Optimization and Prediction of Water Quality Model Based on Artificial Intelligence

A special issue of Water (ISSN 2073-4441). This special issue belongs to the section "New Sensors, New Technologies and Machine Learning in Water Sciences".

Deadline for manuscript submissions: closed (20 June 2023) | Viewed by 40092

Special Issue Editors


E-Mail Website
Guest Editor
State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Yangtze Institute for Conservation and Development, Hohai University, Nanjing 210098, China
Interests: integrated stormwater management; urban diffuse pollution
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
1. School of Management Science and Engineering, Chongqing Technology and Business University, Chongqing 400067, China 2. Centro de Electrónica, Optoelectronica e Telecomunicações, Universidade do Algarve, 8005139 Faro, Portugal
Interests: water resources management; forecasting with intelligent modelling; big data techniques and application

E-Mail Website
Guest Editor
School of Environment, South China Normal University, University Town, Guangzhou, China
Interests: drinking water quality; intelligent modelling
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Natural water qualities such as lakes, streams, and estuaries are influenced by anthropogenic activities, and water deterioration and the need for further treatment is one of the direst and most worrisome issues. Accurate water quality prediction helps to implement early warning decision activities, which are usually considered a cost-effective and alternative water management measure. Traditional process-based models are the main tools for water pollution prediction, which could provide a coherent prediction of pollutant transport and distribution in time and space. However, it is difficult or less accurate to predict pollutants with traditional models due to the complex physical–chemical process-induced uncertainty of parameter values and the complexity of the simulation.

A recent big wave in machine learning has led to massive successes in different research matrices by leveraging large amounts of training data. Machine learning approaches have shown great abilities to extract featured information and identify the inherent correlations and patterns among complex datasets. However, the effectiveness, reliability, accuracy, as well as usability of machine learning algorithms in optimization and prediction of water quality are still largely unexplored.

Accordingly, the primary purpose of this Special Issue is to provide recent studies on novel machine learning approaches for tackling problems in water supply/distribution systems, river networks, water quality assessment, classical and emerging pollutant transportation, etc. Theoretical and practical advancements in physics-informed and/or theory-guided machine learning approaches are also welcomed.

Prof. Dr. Jin Zhang
Prof. Dr. Yun Bai
Prof. Dr. Pei Hua
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. 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

  • deep learning tools
  • novel machine learning algorithms
  • intelligent forecasting
  • uncertainty quantification
  • neural networks
  • water supply/distribution systems
  • data-driven techniques
  • water quality model
  • predicting classical and emerging contaminants
  • low carbon–water quality-based forecasting and decision making

Published Papers (13 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

26 pages, 36202 KiB  
Article
Physics-Informed Neural Networks-Based Salinity Modeling in the Sacramento–San Joaquin Delta of California
by Dong Min Roh, Minxue He, Zhaojun Bai, Prabhjot Sandhu, Francis Chung, Zhi Ding, Siyu Qi, Yu Zhou, Raymond Hoang, Peyman Namadi, Bradley Tom and Jamie Anderson
Water 2023, 15(13), 2320; https://doi.org/10.3390/w15132320 - 21 Jun 2023
Cited by 2 | Viewed by 1472
Abstract
Salinity in estuarine environments has been traditionally simulated using process-based models. More recently, data-driven models including artificial neural networks (ANNs) have been developed for simulating salinity. Compared to process-based models, ANNs yield faster salinity simulations with comparable accuracy. However, ANNs are often purely [...] Read more.
Salinity in estuarine environments has been traditionally simulated using process-based models. More recently, data-driven models including artificial neural networks (ANNs) have been developed for simulating salinity. Compared to process-based models, ANNs yield faster salinity simulations with comparable accuracy. However, ANNs are often purely data-driven and not constrained by physical laws, making it difficult to interpret the causality between input and output data. Physics-informed neural networks (PINNs) are emerging machine-learning models to integrate the benefits of both process-based models and data-driven ANNs. PINNs can embed the knowledge of physical laws in terms of the partial differential equations (PDE) that govern the dynamics of salinity transport into the training of the neural networks. This study explores the application of PINNs in salinity modeling by incorporating the one-dimensional advection–dispersion salinity transport equation into the neural networks. Two PINN models are explored in this study, namely PINNs and FoNets. PINNs are multilayer perceptrons (MLPs) that incorporate the advection–dispersion equation, while FoNets are an extension of PINNs with an additional encoding layer. The exploration is exemplified at four study locations in the Sacramento–San Joaquin Delta of California: Pittsburg, Chipps Island, Port Chicago, and Martinez. Both PINN models and benchmark ANNs are trained and tested using simulated daily salinity from 1991 to 2015 at study locations. Results indicate that PINNs and FoNets outperform the benchmark ANNs in simulating salinity at the study locations. Specifically, PINNs and FoNets have lower absolute biases and higher correlation coefficients and Nash–Sutcliffe efficiency values than ANNs. In addition, PINN models overcome some limitations of purely data-driven ANNs (e.g., neuron saturation) and generate more realistic salinity simulations. Overall, this study demonstrates the potential of PINNs to supplement existing process-based and ANN models in providing accurate and timely salinity estimation. Full article
Show Figures

