Scientific Results

This catalogue is obtained by conducting a systematic literature review of scientific studies and reviews related to monitoring, forecasting, and simulating the inland water cycle. The analysis maps scientific expertise across research groups and classifies findings by the type of inland water studied, application focus, and geographical scope. A gap analysis will identify missing research areas and assess their relevance to policymaking.

ID ▲	Type	Year	Authors	Title	Venue/Journal	DOI	Abstract
publications-5091	Article	2023	Wang H.; Yin Z.; Jiang Z.-P.	Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach	IEEE Access	10.1109/ACCESS.2023.3340627	In recent years, deep learning has been widely applied to learning nonlinear dynamic models for the development of a digital twin system. However, most traditional deep learning frameworks, such as recurrent neural networks, convolutional neural networks, and multilayer perceptrons, find it difficult to learn continuous-time and nonlinear system models. To address this challenge, in this paper, a novel deep learning method called neural controlled differential equation has been proposed to model the unknown nonlinear dynamics of controlled continuous-time systems seen in Francis hydroturbines of hydropower systems. Following the development of discretized-model structures for the system using the first principles, a detailed learning algorithm is formulated that is integrated with the physical model of the hydroturbine. As a result, a hybrid modeling with effective learning capability is obtained. To test the effectiveness of the proposed learning algorithm, a set of operational data has been collected and used to train the nonlinear dynamics of the Francis hydroturbine, where the learning results of the two nonlinear dynamics, namely the mechanical torque and water flow dynamics, using the real data have indicated that the proposed method can accurately learn these unknown nonlinear dynamics in an online, adaptive way. Moreover, to address the overfitting problem that appears during the online training phase, we propose to apply a meta-learning technique to pre-train a meta-initial value for each parameter of the proposed neural controlled differential equations. It has been shown that the use of the meta-learning technique can reduce the prediction mean square error significantly by more than 60%. Β© 2013 IEEE.
publications-5092	Article	2023	Pervez Z.; Khan Z.; Ghafoor A.; Soomro K.	SIGNED: Smart cIty diGital twiN vErifiable Data Framework	IEEE Access	10.1109/ACCESS.2023.3260621	Smart city digital twins can provide useful insights by making effective use of multidisciplinary urban data from diverse sources. Whilst these insights provide new information that helps cities in decision making, verifying the authenticity, integrity, traceability and data ownership across various functional units have become critical characteristics to ensure the data is from an authentic and trustworthy source. However, these characteristics are rarely considered in a digital twin ecosystem. In this research we introduce a novel framework, namely, 'SIGNED: Smart cIty diGital twiN vErifiable Data framework' that is designed on the basis of data ownership, selective disclosure and verifiability principles. Using Verifiable Credentials, SIGNED ensures digital twin data are verifiably authentic i.e., it covers provenance, transparency, and reliability through verifiable presentation. A proof of concept is designed and evaluated based on a smart water management use case to demonstrate the effectiveness of SIGNED in securing verifiable exchange of digital twin data across multiple functional units. The proof-of-concept demonstrates that SIGNED successfully allows the exchange of data in a trusted and verifiable manner at negligible performance cost, thus enhancing security and alleviating privacy issues when sharing data between various functional units in a smart city. Β© 2013 IEEE.
publications-5093	Conference paper	2023	Borgia S.; Topputo F.; Zanero S.	HACK: a Holistic modeling Approach for Cubesat cyberattacKs	Materials Research Proceedings	10.21741/9781644902677-41	In recent years, the threat of cyberattacks has been growing rapidly in numerous industrial sectors that have an impact on our daily life. One of these is the space industry, where the risk of hacking a single satellite can lead to dangerous effects not only for economics but also for Earth critical infrastructure like: transportation systems, water networks, and electric grid. The vulnerability of complex space systems has already been demonstrated in the past. In 1998, for example, hackers took control of the ROSAT X-Ray satellite pointing its solar panels directly to the Sun and causing physical damage. Nowadays, since the attention is moved on small and less sophisticated system, such as CubeSat, the risk of cyber intrusions is even higher as the COTS (Commercial-Off-The-Shelf) technology they use is based on open-source operating systems. In order to counteract this imminent problem, the development of a high-fidelity CubeSat digital model is needed to study and solve related space cybersecurity issues. In fact, thanks to the virtual prototype, what-if simulations can be performed allowing to analyze different cyberattacks scenarios and predict undesirable events on the CubeSat flying on its operative orbit. Moreover, the building of the digital model requires a holistic modeling approach and simulation tools which allows to consider Multiphysics phenomena occurring on the space system itself. Finally, the possibility of connecting the virtual model to a real space system, obtaining the so-called Digital Twin (DT), will help engineers to conduct more accurate actions during the mission. Β© 2023, Association of American Publishers. All rights reserved.
