[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.8
3.0
Journals
Water
Special Issues
Hydrological-Hydrodynamic Simulation Based on Artificial Intelligence
water-logo
Submit to Water Review for Water Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Hydrological-Hydrodynamic Simulation Based on Artificial Intelligence

A special issue of Water (ISSN 2073-4441). This special issue belongs to the section "Hydraulics and Hydrodynamics".

Deadline for manuscript submissions: closed (25 September 2024) | Viewed by 3403

Special Issue Editors

Dr. Qiang Ma

E-Mail Website
Guest Editor
China Institute of Water Resources and Hydropower Research, Beijing, China
Interests: hydrology; hydraulics; hydrodynamic; digital water; flood hazard; climate change
Dr. Morgan Abily

E-Mail Website
Guest Editor Assistant
CNRS, Observatoire de la Côte d’Azur, IRD, Géoazur, Université Côte d’Azur, Valbonne, France
Interests: hydroinformatics; hydraulics; urban water systems; flood hazards mitigation and disaster prevention; water uses; NBS; climate change
Dr. Dongwoo Jang

E-Mail Website
Guest Editor Assistant
Department of Civil & Environmental Engineering, Incheon National University, Incheon 22012, Republic of Korea
Interests: smart water grid; water distribution systems; water balance and drought assessment; numerical analysis in river hydraulics and water quality assessment
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Numerical modelling and simulation are essential ways of supporting the engineers, managers and decision makers in assessing the characteristics of the water cycle and the human impacts in the past, the present and the future. However, the growing complexity of the competition among water uses and the emerging understanding of the synergy effects within catchments and rivers have underlined the need for more detailed information to comprehend these systems. Nevertheless, dataset sources, even though they are becoming diverse and predominant in our digitalised society, remain largely unexploited within the community. Traditional physical-based hydrological–hydrodynamic modelling approaches have difficulties in transitioning toward an efficient integration in the big data era Therefore, this Special Issue aims to curate a comprehensive and interdisciplinary collection of innovations integrating big data and deep learning in hydrological and hydrodynamic processes’ simulation, introducing novel models, algorithms and frameworks that harness advanced artificial intelligence to refine the accuracy, efficiency and reliability of real-time assessment, representation and prediction.

We welcome submissions from researchers involved in experimental, theoretical, and computational aspects of high-performance hydrological–hydrodynamic modelling with artificial intelligence techniques in the field of real-time simulation, scenario analysis, parameter optimization, parallel computation, system integration, etc.

Dr. Qiang Ma
Guest Editor

Dr. Morgan Abily
Dr. Dongwoo Jang
Guest Editor Assistants

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Water is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • hydrological-hydrodynamic modelling
  • artificial intelligence
  • machine learning
  • optimization algorithm
  • high performance computation
  • real-time simulation
  • climate change
  • digital water