Figure 1

16 pages, 3435 KiB  
Article
Principal Component Analysis and the Water Quality Index—A Powerful Tool for Surface Water Quality Assessment: A Case Study on Struma River Catchment, Bulgaria
by Ivan Benkov, Marian Varbanov, Tony Venelinov and Stefan Tsakovski
Water 2023, 15(10), 1961; https://doi.org/10.3390/w15101961 - 22 May 2023
Cited by 5 | Viewed by 3952
Abstract
The water quality assessment of the surface water bodies (SWBs) is one of the major tasks of environmental authorities dealing with water management. The present study proposes a water quality assessment scheme for the investigation of the surface waters’ physicochemical status changes and [...] Read more.
The water quality assessment of the surface water bodies (SWBs) is one of the major tasks of environmental authorities dealing with water management. The present study proposes a water quality assessment scheme for the investigation of the surface waters’ physicochemical status changes and the identification of significant anthropogenic pressures. It is designed to extract valuable knowledge from the Water Frame Directive (WFD) mandatory monitoring datasets. The water quality assessment scheme is based on the Canadian Council of Ministers of the Environment water quality index (CCME-WQI), trend analysis of estimated WQI values, and Principal Component Analysis (PCA) using calculated excursions during the determination of WQI values. The combination of the abovementioned techniques preserves their benefits and additionally provides important information for water management by revealing the latent factors controlling water quality, taking into account the type of the SWB. The results enable the identification of the anthropogenic impact on SWBs and the type of the corresponding anthropogenic pressure, prioritization and monitoring restoration measures, and optimization of conducted monitoring programs to reflect significant anthropogenic pressures. The proposed simple and reliable assessment scheme is flexible to introducing additional water quality indicators (hydrological, biological, specific pollutants, etc.), which could lead to a more comprehensive surface water quality assessment. Full article
Show Figures

Figure 1

18 pages, 3357 KiB  
Article
Data-Driven Parameter Prediction of Water Pumping Station
by Jun Zhang, Yongchuan Yu, Jianzhuo Yan and Jianhui Chen
Water 2023, 15(6), 1128; https://doi.org/10.3390/w15061128 - 15 Mar 2023
Cited by 1 | Viewed by 1808
Abstract
In the construction process of an intelligent pumping station, the parameter calibration of the pumping station unit is very important. In actual engineering, the working parameters of the pumping station are affected by complex working conditions and natural factors, so that it is [...] Read more.
In the construction process of an intelligent pumping station, the parameter calibration of the pumping station unit is very important. In actual engineering, the working parameters of the pumping station are affected by complex working conditions and natural factors, so that it is difficult to establish a traditional physical model for the pumping station. This paper uses a data-driven method to apply the hybrid model of the convolutional neural network (CNN) and long-term short-term memory network (LSTM) to water level prediction in pumping stations and adds self-attention mechanism feature selection and a bagging optimization algorithm. Then, after an error analysis of the hybrid model, a performance comparison experiment with the separate model was conducted. The historical data of the pumping station project provided by the Tuancheng Lake Management Office of Beijing South-to-North Water Diversion Project was used to train and verify the proposed pumping station water level prediction model. The results show that the CNN–LSTM model based on the self-attention mechanism has higher accuracy than the separate CNN model and LSTM model, with a correlation coefficient (R2) of 0.72 and a mean absolute error (MAE) of 19.14. The model can effectively solve the problem of water level prediction in the front and rear pools under complex pumping station conditions. Full article
Show Figures