publications-5094	Conference paper	2023	Park H.; Park D.-H.; Jo S.-K.	A Method for Optimizing Water Quality of the Aquafarm Using Application Independent Digital Twins	International Conference on ICT Convergence	10.1109/ICTC58733.2023.10393111	Land-based aquafarm is a method of farming fish on the ground, and the quality of the water has a great influence on the mortality of farmed fish, so the condition of the water in the tank is an important factor. Therefore, it is necessary to maintain the optimal condition of water quality through the analysis of various sensor and control data in the tank. To this end, attempts to improve water quality in landbased aquafarms based on digital twins have recently appeared. In this paper, a systematic interworking mechanism between real and virtual environments is provided to optimize water quality in land-based aquafarms. This systematic interworking mechanism acquires the information of virtual and real space under the digital twin basis using an application-independent common interface. In this paper, a common interface is proposed to enable mutual interworking between virtual simulation and the real world so that it can be used for any application. The information obtained from the virtual and the real space allows the simulation results of the virtual space to be reflected in the real space, and the results are analyzed and fed back to the virtual space so that the real and virtual spaces are optimized. Β© 2023 IEEE.
publications-5095	Article	2023	Chen X.; Jin Y.; Xu X.; He W.	Thinking on smart water dispatching in the South-to-North Water Diversion Middle Route Project; [ε_x008d_—ζ°΄ε_x008c_—θ°ƒδΈηΊΏεΉ²ηΊΏζ™Ίζ…§θΎ“ζ°΄θ°ƒεΊ¦η_x009a_„ζ€_x009d_θ€ƒ]	Journal of Hohai University	10.3876/j.issn.1000-1980.2023.05.007	According to the relevant requirements of smart water conservancy and digital twin engineering construction, by integrating the modern artificial intelligence and water dispatching professional knowledge, the definition and basic functions of smart water dispatching for the South-to-North Water Diversion Middle Route Project are tentatively proposed in this paper combined with the tasks and responsibilities of water transportation scheduling. Through analyzing the logical relationship between intelligence and wisdom, this paper systematically discusses the key technologies, existing shortcomings, and improvement suggestions for the smart water transportation and dispatching in the middle route from the perspectives of perceptual intelligence, cognitive intelligence, and decision-making intelligence. With respect to the perception intelligence, it should be a combination of non-contact and contact measurement, a mixture of machine vision and traditional sensors, and an integration of automatic monitoring and manual inspection. Data cleaning technology is required to support the multi-source data fusion. In the cognition intelligence, a framework is suggested by integrating mechanism studying and data mining. From the perspective of prediction, early warning, rehearsal and emergency plan, the key technologies and modeling requirements of water dispatching were comprehensively analyzed, and the regulation strategy model, simulation model, prediction and early warning model, Self-adaptive model, and so on should be constructed. In terms of intelligent decision-making for the dispatch of the middle route, a regulation approach based on simulation deduction as feedforward and real-time monitoring as feedback is proposed. An automated water dispatching regulation strategy based on rolling decision correction and real-time response is established, and a multi-objective optimization dispatch model should be constructed. Β© 2023 Editorial Office of Journal of Hohai University (Nature Sciences). All rights reserved.
publications-5096	Article	2023	di Capaci R.B.; Doneddu M.; Brunazzi E.; Pannocchia G.; Galletti C.	CFD Analysis of Inline Mixing of Non-Ideal Liquid Mixtures	Chemical Engineering Transactions	10.3303/CET23100055	Numerical simulations based on Computational Fluid Dynamics have been performed for the assisted design of the flexible and transportable flow reactor developed within the Turboflux project. The core of the system consists of a tubular pipe, carrying the main fluids, and multiple injection ducts for the additive components. Mixing is ensured by a series of static mixing elements fitted within the main pipe. More specifically, we focus herein on the production of the sanitizing gel, obtained from three main components, i.e., ethanol, water, and glycerol. Hence, the numerical code is customized by implementing the non-ideal behaviour of the mixture. The degree of mixing and pressure drops are estimated in a wide range of scenarios, covering different flow regimes. The analysis allows one to identify the optimal operating conditions and, also, to put the basis for the setup of a digital twin of the system. Copyright Β© 2023, AIDIC Servizi S.r.l.