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

30 pages, 4803 KiB  
Article
Advanced Prediction Models for Scouring Around Bridge Abutments: A Comparative Study of Empirical and AI Techniques
by Zaka Ullah Khan, Diyar Khan, Nadir Murtaza, Ghufran Ahmed Pasha, Saleh Alotaibi, Aïssa Rezzoug, Brahim Benzougagh and Khaled Mohamed Khedher
Water 2024, 16(21), 3082; https://doi.org/10.3390/w16213082 - 28 Oct 2024
Cited by 2 | Viewed by 878
Abstract
Scouring is a major concern affecting the overall stability and safety of a bridge. The current research investigated the effectiveness of the various artificial intelligence (AI) techniques, such as artificial neural networks (ANNs), the adaptive neuro-fuzzy inference system (ANFIS), and random forest (RF), [...] Read more.
Scouring is a major concern affecting the overall stability and safety of a bridge. The current research investigated the effectiveness of the various artificial intelligence (AI) techniques, such as artificial neural networks (ANNs), the adaptive neuro-fuzzy inference system (ANFIS), and random forest (RF), for scouring depth prediction around a bridge abutment. This study attempted to make a comparative analysis between these AI models and empirical equations developed by various researchers. The current research paper utilized a dataset of water depth (Y), flow velocity (V), discharge (Q), and sediment particle diameter (d50) from a controlled laboratory setting. An efficient optimization tool (MATLAB Optimization Tool (version R2023a)) was used to develop a scour estimation formula around bridge abutments. The findings of the current investigation demonstrated the superior performance of the AI models, especially the ANFIS model, over empirical equations by precisely capturing the non-linear and complex interactions between these parameters. Moreover, the result of the sensitivity analysis demonstrated flow velocity and discharge to be the most influencing parameters affecting the scouring depth around a bridge abutment. The results of the current research highlight the precise and accurate prediction of the scouring depth around a bridge abutment using AI models. However, the empirical equation (Equation 2) demonstrated better performance with a higher R-value of 0.90 and a lower MSE value of 0.0012 compared to other empirical equations. The findings revealed that ANFIS, when combined with neural networks and fuzzy logic systems, produced highly accurate and precise results compared to the ANN models. Full article
(This article belongs to the Special Issue Hydrological-Hydrodynamic Simulation Based on Artificial Intelligence)
►▼ Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
<p>Laboratory setup and experimental data collection around the bridge abutment.</p> Full article ">Figure 2
<p>Flowchart of research methodology including AI techniques and empirical equations Proposed by Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>].</p> Full article ">Figure 3
<p>Architecture of the ANN, ANFIS, and RF model and various layers (<b>a</b>) Working mechanism of the ANN model architecture, (<b>b</b>) flowchart of the ANN model architecture, (<b>c</b>) ANFIS working mechanism, (<b>d</b>) flowchart of random forest model. ANN: artificial neural network, ANFIS: adaptive neuro-fuzzy inference system, and RF: random forest.</p> Full article ">Figure 3 Cont.
<p>Architecture of the ANN, ANFIS, and RF model and various layers (<b>a</b>) Working mechanism of the ANN model architecture, (<b>b</b>) flowchart of the ANN model architecture, (<b>c</b>) ANFIS working mechanism, (<b>d</b>) flowchart of random forest model. ANN: artificial neural network, ANFIS: adaptive neuro-fuzzy inference system, and RF: random forest.</p> Full article ">Figure 4
<p>Various nine input combinations of different variables.</p> Full article ">Figure 5
<p>Result of double-layer (DL) and triple-layer (TL) ANN model against different numbers of neurons in the hidden layer. (<b>a</b>) DL-ANN models R-value. (<b>b</b>) DL-ANN models MSE values. (<b>c</b>) TL-ANN models R-values. (<b>d</b>) TL-ANN models MSE values. R: correlation coefficient; MSE: mean square error.</p> Full article ">Figure 5 Cont.
<p>Result of double-layer (DL) and triple-layer (TL) ANN model against different numbers of neurons in the hidden layer. (<b>a</b>) DL-ANN models R-value. (<b>b</b>) DL-ANN models MSE values. (<b>c</b>) TL-ANN models R-values. (<b>d</b>) TL-ANN models MSE values. R: correlation coefficient; MSE: mean square error.</p> Full article ">Figure 6
