Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Data Science in Water Conservancy Engineering
share announcement

Data Science in Water Conservancy Engineering

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 10 November 2024 | Viewed by 2076

Special Issue Editors

Prof. Dr. Jun Feng

E-Mail Website
Guest Editor
Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing 211100, China
Interests: data management; spatiotemporal indexing and search methods; knowledge engineering; domain data mining; intelligent water conservancy
Dr. Yirui Wu

E-Mail Website
Guest Editor
College of Computer and Information, Hohai University, Nanjing 211100, China
Interests: computer vision; artifical intelligence; multimedia computing; intelligent water conservancy
Special Issues, Collections and Topics in MDPI journals
Dr. Xiaodong Li

E-Mail Website
Guest Editor
College of Computer and Information, Hohai University, Nanjing 211100, China
Interests: data mining; mining algorithms and analysis methods of structured and unstructured data; research on knowledge graph; knowledge extraction and representation; knowledge reasoning technology; reinforcement learning; learning algorithm design and performance optimization method research

Special Issue Information

Dear Colleagues,

With the development of water conservancy engineering and the construction of infrastructure, water resources are properly managed and protected, contributing to the economic growth. It is noted that the social progress has exposed the drawbacks of current water conservancy engineering, and the management efficiency of water resources is low. The key reason lies in the lack of involving both expert experience and data intelligent to overcome the backwardness of current management technology. Therefore, water conservancy engineering needs intelligent management technology. As a promising field of data statistics, data science has shown considerable potential in the collection, analysis and utilization of water conservancy data. Recent research shows that there are various data science methods that have been used to meet the relevant needs of other fields, and have shown excellent performance. How to apply existing data science methods in water conservancy engineering, or realize new data science technologies more suitable for water conservancy scenarios, is of great significance for water conservancy data management.

Combined with applied mathematics, statistics, pattern recognition, machine learning and other methods, data science can predict, interpret and make decisions on water conservancy data by studying the “data world”. In addition, reliable data science methods should be customized or have an interpretable theoretical basis to promote the continuous progress and leapfrog development of water conservancy engineering. This Research Topic focuses on data science in water conservancy engineering, including data collection, data analysis, data decision-making and other related technological innovations. In order to connect novel data science with water conservancy engineering, and stimulate the potential of data science in water conservancy, this research welcomes researchers and practitioners from academia and industry to explore more new applications and technological innovations.

The topics of interest for this Special Issue include, but are not limited to:

  1. Data mining in water conservancy engineering;
  2. Data governance technology in water conservancy engineering;
  3. Big data analytics in water conservancy engineering;
  4. Data-driven technology in water conservancy engineering;
  5. Knowledge-aware technology in water conservancy engineering;
  6. Explainable data science in water conservancy engineering;
  7. Visualization of data science in water conservancy engineering;
  8.  Data science applications in water conservancy engineering.

Prof. Dr. Jun Feng
Dr. Yirui Wu
Dr. Xiaodong Li
Guest Editors

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. Applied Sciences 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 2400 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

  • smart water conservancy
  • data science
  • data mining and governance
  • big data analytics
  • explainable data science
  • data driven
  • knowledge-aware
  • visualization and applications

Published Papers (2 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

19 pages, 4568 KiB  
Article
Pore Water Pressure Prediction Based on Machine Learning Methods—Application to an Earth Dam Case
by Lu An, Daniel Dias, Claudio Carvajal, Laurent Peyras, Pierre Breul, Orianne Jenck and Xiangfeng Guo
Appl. Sci. 2024, 14(11), 4749; https://doi.org/10.3390/app14114749 - 31 May 2024
Abstract
Pore water pressure (PWP) response is significant for evaluating the earth dams’ stability, and PWPs are, therefore, generally monitored. However, due to the soil heterogeneity and its non-linear behavior within earths, the PWP is usually difficult to estimate and predict accurately in order [...] Read more.
Pore water pressure (PWP) response is significant for evaluating the earth dams’ stability, and PWPs are, therefore, generally monitored. However, due to the soil heterogeneity and its non-linear behavior within earths, the PWP is usually difficult to estimate and predict accurately in order to detect a pathology or anomaly in the behavior of an embankment dam. This study endeavors to tackle this challenge through the application of diverse machine learning (ML) techniques in estimating the PWP within an existing earth dam. The methods employed include random forest (RF) combined with simulated annealing (SA), multilayer perceptron (MLP), standard recurrent neural networks (RNNs), and gated recurrent unit (GRU). The prediction capability of these techniques was gauged using metrics such as the coefficient of determination (R2), mean square error (MSE), and CPU training time. It was found that all the considered ML methods could give satisfactory results for the PWP estimation. Upon comparing these methods within the case study, the findings suggest that, in this study, multilayer perceptron (MLP) gives the most accurate PWP prediction, achieving the highest coefficient of determination (R2 = 0.99) and the lowest mean square error (MSE = 0.0087) metrics. A sensitivity analysis is then presented to evaluate the models’ robustness and the hyperparameter’s influence on the performance of the prediction model. Full article
(This article belongs to the Special Issue Data Science in Water Conservancy Engineering)
►▼ Show Figures

Figure 1

21 pages, 4558 KiB  
Article
Data-Driven and Knowledge-Guided Heterogeneous Graphs and Temporal Convolution Networks for Flood Forecasting
by Pingping Shao, Jun Feng, Yirui Wu, Wenpeng Wang and Jiamin Lu
Appl. Sci. 2023, 13(12), 7191; https://doi.org/10.3390/app13127191 - 15 Jun 2023
Cited by 1 | Viewed by 1043
Abstract
Data-driven models have been successfully applied to flood prediction. However, the nonlinearity and uncertainty of the prediction process and the possible noise or outliers in the data set will lead to incorrect results. In addition, data-driven models are only trained from available datasets [...] Read more.
Data-driven models have been successfully applied to flood prediction. However, the nonlinearity and uncertainty of the prediction process and the possible noise or outliers in the data set will lead to incorrect results. In addition, data-driven models are only trained from available datasets and do not involve scientific principles or laws during the model training process, which may lead to predictions that do not conform to physical laws. To this end, we propose a flood prediction method based on data-driven and knowledge-guided heterogeneous graphs and temporal convolutional networks (DK-HTAN). In the data preprocessing stage, a low-rank approximate decomposition algorithm based on a time tensor was designed to interpolate the input data. Adding an attention mechanism to the heterogeneous graph module is beneficial for introducing prior knowledge. A self-attention mechanism with temporal convolutional network was introduced to dynamically calculate spatiotemporal correlation characteristics of flood data. Finally, we propose physical mechanism constraints for flood processes, adjusted and optimized data-driven models, corrected predictions that did not conform to physical mechanisms, and quantified the uncertainty of predictions. The experimental results on the Qijiang River Basin dataset show that the model has good predictive performance in terms of interval prediction index (PI), RMSE, and MAPE. Full article
(This article belongs to the Special Issue Data Science in Water Conservancy Engineering)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Prediction of cement intake based on 3D fracture connectivity
Authors: Zongxian Liu
Affiliation: State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu 610065, China; Yalong River Valley Hydropower Development Co., Ltd., Chengdu 610051, China.
Abstract: Cement intake is an important indicator that must be precisely predicted. However, most existing models overlook the vital factor - the connectivity of fractures, which will block the further improvement of prediction accuracy. To this end, a method was developed to predict the cement intake based on 3D fracture connectivity. Firstly, a 3D fracture model based on the discrete fracture network (DFN) method was established. Furthermore, digital drilling and depth first search (DFS) methods were applied to calculate the parameters that can characterize the connectivity of fractures. Finally, a prediction model for cement intake was proposed that combined deep belief network (DBN) with genetic algorithm (GA), and it has been demonstrated to be more effective and have an advantage over the previous methods by a case study.

Back to TopTop