difficult to detect by most existing countermeasures. So far, it is unclear if such an attack could be practically realized, and if there are challenges that would impair the attacker. In this work, we systematically discuss options for an attacker to mount evasion attacks in real-world ICS, and show the constraints that result from those options. To validate our findings, we design and implement a framework that allows the realization of evasion attacks and anomaly detection for ICS emulation. We demonstrate practical constraints that arise from different settings, and their effect on attack performance. For example, we found that network packet replay might trigger network errors, which will result in unexpected spoofing patterns.@en

Storm water systems (SWSs) are essential infrastructure providing multiple services including environmental protection and flood prevention. Typically, utility companies rely on computer simulators to properly design, operate, and manage SWSs. However, multiple applications in SWSs are highly time-consuming. Researchers have resorted to cheaper-to-run models, i.e. metamodels, as alternatives of computationally expensive models. With the recent surge in artificial intelligence applications, machine learning has become a key approach for metamodelling urban water networks. Specifically, deep learning methods, such as feed-forward neural networks, have gained importance in this context. However, these methods require generating a sufficiently large database of examples and training their internal parameters. Both processes defeat the purpose of using a metamodel, i.e., saving time. To overcome this issue, this research focuses on the application of inductive biases and transfer learning for creating SWS metamodels which require less data and retain high performance when used elsewhere. In particular, this study proposes an auto-regressive graph neural network metamodel of the Storm Water Management Model (SWMM) from the Environmental Protection Agency (EPA) for estimating hydraulic heads. The results indicate that the proposed metamodel requires a smaller number of examples to reach high accuracy and speed-up, in comparison to fully connected neural networks. Furthermore, the metamodel shows transferability as it can be used to predict hydraulic heads with high accuracy on unseen parts of the network. This work presents a novel approach that benefits both urban drainage practitioners and water network modeling researchers. The proposed metamodel can help practitioners on the planning, operation, and maintenance of their systems by offering an efficient metamodel of SWMM for computationally intensive tasks like optimization and Monte Carlo analyses. Researchers can leverage the current metamodel’s structure for developing new surrogate model architectures tailored to their specific needs or start paving the way for more general foundation metamodels of urban drainage systems.@en

Recent research highlights the potential of consumption-based feedback for water conservation, emphasizing the need for Non Intrusive Water Monitoring (NIWM). However, existing NIWM studies often rely on small datasets, a pre-selected class of models, and inaccessible software. Here, we introduce PyNIWM, a machine learning-based open-source Python framework for NIWM. PyNIWM enables water end-use classification via (i) data characterization and feature engineering, (ii) water end-use event classification with four machine learning classifiers, and (iii) performance assessment. We demonstrate PyNIWM on a real-world dataset containing around 800,000 labeled end-use events from 762 homes across the USA and Canada. The four PyNIWM classifiers achieve F1 scores above 0.85, indicating high suitability for water end-use classification. However, a tradeoff between accuracy and computational cost exists. Finally, data balancing through oversampling enhances classification of low-represented end-use classes, but does not improve overall classification. We release PyNIWM as an open-source software, aiming for collaborative and reproducible research.@en

Data-driven metamodels reproduce the input-output mapping of physics-based models while significantly reducing simulation times. Such techniques are widely used in the design, control, and optimization of water distribution systems. Recent research highlights the potential of metamodels based on Graph Neural Networks as they efficiently leverage graph-structured characteristics of water distribution systems. Furthermore, these metamodels possess inductive biases that facilitate generalization to unseen topologies. Transferable metamodels are particularly advantageous for problems that require an efficient evaluation of many alternative layouts or when training data is scarce. However, the transferability of metamodels based on GNNs remains limited, due to the lack of representation of physical processes that occur on edge level, i.e. pipes. To address this limitation, our work introduces Edge-Based Graph Neural Networks, which extend the set of inductive biases and represent link-level processes in more detail than traditional Graph Neural Networks. Such an architecture is theoretically related to the constraints of mass conservation at the junctions. To verify our approach, we test the suitability of the edge-based network to estimate pipe flowrates and nodal pressures emulating steady-state EPANET simulations. We first compare the effectiveness of the metamodels on several benchmark water distribution systems against Graph Neural Networks. Then, we explore transferability by evaluating the performance on unseen systems. For each configuration, we calculate model performance metrics, such as coefficient of determination and speed-up with respect to the original numerical model. Our results show that the proposed method captures the pipe-level physical processes more accurately than node-based models. When tested on unseen water networks with a similar distribution of demands, our model retains a good generalization performance with a coefficient of determination of up to 0.98 for flowrates and up to 0.95 for predicted heads. Further developments could include simultaneous derivation of pressures and flowrates.

@en

This paper investigates the influence of multi-decadal climatic variability on the temporal evolution of root zone storage capacities (Sr,max) and its implications for streamflow predictions in the Meuse basin. Through a comprehensive analysis of 286 catchments across Europe and the US that are hydro-climatically comparable to the Meuse basin, we construct inter-decadal distributions of past deviations in evaporative ratios (IE) from expected values based on catchment aridity (IA). These distributions of ΔIE were then used to estimate inter-decadal changes in Sr,max and to quantify the associated consequences for streamflow predictions in the Meuse basin. Our findings reveal that, while catchments do not strictly adhere to their specific parametric Budyko curves over time, the deviations in IE are generally very minor, with an average ΔIE=0.01 and an interquartile range (IQR) of −0.01 to 0.03. Consequently, these minor deviations lead to limited inter-decadal changes in Sr,max, mostly ranging between −10 and +21 mm (−5 % to +10 %). When these changes (ΔSr,max) are accounted for in hydrological models, the impact on streamflow predictions in the Meuse basin is found to be marginal, with the most significant shifts in monthly evaporation and streamflow not exceeding 4 % and 12 %, respectively. Our study underscores the utility of parametric Budyko-style equations for first-order estimates of future Sr,max in hydrological models, even in the face of climate change and variability. This research contributes to a more nuanced understanding of hydrological responses to changing climatic conditions and offers valuable insights for future climate impact studies in hydrology.@en

Researchers and practitioners have extensively utilized supervised Deep Learning methods to quantify floating litter in rivers and canals. These methods require the availability of large amount of labeled data for training. The labeling work is expensive and laborious, resulting in small open datasets available in the field compared to the comprehensive datasets for computer vision, e.g., ImageNet. Fine-tuning models pre-trained on these larger datasets helps improve litter detection performances and reduces data requirements. Yet, the effectiveness of using features learned from generic datasets is limited in large-scale monitoring, where automated detection must adapt across different locations, environmental conditions, and sensor settings. To address this issue, we propose a two-stage semi-supervised learning method to detect floating litter based on the Swapping Assignments between multiple Views of the same image (SwAV). SwAV is a self-supervised learning approach that learns the underlying feature representation from unlabeled data. In the first stage, we used SwAV to pre-train a ResNet50 backbone architecture on about 100k unlabeled images. In the second stage, we added new layers to the pre-trained ResNet50 to create a Faster R-CNN architecture, and fine-tuned it with a limited number of labeled images (≈1.8k images with 2.6k annotated litter items). We developed and validated our semi-supervised floating litter detection methodology for images collected in canals and waterways of Delft (the Netherlands) and Jakarta (Indonesia). We tested for out-of-domain generalization performances in a zero-shot fashion using additional data from Ho Chi Minh City (Vietnam), Amsterdam and Groningen (the Netherlands). We benchmarked our results against the same Faster R-CNN architecture trained via supervised learning alone by fine-tuning ImageNet pre-trained weights. The findings indicate that the semi-supervised learning method matches or surpasses the supervised learning benchmark when tested on new images from the same training locations. We measured better performances when little data (≈200 images with about 300 annotated litter items) is available for fine-tuning and with respect to reducing false positive predictions. More importantly, the proposed approach demonstrates clear superiority for generalization on the unseen locations, with improvements in average precision of up to 12.7%. We attribute this superior performance to the more effective high-level feature extraction from SwAV pre-training from relevant unlabeled images. Our findings highlight a promising direction to leverage semi-supervised learning for developing foundational models, which have revolutionized artificial intelligence applications in most fields. By scaling our proposed approach with more data and compute, we can make significant strides in monitoring to address the global challenge of litter pollution in water bodies.

@en

Two-dimensional hydrodynamic models are computationally expensive. This drawback can limit their application to solving problems requiring real-time predictions or several simulation runs. Although the literature presented improvements in using Deep Learning as an alternative to hydrodynamic models, Artificial Neural Networks applications for flood prediction cannot satisfactorily predict floods for areas outside the training datasets with different boundary conditions. In this paper, we used a conditional generative adversarial network (cGAN) aiming to generalize flood predictions in catchments not included in the training process. The proposed method, called cGAN-Flood, uses two cGAN models to solve a rain-on-grid problem by first identifying wet cells and then estimating the water depths. The cGANs were trained using HEC-RAS outputs as ground truth. cGAN-Flood distributes a target flood volume (v_t) in a given catchment, which can be calculated via water balance from hydrological simulations. Our approach was trained on ten and tested on five urban catchments with distinct characteristics. The cGAN-Flood was compared to HEC-RAS for different rainfall magnitudes and surface roughness. We also compared our approach to the Weighted Cellular Automata 2D (WCA2D), a rapid flood model (RFM) used for rain-on-grid simulations. Our method successfully predicted water depths in the testing areas, showing that cGAN-Flood could generalize to different locations. However, cGAN-Flood tended to underestimate depths in channels in some areas for events with a small peak of precipitation intensity. cGAN-Flood was 50 and 250 times faster than WCA2D and HEC-RAS, respectively. Due to its computational efficiency and accuracy, we suggest that cGAN-Flood can be applied when fast simulations are necessary, and it can be a viable modeling solution for flood forecasts in large-scale watersheds.

@en

Metamodels accurately reproduce the output of physics-based hydraulic models with a significant reduction in simulation times. They are widely employed in water distribution system (WDS) analysis since they enable computationally expensive applications in the design, control, and optimisation of water networks. Recent machine-learning-based metamodels grant improved fidelity and speed; however, they are only applicable to the water network they were trained on. To address this issue, we investigate graph neural networks (GNNs) as metamodels for WDSs. GNNs leverage the networked structure of WDS by learning shared coefficients and thus offering the potential of transferability. This work evaluates the suitability of GNNs as metamodels for estimating nodal pressures in steady-state EPANET simulations. We first compare the effectiveness of GNN metamodels against multi-layer perceptrons (MLPs) on several benchmark WDSs. Then, we explore the transferability of GNNs by training them concurrently on multiple WDSs. For each configuration, we calculate model accuracy and speedups with respect to the original numerical model. GNNs perform similarly to MLPs in terms of accuracy and take longer to execute but may still provide substantial speedup. Our preliminary results indicate that GNNs can learn shared representations across networks, although assessing the feasibility of truly general metamodels requires further work.

@en

Numerical simulation models are a fundamental tool for planning and managing smart water networks—an evolution of water distribution systems in which physical assets are monitored and controlled by information and communication technologies. While simulation models allow us to understand the interactions between physical processes and abstract control strategies, they ignore key implementation aspects of distributed control systems, such as the required communication over digital links. As a result, the effects of anomalies and faults in the communication on the process control cannot be investigated with existing tools. In this work, we fill this gap by introducing DHALSIM (Digital HydrAuLic SIMulator), a numerical modelling platform combining EPANET-based process simulation with a network and host emulation environment, offering a high-fidelity representation of the processes occurring in the cyber domain. We illustrate DHALSIM’s key functionalities by implementing it on a benchmark water distribution system, present case studies of simulated network traffic, and demonstrate how anomalies in the behavior of the communication network affect the process data received by the supervisory control and data acquisition (SCADA) server. In a companion paper, we further illustrate how DHALSIM enables research opportunities in the domain of cyber-physical security. The easily customizable and open source DHALSIM provides a “workbench” for studying smart water networks, developing digital twins, and designing a broad spectrum of engineering solutions.@en

Numerical modelling is a reliable tool for flood simulations, but accurate solutions are computationally expensive. In recent years, researchers have explored data-driven methodologies based on neural networks to overcome this limitation. However, most models are only used for a specific case study and disregard the dynamic evolution of the flood wave. This limits their generalizability to topographies that the model was not trained on and in time-dependent applications. In this paper, we introduce shallow water equation–graph neural network (SWE–GNN), a hydraulics-inspired surrogate model based on GNNs that can be used for rapid spatio-temporal flood modelling. The model exploits the analogy between finite-volume methods used to solve SWEs and GNNs. For a computational mesh, we create a graph by considering finite-volume cells as nodes and adjacent cells as being connected by edges. The inputs are determined by the topographical properties of the domain and the initial hydraulic conditions. The GNN then determines how fluxes are exchanged between cells via a learned local function. We overcome the time-step constraints by stacking multiple GNN layers, which expand the considered space instead of increasing the time resolution. We also propose a multi-step-ahead loss function along with a curriculum learning strategy to improve the stability and performance. We validate this approach using a dataset of two-dimensional dike breach flood simulations in randomly generated digital elevation models generated with a high-fidelity numerical solver. The SWE–GNN model predicts the spatio-temporal evolution of the flood for unseen topographies with mean average errors in time of 0.04 m for water depths and 0.004 m2 s−1 for unit discharges. Moreover, it generalizes well to unseen breach locations, bigger domains, and longer periods of time compared to those of the training set, outperforming other deep-learning models. On top of this, SWE–GNN has a computational speed-up of up to 2 orders of magnitude faster than the numerical solver. Our framework opens the doors to a new approach to replace numerical solvers in time-sensitive applications with spatially dependent uncertainties.@en

Plastic pollution in water bodies is an unresolved environmental issue that damages all aquatic environments, and causes economic and health problems. Accurate detection of macroplastic litter (plastic items >5 mm) in water is essential to estimate the quantities, compositions and sources, identify emerging trends, and design preventive measures or mitigation strategies. In recent years, researchers have demonstrated the potential of computer vision (CV) techniques based on deep learning (DL) for automated detection of macroplastic litter in water bodies. However, a systematic review to describe the state-of-the-art of the field is lacking. Here we provide such a review, and we highlight current knowledge gaps and suggest promising future research directions. The review compares 34 papers with respect to their application and modeling related criteria. The results show that the researchers have employed a variety of DL architectures implementing different CV techniques to detect macroplastic litter in various aquatic environments. However, key knowledge gaps must be addressed to overcome the lack of: (i) DL-based macroplastic litter detection models with sufficient generalization capability, (ii) DL-based quantification of macroplastic (mass) fluxes and hotspots and (iii) scalable macroplastic litter monitoring strategies based on robust DL-based quantification. We advocate for the exploration of data-centric artificial intelligence approaches and semi-supervised learning to develop models with improved generalization capabilities. These models can boost the development of new methods for the quantification of macroplastic (mass) fluxes and hotspots, and allow for structural monitoring strategies that leverage robust DL-based quantification. While the identified gaps concern all bodies of water, we recommend increased efforts with respect to riverine ecosystems, considering their major role in transport and storage of litter.

@en

Researchers and engineers employ machine learning (ML) tools to detect pipe bursts and prevent significant non-revenue water losses in water distribution systems (WDS). Nonetheless, many approaches developed so far consider a fixed number of sensors, which requires the ML model redevelopment and collection of sufficient data with the new sensor configuration for training. To overcome these issues, this study presents a novel approach based on Long Short-Term Memory neural networks (NNs) that leverages transfer learning to manage a varying number of sensors and retain good detection performance with limited training data. The proposed detection model first learns to reproduce the normal behavior of the system on a dataset obtained in burst-free conditions. The training process involves predicting flow and pressure one-time step ahead using historical data and time-related features as inputs. During testing, a post-prediction step flags potential bursts based on the comparison between the observations and model predictions using a time-varied error threshold. When adding new sensors, we implement transfer learning by replicating the weights of existing channels and then fine-tune the augmented NN. We evaluate the robustness of the methodology on simulated fire hydrant bursts and real-bursts in 10 district metered areas (DMAs) of the UK. For real bursts, we perform a sensitivity analysis to understand the impact of data resolution and error threshold on burst detection performance. The results obtained demonstrate that this ML-based methodology can achieve Precision of up to 98.1% in real-life settings and can identify bursts, even in data scarce conditions.

@en

Streamflow predictions remain a challenge for poorly gauged and ungauged catchments. Recent research has shown that deep learning methods based on Long Short-Term Memory (LSTM) cells outperform process-based hydrological models for rainfall-runoff modeling, opening new possibilities for prediction in ungauged basins (PUB). These studies usually feature local datasets for model development, while predictions in ungauged basins at a global scale require training on global datasets. In this study, we develop LSTM models for over 500 catchments from the CAMELS-US data base using global ERA5 meteorological forcing and global catchment characteristics retrieved with the HydroMT tool. Comparison against an LSTM trained with local datasets shows that, while the latter generally yields superior performances due to the higher spatial resolution meteorological forcing (overall median daily NSE 0.54 vs. 0.71), training with ERA5 results in higher NSE in most catchments of Western and North-Western US (median daily NSE of 0.83 vs. 0.78). No significant changes in performance occur when substituting local with global data sources for deriving the catchment characteristics. These results encourage further research to develop LSTM models for worldwide predictions of streamflow in ungauged basins using available global datasets. Promising directions include training the models with streamflow data from different regions of the world and with higher quality meteorological forcing.@en

West African food systems and rural socio-economics are based on rainfed agriculture, which makes society highly vulnerable to rainfall uncertainty and frequent floods and droughts. Reliable rainfall information is currently missing. There is a sparse and uneven rain gauge distribution and, despite continuous efforts, rainfall satellite products continue to show weak correlations with ground measurements. This paper aims to investigate whether water vapor (WV) observations together with temporal information can complement thermal infrared (TIR) data for satellite rainfall retrieval in a Deep Learning (DL) framework. This is motivated by the fact that water vapor plays a key role in the highly seasonal West African rainfall dynamics. We present a DL model for satellite rainfall detection based on WV and TIR channels of Meteosat Second Generation and temporal information. Results show that the WV inhibition of low-level features enables the depiction of strong convective motions usually related to heavy rainfall. This is especially relevant in areas where convective rainfall is dominant, such as the tropics. Additionally, WV data allow us to detect dry air masses over our study area, that are advected from the Sahara Desert and create discontinuities in precipitation events. The developed DL model shows strong performance in rainfall binary classification, with less false alarms and lower rainfall overdetection (FBias <2.0) than the state-of-the-art Integrated MultisatellitE Retrievals for GPM (IMERG) Final Run.@en

Food and economic security in West Africa rely heavily on rainfed agriculture and are threatened by climate change and demographic growth. Accurate rainfall information is therefore crucial to tackling these challenges. Particularly, information about the occurrence and length of droughts as well as the onset date of the rainy season is essential for agricultural planning. However, existing rainfall models fail to accurately represent the highly variable and sparsely monitored West African rainfall patterns. In this paper, we show the potential of deep learning (DL) to model rainfall in the region and propose a methodology to develop DL models in data-scarce areas. We built two DL models for satellite rainfall (rain/no-rain) detection over northern Ghana from Meteosat TIR data based on standard DL architectures: Convolutional neural networks (CNNs) and convolutional long short-term memory neural networks (ConvLSTM). The Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) and Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System (PERSIANN-CCS) products are used as benchmarks. We use rain gauge data from the Trans-African Hydro-Meteorological Observatory (TAHMO) for model development and performance evaluation. We show that our models compare well against existing products despite being considerably simpler, developed with a small training dataset—i.e., 8 stations covering 2.5 years with 20.4% of the data missing—and using TIR data alone. Concretely, our models consistently outperform PERSIANN-CCS for rain/no-rain detection at a sub-daily timescale. While IMERG is the overall best performer, the DL models perform better in the second half of the rainy season despite their simplicity (i.e., up to 120 k parameters). Our results suggest that DL-based regional models are a promising alternative to state-of-the-art global products for providing regional rainfall information, especially in meteorologically complex regions such as the (sub)tropics, which are poorly covered by ground-based rainfall observations.@en

Supervised Deep Learning (DL) methods have shown promise in monitoring the floating litter in rivers and urban canals but further advancements are hard to obtain due to the limited availability of relevant labeled data. To address this challenge, researchers often utilize techniques such as transfer learning (TL) and data augmentation (DA). However, there is no study currently reporting a rigorous evaluation of the effectiveness of these approaches for floating litter detection and their effects on the models' generalization capability. To overcome the problem of limited data availability, this work introduces the “TU Delft—Green Village” dataset, a novel labeled dataset of 9,473 camera and phone images of floating macroplastic litter and other litter items, captured using experiments in a drainage canal of TU Delft. We use the new dataset to conduct a thorough evaluation of the detection performance of five DL architectures for multi-class image classification. We focus the analysis on a systematic evaluation of the benefits of TL and DA on model performances. Moreover, we evaluate the generalization capability of these models for unseen litter items and new device settings, such as increasing the cameras' height and tilting them to 45°. The results obtained show that, for the specific problem of floating litter detection, fine-tuning all layers is more effective than the common approach of fine-tuning the classifier alone. Among the tested DA techniques, we find that simple image flipping boosts model accuracy the most, while other methods have little impact on the performance. The SqueezeNet and DenseNet121 architectures perform the best, achieving an overall accuracy of 89.6 and 91.7%, respectively. We also observe that both models retain good generalization capability which drops significantly only for the most complex scenario tested, but the overall accuracy raises significantly to around 75% when adding a limited amount of images to training data, combined with flipping augmentation. The detailed analyses conducted here and the released open source dataset offer valuable insights and serve as a precious resource for future research.@en

A fundamental problem in the realm of cyber-physical security of smart water networks is attack detection, a key step towards designing adequate countermeasures. This task is typically carried out by algorithms that analyze time series of process data. However, the nature of the data available to develop these algorithms limits their capabilities: by relying on process data only, one cannot distinguish a cyber-attack from the failure of a system’s component or identify the root cause of an attack. Here, we show that these limitations can be addressed through the joint analysis of process and network data—with the latter representing the information exchanged between the components constituting the Industrial Control System, such as sensors and Programmable Logic Controllers (PLCs). For this purpose, we utilize a dataset generated by digital hydraulic simulator (DHALSIM)—a numerical modelling platform built on a two-way interaction between EPANET version 2.2 and a network emulation tool—which is extended here to include a framework for launching cyber-physical attacks. This paper presents a dataset with realistic network information of a smart water network under cyber-physical attacks and presents an analysis of how that information can enable the development of better intrusion detection systems that can localize and identify attacks. Through this analysis, the dataset provided here, and the open-source availability of DHALSIM, our work paves the way to a novel class of analytics for actionable detection.

@en