<p>Comparative analysis of different AI models. (<b>a</b>) Comparison of the ANN(DL-10), ANFIS, RF, developed equation, and empirical equation (Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>], based on an R-value. (<b>b</b>) Comparison of the ANN(DL-10), ANFIS, RF, developed equation, and empirical equation based on the predicted values. (<b>c</b>) Comparison of ANN(TL-10), ANFIS, RF, developed equation, and empirical equation (Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>]) based on an R-value. (<b>d</b>) Comparison of ANN(TL-10), ANFIS, RF, developed equation, and empirical equation (Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>]) based on the predicted values. DL and TL represent double and triple layers, ANN represents the artificial neural network, ANFIS represents an adaptive neuro-fuzzy inference system, RF represents random forest, and Ds/Y represents non-dimensional scour depth.</p> Full article ">Figure 6 Cont.
<p>Comparative analysis of different AI models. (<b>a</b>) Comparison of the ANN(DL-10), ANFIS, RF, developed equation, and empirical equation (Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>], based on an R-value. (<b>b</b>) Comparison of the ANN(DL-10), ANFIS, RF, developed equation, and empirical equation based on the predicted values. (<b>c</b>) Comparison of ANN(TL-10), ANFIS, RF, developed equation, and empirical equation (Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>]) based on an R-value. (<b>d</b>) Comparison of ANN(TL-10), ANFIS, RF, developed equation, and empirical equation (Ettema [<a href="#B29-water-16-03082" class="html-bibr">29</a>], Shen [<a href="#B30-water-16-03082" class="html-bibr">30</a>], and Yanmaz [<a href="#B31-water-16-03082" class="html-bibr">31</a>]) based on the predicted values. DL and TL represent double and triple layers, ANN represents the artificial neural network, ANFIS represents an adaptive neuro-fuzzy inference system, RF represents random forest, and Ds/Y represents non-dimensional scour depth.</p> Full article ">Figure 7
<p>Influence of various neurons in the hidden layer and input combination on ANN models: (<b>a</b>) various neurons in the hidden layer; (<b>b</b>) various input combinations. IC1 to IC9 represent various input combinations.</p> Full article ">Figure 8
<p>Result of sensitivity analysis by various empirical equations: (<b>a</b>) empirical equation derived by Ref. [<a href="#B2-water-16-03082" class="html-bibr">2</a>], (<b>b</b>) empirical equation derived by Ref. [<a href="#B53-water-16-03082" class="html-bibr">53</a>], (<b>c</b>) empirical equation derived by Ref. [<a href="#B54-water-16-03082" class="html-bibr">54</a>], (<b>d</b>) Monte Carlo sensitivity analysis. Fr: Froude number, Y: water depth, b: channel width, and La: abutment length.</p> Full article ">Figure 9
<p>ANOVA, <span class="html-italic">t</span>-test, and Taylor’s diagram result: (<b>a</b>) ANOVA and <span class="html-italic">t</span>-test, (<b>b</b>) comparison of the 7 DL-ANN models with the ANFIS and RF models, (<b>c</b>) comparison of the 7 TL-ANN models with the ANFIS and RF models.</p> Full article ">
15 pages, 5351 KiB  
Article
Estimation of Hydraulic and Water Quality Parameters Using Long Short-Term Memory in Water Distribution Systems
by Nadia Sadiki and Dong-Woo Jang
Water 2024, 16(21), 3028; https://doi.org/10.3390/w16213028 - 22 Oct 2024
Viewed by 1157
Abstract
Predicting essential water quality parameters, such as discharge, pressure, turbidity, temperature, conductivity, residual chlorine, and pH, is crucial for ensuring the safety and efficiency of water supply systems. This study employs long short-term memory (LSTM) networks to address the challenge of capturing temporal [...] Read more.
Predicting essential water quality parameters, such as discharge, pressure, turbidity, temperature, conductivity, residual chlorine, and pH, is crucial for ensuring the safety and efficiency of water supply systems. This study employs long short-term memory (LSTM) networks to address the challenge of capturing temporal dependencies in these complex processes. Our approach, using a robust LSTM-based model, has demonstrated significant predictive accuracy, as evidenced by substantial R-squared values (e.g., 0.86 for discharge and 0.97 for conductivity). These models have proven particularly effective in handling non-linear patterns and time-series data, which are prevalent in water quality metrics. The results indicate the potential for LSTMs not only to enhance the real-time monitoring of water systems but also to aid in the strategic planning and management of water supply systems. This study’s findings can serve as a basis for further research into the integration of AI in environmental engineering, particularly for predictive tasks in complex, dynamic systems. Full article
(This article belongs to the Special Issue Hydrological-Hydrodynamic Simulation Based on Artificial Intelligence)
►▼ Show Figures