publications-5097	Conference paper	2023	Preite L.; Solari F.; Vignali G.	A digital model application to optimize water consumption in agriculture	Proceedings of the International Food Operations and Processing Simulation Workshop, FOODOPS	10.46354/i3m.2023.foodops.006	Agriculture is a key driver of global biodiversity and economy. In the recent years, the over-exploitation of water resources, climate change and pollution have led to a global water crisis, exposing the agricultural sector to significant risks in both the short and long term. For these reasons, the development, and the optimization of the technologies to efficiently manage the water consumption are the main weapons to reduce the impact on this valuable resource. The main aim of this study is to assess the application of a digital model (DM) to agricultural operations to ensure the correct supply of water and nutrients to crops, minimizing the consumption of resources and increasing the efficiency of the water management. The simulation model of an irrigation network has been developed on Flownex, a 1D, concentrated-parameter fluid dynamics simulation software dedicated to network simulations. To model the drip irrigation system a specific characterization was carried out through fluid-dynamic simulation (ANSYS Fluent). The developed tool has emerged as an evaluable solution to apply the benefits of DT to agricultural applications. Indeed, the DM can reliably predict the performance of the system in terms of water distribution considering different operating conditions. Β© 2023 The Authors.
publications-5098	Article	2023	Chae M.-S.; Ha M.-H.; Park T.-H.	LSTM Based Forecasting and Evaluation of Sensor Signals Containing Anomaly Data	Journal of Institute of Control, Robotics and Systems	10.5302/J.ICROS.2023.23.0182	Sensors are being used in various fields such as smart factories, CPS, and digital twins. It is important to minimize and prevent losses by forecasting abnormal sensor signals when these sensors malfunction or when abnormal signals occur due to environmental effects. Recently, various studies have been conducted with LSTM, which is widely used as time series prediction, but there are not many studies that evaluate performance by applying this to sensor signals. In this study, an LSTM with excellent performance was designed with an optimal hyperparameter setting by applying a water distribution sensor containing 7-17% abnormal sensor data. In addition, as a result of performance comparison with ARIMA, it was found that LSTM was 94.29% superior on average in terms of precision and accuracy. CopyrightΒ© ICROS 2023.
publications-5099	Conference paper	2023	Srisawat J.; Patimakornpong S.; Ramunudom P.; Putthividhya W.; Hongwarittorrn N.; Rattanatamrong P.	Human-Computer Interaction for Decision Making in Digital Twins with Various Display Environments	27th International Computer Science and Engineering Conference 2023, ICSEC 2023	10.1109/ICSEC59635.2023.10329364	Human-Computer Interaction (HCI) is the study of how humans and computers interact to achieve a specific purpose. The applications of digital twins in building/facility management are of special interest in this work. Digital twins of buildings are created by compiling various data into their three-dimensional virtual replicas, which are then updated in real time with the state of the buildings. By employing this approach, facility managers can minimize the time required to assess risks and devise problem-solving strategies remotely, which in turn reduces the need for their physical presence in the facility. The purpose of this study is to investigate the effectiveness of three virtual display environments when the users must make decisions regarding various building-related issues. A single monitor, a tiled display consisting of multiple monitors, and a head-mounted display (often known as VR) make up the three virtual display environments that are key to us. The times it took participants to make decisions in three simulated scenarios-detecting water leakage, identifying and extinguishing fires, and measuring objects-were recorded. Due to participants' prior expertise with the single monitor, this display setting had the best average decision making time. However, upon closer examination of each task, we discovered that the head-mounted display placed second in multiple tasks, despite the fact that the majority of participants had never used it. Decision-making duties involving the collection of data from multiple perspectives and with a realistic sense of objects or surroundings will make the most of this display environment. Β© 2023 IEEE.
publications-5100	Conference paper	2023	Cardoso M.G.; Ares E.; Pinto Ferreira L.; Pelaez G.	The use of simulation and artificial intelligence as a decision support tool for sustainable production lines	Advances in Science and Technology	10.4028/p-Cv6rt1	In recent years, the general population has become increasingly aware of the importance of adopting more sustainable lifestyles. For companies, the implementation of sustainable systems is essential. This study aims to examine the contribution of simulation, in combination with artificial intelligence (AI), to the sustainability of production lines. Simulation plays a crucial role for managers, as it allows for the prediction of future scenarios based on past experiences, thus enabling more informed decisions. With the rise of digitization in the industry, it is now possible to manage resources such as energy and water in a more efficient manner. This is achieved through the use of techniques such as data scanning, communication with intelligent industrial sensors-known as the Industrial Internet of Things (IIoT)-and the application of optimization and AI-based solutions to tackle complex problems, both in terms of efficiency and sustainability. This analysis has confirmed the significance of simulation, when partnered with AI, in improving the sustainability of production lines. Thus, it constitutes a means to improve resource management from an economic, environmental, and social perspective. Β© 2023 Trans Tech Publications Ltd, Switzerland.