Figure 1

15 pages, 3194 KiB  
Article
Predicting Influent and Effluent Quality Parameters for a UASB-Based Wastewater Treatment Plant in Asia Covering Data Variations during COVID-19: A Machine Learning Approach
by Parul Yadav, Manik Chandra, Nishat Fatima, Saqib Sarwar, Aditya Chaudhary, Kumar Saurabh and Brijesh Singh Yadav
Water 2023, 15(4), 710; https://doi.org/10.3390/w15040710 - 11 Feb 2023
Cited by 3 | Viewed by 3685
Abstract
A region’s population growth inevitably results in higher water consumption. This persistent rise in water use increases the region’s wastewater production. Consequently, due to this increase in wastewater (influent), Wastewater Treatment Plants (WWTPs) are required to run effectively in order to handle the [...] Read more.
A region’s population growth inevitably results in higher water consumption. This persistent rise in water use increases the region’s wastewater production. Consequently, due to this increase in wastewater (influent), Wastewater Treatment Plants (WWTPs) are required to run effectively in order to handle the huge demand for treated/processed water (effluent). Knowing in advance the influent and effluent parameters increases the operational efficiency and enables cost-effective utilization of diverse resources at wastewater treatment plants. This paper is based on a prediction/forecasting of an influent quality parameter, namely total MLD, as well as effluent quality parameters, namely MPN, BOD, DO, COD and pH for the real-time data collected pre-, during and post-COVID-19 at the Bharwara WWTP in Lucknow, India. It is the largest UASB-based wastewater treatment facility in Uttar Pradesh and the second largest in Asia. In this paper, we propose a novel model namely, wPred comprising extensions of SARIMA with seasonal order and ANN-based ML models to estimate the influent and effluent quality parameters, respectively, and compare it with the existing machine learning models. The lowest sMAPE error for the influent parameters using wPred is 2.59%. The findings of the paper show a strong correlation (R-value), up to 0.99, between the effluent parameters actually measured and predicted. As a result, the model designed in this paper has an acceptable level of accuracy and generalizability which efficiently predicts/forecasts the performance of Bharwara WWTP. Full article
Show Figures

Figure 1

31 pages, 17931 KiB  
Article
Novel Salinity Modeling Using Deep Learning for the Sacramento–San Joaquin Delta of California
by Siyu Qi, Minxue He, Zhaojun Bai, Zhi Ding, Prabhjot Sandhu, Francis Chung, Peyman Namadi, Yu Zhou, Raymond Hoang, Bradley Tom, Jamie Anderson and Dong Min Roh
Water 2022, 14(22), 3628; https://doi.org/10.3390/w14223628 - 11 Nov 2022
Cited by 2 | Viewed by 2536
Abstract
Water resources management in estuarine environments for water supply and environmental protection typically requires estimates of salinity for various flow and operational conditions. This study develops and applies two novel deep learning (DL) models, a residual long short-term memory (Res-LSTM) network, and a [...] Read more.
Water resources management in estuarine environments for water supply and environmental protection typically requires estimates of salinity for various flow and operational conditions. This study develops and applies two novel deep learning (DL) models, a residual long short-term memory (Res-LSTM) network, and a residual gated recurrent unit (Res-GRU) model, in estimating the spatial and temporal variations of salinity. Four other machine learning (ML) models, previously developed and reported, consisting of multi-layer perceptron (MLP), residual network (ResNet), LSTM, and GRU are utilized as the baseline models to benchmark the performance of the two novel models. All six models are applied at 23 study locations in the Sacramento–San Joaquin Delta (Delta), the hub of California’s water supply system. Model input features include observed or calculated tidal stage (water level), flow and salinity at model upstream boundaries, salinity control gate operations, crop consumptive use, and pumping for the period of 2001–2019. Meanwhile, field observations of salinity at the study locations during the same period are also utilized for the development of the predictive use of the models. Results indicate that the proposed DL models generally outperform the baseline models in simulating and predicting salinity on both daily and hourly scales at the study locations. The absolute bias is generally less than 5%. The correlation coefficients and Nash–Sutcliffe efficiency values are close to 1. Particularly, Res-LSTM has slightly superior performance over Res-GRU. Moreover, the study investigates the overfitting issues of both the DL and baseline models. The investigation indicates that overfitting is not notable. Finally, the study compares the performance of Res-LSTM against that of an operational process-based salinity model. It is shown Res-LSTM outperforms the process-based model consistently across all study locations. Overall, the study demonstrates the feasibility of DL-based models in supplementing the existing operational models in providing accurate and real-time estimates of salinity to inform water management decision making. Full article
Show Figures

Figure 1

27 pages, 4568 KiB  
Article
Micro-Climate Computed Machine and Deep Learning Models for Prediction of Surface Water Temperature Using Satellite Data in Mundan Water Reservoir
by Sabastian Simbarashe Mukonza and Jie-Lun Chiang
Water 2022, 14(18), 2935; https://doi.org/10.3390/w14182935 - 19 Sep 2022
Cited by 2 | Viewed by 2903
Abstract
Water temperature is an important indicator of water quality for surface water resources because it impacts solubility of dissolved gases in water, affects metabolic rates of aquatic inhabitants, such as fish and harmful algal blooms (HABs), and determines the fate of water resident [...] Read more.
Water temperature is an important indicator of water quality for surface water resources because it impacts solubility of dissolved gases in water, affects metabolic rates of aquatic inhabitants, such as fish and harmful algal blooms (HABs), and determines the fate of water resident biogeochemical nutrients. Furthermore, global warming is causing a widespread rise in temperature levels in water sources on a global scale, threatening clean drinking water supplies. Therefore, it is key to increase the frequency of spatio-monitoring for surface water temperature (SWT). However, there is a lack of comprehensive SWT monitoring datasets because current methods for monitoring SWT are costly, time consuming, and not standardized. The research objective of this study was to estimate SWT using data from the Landsat-8 (L8) and Sentinel-3 (S3) satellites. To do this, we used machine learning techniques, such as Support Vector Regression (SVR), Gaussian Process Regression (GPR), simple neural network (ANN), and deep learning techniques (Long Short Term Memory, LSTM, and Convolutional Long Short Term Memory, 1D ConvLSTM). Using deep and machine learning techniques to regress satellite data to estimate SWT presents a number of challenges, including prediction uncertainty, over- or under-estimation of measured values, and significant variation in the final estimated data. The performance of the L8 ConvLSTM model was superior to all other methods (R2 of 0.93 RMSE of 0.16 °C, and bias of 0.01 °C). The factors that had a significant effect on the model’s accuracy performance were identified and quantified using a two-factor analysis of variance (ANOVA) analysis. The results demonstrate that the main effects and interaction of the type of machine/deep learning (ML/DL) model and the type of satellite have statistically significant effects on the performances of the different models. The test statistics are as follows: (satellite type main effect p *** ≤ 0.05, Ftest = 15.4478), (type of ML/DL main effect p *** ≤ 0.05, Ftest = 17.4607) and (interaction, satellite type × type of ML/DL p ** ≤ 0.05, Ftest = 3.5325), respectively. The models were successfully deployed to enable satellite remote sensing monitoring of SWT for the reservoir, which will help to resolve the limitations of the conventional sampling and laboratory techniques. Full article
Show Figures

Figure 1

16 pages, 1578 KiB  
Article
Designing Efficient and Sustainable Predictions of Water Quality Indexes at the Regional Scale Using Machine Learning Algorithms
by Abdessamed Derdour, Antonio Jodar-Abellan, Miguel Ángel Pardo, Sherif S. M. Ghoneim and Enas E. Hussein
Water 2022, 14(18), 2801; https://doi.org/10.3390/w14182801 - 9 Sep 2022
Cited by 12 | Viewed by 2905
Abstract
Water quality and scarcity are key topics considered by the Sustainable Development Goals (SDGs), institutions, policymakers and stakeholders to guarantee human safety, but also vital to protect natural ecosystems. However, conventional approaches to deciding the suitability of water for drinking purposes are often [...] Read more.
Water quality and scarcity are key topics considered by the Sustainable Development Goals (SDGs), institutions, policymakers and stakeholders to guarantee human safety, but also vital to protect natural ecosystems. However, conventional approaches to deciding the suitability of water for drinking purposes are often costly because multiple characteristics are required, notably in low-income countries. As a result, building right and trustworthy models is mandatory to correctly manage available groundwater resources. In this research, we propose to check multiple classification techniques such as Decision Trees (DT), K-Nearest Neighbors (KNN), Discriminants Analysis (DA), Support Vector Machine (SVM), and Ensemble Trees (ET) to design the best strategy allowing the forecast a Water Quality Index (WQI). To achieve this goal, an extended dataset characterized by water samples collected in a total of twelve municipalities of the Wilaya of Naâma in Algeria was considered. Among them, 151 samples were examined as training samples, and 18 were used to test and confirm the prediction model. Later, data samples were classified based on the WQI into four states: excellent water quality, good water quality, poor water quality, and very poor or unsafe water. The main results revealed that the SVM classifier obtained the highest forecast accuracy, with 95.4% of prediction accuracy when the data are standardized and 88.9% for the accuracy of the test samples. The results confirmed that the use of machine learning models are powerful tools for forecasting drinking water as larger scales to promote the design of efficient and sustainable water quality control and support decision-plans. Full article
Show Figures

Figure 1

14 pages, 3148 KiB  
Article
Application of a New Architecture Neural Network in Determination of Flocculant Dosing for Better Controlling Drinking Water Quality
by Huihao Luo, Xiaoshang Li, Fang Yuan, Cheng Yuan, Wei Huang, Qiannan Ji, Xifeng Wang, Binzhi Liu and Guocheng Zhu
Water 2022, 14(17), 2727; https://doi.org/10.3390/w14172727 - 1 Sep 2022
Cited by 1 | Viewed by 2037
Abstract
In drinking water plants, accurate control of flocculation dosing not only improves the level of operation automation, thus reducing the chemical cost, but also strengthens the monitoring of pollutants in the whole water system. In this study, we used feedforward signal and feedback [...] Read more.
In drinking water plants, accurate control of flocculation dosing not only improves the level of operation automation, thus reducing the chemical cost, but also strengthens the monitoring of pollutants in the whole water system. In this study, we used feedforward signal and feedback signal data to establish a back-propagation (BP) model for the prediction of flocculant dosing. We examined the effect of the particle swarm optimization (PSO) algorithm and data type on the simulation performance of the model. The results showed that the parameters, such as the learning factor, population size, and number of generations, significantly affected the simulation. The best optimization conditions were attained at a learning factor of 1.4, population size of 20, 20 generations, 8 feedforward signals and 1 feedback signal as input data, 6 hidden layer nodes, and 1 output node. The coefficient of determination (R2) between the predicted and measured values was 0.68, and the root mean square error (RMSE) was lower than 20%, showing a good prediction result. Weak time-delay data enhanced the model accuracy, which increased the R2 to 0.73. Overall, with the hybridized data, PSO, and weak time-delay data, the new architecture neural network was able to predict flocculant dosing. Full article
Show Figures

Figure 1

25 pages, 4073 KiB  
Article
Spatiotemporal Variation and Driving Factors of Water Supply Services in the Three Gorges Reservoir Area of China Based on Supply-Demand Balance
by Jia He, Yiqiu Zhao and Chuanhao Wen
Water 2022, 14(14), 2271; https://doi.org/10.3390/w14142271 - 21 Jul 2022
Cited by 5 | Viewed by 2439
Abstract
Water supply services (WSSs) are critical to human survival and development. The Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model enables an integrated, dynamic, and visual assessment of ecosystem services at different scales. In addition, Geodetector is an effective tool for identifying [...] Read more.
Water supply services (WSSs) are critical to human survival and development. The Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model enables an integrated, dynamic, and visual assessment of ecosystem services at different scales. In addition, Geodetector is an effective tool for identifying the main driving factors of spatial heterogeneity of ecosystem services. Therefore, this article takes the Three Gorges Reservoir Area (TGRA), the most prominent strategic reserve of freshwater resources in China, as the study area and uses the InVEST model to simulate the spatiotemporal heterogeneity of the supply-demand balance of WSSs and freshwater security patterns in 2005, 2010, 2015, and 2018, and explores the key driving factors of freshwater security index (FSI) with Geodetector. The total supply of WSSs in the TGRA decreased by 1.05% overall between 2005 and 2018, with the head and tail areas being low-value regions for water yield and the central part of the belly areas being high-value regions for water yield. The total demand for WSSs in the TGRA increased by 9.1%, with the tail zones and the central part of the belly zones being the high water consumption areas. In contrast, the head zones are of low water consumption. The multi-year average FSI of the TGRA is 0.12, 0.1, 0.21, and 0.16, showing an upward trend. The key ecological function areas in the TGRA are high-value FSI regions, while the tail zones in the key development areas are low-value FSI regions. Industrial water consumption significantly impacts FSI, with a multi-year average q value of 0.82. Meanwhile, the q value of industrial and domestic water consumption on FSI in 2018 increased by 43.54% and 30%, respectively, compared with 2005. This study analyzes the spatiotemporal variation of WSSs and detects the drivers in the natural-economic-social perspective and innovation in ecosystem services research. The study results can guide water resource security management in other large reservoirs or specific reservoir areas. Full article
Show Figures

Figure 1

14 pages, 2125 KiB  
Article
Using a Grey Niche Model to Predict the Water Consumption in 31 Regions of China
by Xiaoying Pan, Kai Cai and Lifeng Wu
Water 2022, 14(12), 1883; https://doi.org/10.3390/w14121883 - 11 Jun 2022
Cited by 3 | Viewed by 1787
Abstract
Regional development brings significant changes in industrial structure and water consumption. Researching the trend in water consumption by changes in industrial structure can promote water conservation. The grey niche model describes the industrial changes in China and analyzes the water consumption of different [...] Read more.
Regional development brings significant changes in industrial structure and water consumption. Researching the trend in water consumption by changes in industrial structure can promote water conservation. The grey niche model describes the industrial changes in China and analyzes the water consumption of different leading industries. Using data from 2014 to 2019, and taking the economy as the influencing reason and the industrial niche as the weight, water consumption was predicted. The average percentage errors of the prediction results were all less than 0.1%. While improving the forecasting accuracy, the water consumption forecasting has been strengthened. The calculation results show that regional industry is undergoing transformation, and tertiary industry is rising in the national economy. The successful implementation of industrial water-saving measures has kept the water consumption of industrially developed cities stable but the rapid development of tertiary industries will increase water consumption. Incorporating changes in industrial structure into water use analysis allows the Chinese government to draft water conservation policies for various industries. Full article
Show Figures

Figure 1

13 pages, 2147 KiB  
Article
Prediction of Flow Based on a CNN-LSTM Combined Deep Learning Approach
by Peifeng Li, Jin Zhang and Peter Krebs
Water 2022, 14(6), 993; https://doi.org/10.3390/w14060993 - 21 Mar 2022
Cited by 55 | Viewed by 6451
Abstract
Although machine learning (ML) techniques are increasingly used in rainfall-runoff models, most of them are based on one-dimensional datasets. In this study, a rainfall-runoff model with deep learning algorithms (CNN-LSTM) was proposed to compute runoff in the watershed based on two-dimensional rainfall radar [...] Read more.
Although machine learning (ML) techniques are increasingly used in rainfall-runoff models, most of them are based on one-dimensional datasets. In this study, a rainfall-runoff model with deep learning algorithms (CNN-LSTM) was proposed to compute runoff in the watershed based on two-dimensional rainfall radar maps directly. The model explored a convolutional neural network (CNN) to process two-dimensional rainfall maps and long short-term memory (LSTM) to process one-dimensional output data from the CNN and the upstream runoff in order to calculate the flow of the downstream runoff. In addition, the Elbe River basin in Sachsen, Germany, was selected as the study area, and the high-water periods of 2006, 2011, and 2013, and the low-water periods of 2015 and 2018 were used as the study periods. Via the fivefold validation, we found that the Nash–Sutcliffe efficiency (NSE) and Kling–Gupta efficiency (KGE) fluctuated from 0.46 to 0.97 and from 0.47 to 0.92 for the high-water period, where the optimal fold achieved 0.97 and 0.92, respectively. For the low-water period, the NSE and KGE ranged from 0.63 to 0.86 and from 0.68 to 0.93, where the optimal fold achieved 0.86 and 0.93, respectively. Our results demonstrate that CNN-LSTM would be useful for estimating water availability and flood alerts for river basin management. Full article
Show Figures

Figure 1

16 pages, 4853 KiB  
Article
A Water Consumption Forecasting Model by Using a Nonlinear Autoregressive Network with Exogenous Inputs Based on Rough Attributes
by Yihong Zheng, Wanjuan Zhang, Jingjing Xie and Qiao Liu
Water 2022, 14(3), 329; https://doi.org/10.3390/w14030329 - 23 Jan 2022
Cited by 5 | Viewed by 2910
Abstract
Scientific prediction of water consumption is beneficial for the management of water resources. In practice, many factors affect water consumption, and the various impact mechanisms are complex and uncertain. Meanwhile, the water consumption time series has a nonlinear dynamic feature. Therefore, this paper [...] Read more.
Scientific prediction of water consumption is beneficial for the management of water resources. In practice, many factors affect water consumption, and the various impact mechanisms are complex and uncertain. Meanwhile, the water consumption time series has a nonlinear dynamic feature. Therefore, this paper proposes a nonlinear autoregressive model with an exogenous input (NARX) neural network model based on rough set (RS) theory. First, the RS theory was used to analyze the importance of each attribute in water consumption. Then, the main influencing factor was selected as the input of the NARX neural network model, which was applied to predict water consumption. The proposed model is proved to give better results of a single NARX model and a back propagation neural network. The experimental results indicate that the proposed model has higher prediction accuracy in terms of the mean absolute error, mean absolute percentage error and root mean square error. Full article
Show Figures

Figure 1

21 pages, 5433 KiB  
Article
DSS-OSM: An Integrated Decision Support System for Offshore Oil Spill Management
by Pu Li, Bing Chen, Shichun Zou, Zhenhua Lu and Zekun Zhang
Water 2022, 14(1), 20; https://doi.org/10.3390/w14010020 - 22 Dec 2021
Cited by 3 | Viewed by 2888
Abstract
The marine ecosystem, human health and social economy are always severely impacted once an offshore oil spill event has occurred. Thus, the management of oil spills is of importance but is difficult due to constraints from a number of dynamic and interactive processes [...] Read more.
The marine ecosystem, human health and social economy are always severely impacted once an offshore oil spill event has occurred. Thus, the management of oil spills is of importance but is difficult due to constraints from a number of dynamic and interactive processes under uncertain conditions. An integrated decision support system is significantly helpful for offshore oil spill management, but it is yet to be developed. Therefore, this study aims at developing an integrated decision support system for supporting offshore oil spill management (DSS-OSM). The DSS-OSM was developed with the integration of a Monte Carlo simulation, artificial neural network and simulation-optimization coupling approach to provide timely and effective decision support to offshore oil spill vulnerability analysis, response technology screening and response devices/equipment allocation. In addition, the uncertainties and their interactions were also analyzed throughout the modeling of the DSS-OSM. Finally, an offshore oil spill management case study was conducted on the south coast of Newfoundland, Canada, demonstrating the feasibility of the developed DSS-OSM. Full article
Show Figures

Figure 1

Back to TopTop