Figure 1

Figure 1
<p>RNN and LSTM architecture [<a href="#B34-water-16-03028" class="html-bibr">34</a>]. (<b>a</b>) RNN with a single activation layer; (<b>b</b>) LSTM with 4 layers.</p> Full article ">Figure 2
<p>Forget gate layer [<a href="#B34-water-16-03028" class="html-bibr">34</a>].</p> Full article ">Figure 3
<p>Input gate layer [<a href="#B34-water-16-03028" class="html-bibr">34</a>].</p> Full article ">Figure 4
<p>Output gate layer [<a href="#B34-water-16-03028" class="html-bibr">34</a>].</p> Full article ">Figure 5
<p>Target District Metered Area.</p> Full article ">Figure 6
<p>Input data: (<b>a</b>) discharge, (<b>b</b>) pressure, (<b>c</b>) residual chlorine, (<b>d</b>) conductivity, (<b>e</b>) temperature, (<b>f</b>) turbidity, and (<b>g</b>) pH.</p> Full article ">Figure 7
<p>Discharge results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">Figure 8
<p>Pressure results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">Figure 9
<p>Residual chlorine results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">Figure 10
<p>Conductivity results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">Figure 11
<p>Temperature results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">Figure 12
<p>pH results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">Figure 13
<p>Turbidity results. (<b>a</b>) Plot. (<b>b</b>) Scatter plot. (<b>c</b>) Boxplot.</p> Full article ">
17 pages, 2693 KiB  
Article
Optimization of Water Distribution Network Demand Patterns Using Real-Coded Genetic Algorithms
by Dong-Hwi Kim and Dong-Woo Jang
Water 2024, 16(20), 2971; https://doi.org/10.3390/w16202971 - 18 Oct 2024
Viewed by 808
Abstract
The penetration rate of water supply via water supply facilities in the Republic of Korea has reached 99%, with 94% of the energy for operation consumed by pumps transporting water. Consequently, developing efficient pump operation techniques is crucial for reducing energy costs in [...] Read more.
The penetration rate of water supply via water supply facilities in the Republic of Korea has reached 99%, with 94% of the energy for operation consumed by pumps transporting water. Consequently, developing efficient pump operation techniques is crucial for reducing energy costs in water supply systems. This study employs real-coded genetic algorithm techniques to compute optimized demand patterns, considering the utilization of water tanks within networks. Hydraulic appropriateness is verified by evaluating pressure within nodes determined by derived patterns through numerical analysis simulations. Furthermore, after calculating flows supplied to the networks, pump power is determined, and resultant energy costs are estimated to evaluate economic feasibility. Results indicate that pressure distribution in networks with optimal patterns is hydraulically appropriate, meeting hydrodynamic pressure conditions suggested in water supply design standards. Additionally, this study demonstrates a 9% reduction in network energy costs compared to existing patterns. The model presented herein offers a means to efficiently operate water supply systems through water tanks, thereby reducing energy costs. Full article
(This article belongs to the Special Issue Hydrological-Hydrodynamic Simulation Based on Artificial Intelligence)
►▼ Show Figures

Figure 1

Figure 1
<p>Flow chart of the study.</p> Full article ">Figure 2
<p>Components of a genetic algorithm.</p> Full article ">Figure 3
<p>Schematic diagram of a modified simple crossover [<a href="#B26-water-16-02971" class="html-bibr">26</a>].</p> Full article ">Figure 4
<p>EPANET network map of the target area.</p> Full article ">Figure 5
<p>Initial demand patterns in City A.</p> Full article ">Figure 6
<p>Electricity tariff for high-voltage A for industrial use in summer [<a href="#B28-water-16-02971" class="html-bibr">28</a>].</p> Full article ">Figure 7
<p>Calculation results of the objective function and convergence process.</p> Full article ">Figure 8
<p>Graphs of optimized demand pattern results and electricity tariff per time (hour).</p> Full article ">Figure 9
<p>Pressure distribution map of the network with optimized demand patterns (06:00).</p> Full article ">Figure 10
<p>Pressure distribution map of the network with optimized demand patterns (16.00).</p> Full article ">Figure 11
<p>Comparison of pressure distribution per hour at target nodes: (<b>a</b>) target nodes before the application of optimized demand patterns; (<b>b</b>) target nodes after the application of optimized demand patterns.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop