Water quality modelling using principal component analysis and artificial neural network

Ibrahim, Aminu; Ismail, Azimah; Juahir, Hafizan; Iliyasu, Aisha B; Wailare, Balarabe T; Mukhtar, Mustapha; Aminu, Hassan

doi:10.1016/j.marpolbul.2022.114493

Cited by 33 publications

(8 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The primary contaminants influencing rivers worldwide include untreated sewage, the proliferation of harmful algal blooms, biodiversity degradation, and oxygen depletion due to high concentrations of chemicals. Industrial wastewater, sewage from metropolitan areas and scientific laboratories, and surface runoff from urban areas constitute the principal sources of urban wastewater [77].…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

Impact of the Citrus Industry on the Water Quality of the Filobobos River in Veracruz, Mexico

Sandoval Herazo,

González-Moreno,

Carreto-Hernandez

et al. 2024

Sustainability

View full text Add to dashboard Cite

Veracruz, Mexico, boasts abundant water resources. However, the region is facing challenges stemming from population growth and industrial expansion, leading to a notable increase in wastewater discharge into surface water bodies. This discharge has resulted in significant alterations to water quality. In this study, we analyzed the water quality in the Bobos River, Veracruz, with a focus on sustainability. A total of 12 samples were collected from various points along the reservoir. Parameters including temperature, pH, dissolved oxygen (DO), conductivity, total nitrogen (TN), nitrate, chemical oxygen demand (COD), total phosphorus (TP), phosphate, dissolved solids (DSs), and fecal coliforms (FCs) were measured and analyzed. The pH levels ranged from slightly acidic (6.40 ± 0.71) to slightly alkaline (8.65 ± 0.07), with the lowest dissolved oxygen concentration recorded at 0.15 ± 0.07 mg L−1. Conductivity varied between 0.26 and 3.81 mS. Total nitrogen concentrations ranged from 0.21 ± 3.8 to 0.491 ± 1.3 mg L−1. Dissolved solid concentrations were measured at 0.39 ± 0.05 mg L−1, while the final sampling point exhibited elevated values for temperature, nitrate, chemical oxygen demand, total phosphorus, and coliforms (30.35 ± 0.21 °C, 0.35, 389.00 ± 11.31, 13.20 ± 0.85 mg L−1, and 3.2 × 105 ± 3.707107 × 104, respectively). To address these concerning trends and safeguard public health and environmental integrity, the implementation of continuous monitoring and stringent control measures is imperative.

show abstract

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

Impact of the Citrus Industry on the Water Quality of the Filobobos River in Veracruz, Mexico

Sandoval Herazo,

González-Moreno,

Carreto-Hernandez

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…It mainly converts multiple indexes into several comprehensive indexes, and usually refers to the comprehensive indexes generated by the transformation as the main components. From a mathematical point of view, this is a dimension reduction processing technology [26][27][28]. The algorithm flowchart is shown in Figure 1.…”

Section: Principal Component Analysismentioning

confidence: 99%

Application of Correlation Analysis Based on Principal Components in the Study of Global Temperature Changes

Chen

Jiang

Cheng

et al. 2023

IJEE

View full text Add to dashboard Cite

The current issue of global warming is prominent, and there are many factors that affect global temperature changes. Therefore, how to correctly judge the relationship between each influencing factor and global temperature changes and accurately find out the main reasons of global temperature rise which are the problems that must be considered and solved to alleviate global warming at present. According to previous official data, this paper proposed a correlation analysis method based on principal components to comprehensively analyze the relationship between natural disaster factors, human factors, and global temperature changes, and find out the main reasons that affect global temperature rise. Compared with traditional research methods, the new method provided in this paper can still remain scientific and accurate calculation results while reducing computational dimensions. The experimental results showed that in the relationship between natural disasters and global temperature changes, the average correlation coefficient of the principal component represented by biological disasters and geological disasters was the highest at 0.6097 and a test value of p<0.05, indicating a significant positive correlation between them and global temperature. However, the correlation coefficient of the principal component represented by floods and storms was negative, indicating a negative correlation between them and global temperature. In exploring the main factors affecting global temperature rise, both the total global population and the total global CO2 emissions had a significant positive correlation with global temperature. Among them, the average correlation coefficient of the total global population was the highest at 0.9972, and its weight also was the highest at 26.42%. Therefore, this indicates that the total global population is the most important factor affecting global temperature rise. This study can provide reference for countries to make decisions in response to global warming.

show abstract

“…Neural networks use mathematical coding that symbolises predetermined multidimensional variable relationships [6][7][8][9][10][11][12]. Their capacity to comprehend and relate to variable dependency offers a distinct computational superiority and yields more precise WQI ratings than sub-indexing methodologies [13,14]. Like the human brain cortex, ANNs operate using analytical systems based on the structure and functionality of the biological neural configurations.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network (ANN)-Based Water Quality Index (WQI) for Assessing Spatiotemporal Trends in Surface Water Quality—A Case Study of South African River Basins

Banda,

Kumarasamy

2024

Water

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are powerful data-oriented “black-box” algorithms capable of assessing and delineating linear and multifaceted non-linear correlations between the dependent and explanatory variables. Through the years, neural networks have proven to be effective and robust analytical techniques for establishing artificial intelligence-based tools for modelling, estimating, and projecting spatial and temporal variations in water bodies. Accordingly, ANN-based algorithms gained increased attention and have emerged as practical alternatives to traditional approaches for hydro-chemical analysis. ANNs are among the widely used computer systems for modelling surface water quality. Considering their wide recognition, resilience, flexibility, and accuracy, the current study employs a neural network-based methodology to construct a novel water quality index (WQI) model suitable for analysing South African rivers. The feed-forward, back-propagated multilayered perceptron model has three parallel-distributed neuron layers interconnected with seventy weighted links orientated laterally from left to right. First, the input layer includes thirteen neuro-nodes symbolising thirteen explanatory variables, including NH3, Ca, Cl, Chl-a, EC, F CaCO3, Mg, Mn, NO3, pH, SO4, and turbidity (NTU). Second, the hidden layer consists of eleven neuro-nodes accountable for computational tasks. Lastly, the output layer features one neuron responsible for conveying network outcomes using a single-digit WQI rating extending from zero to one hundred, where zero represents substandard water quality and one hundred denotes exceptional water quality. The AI-based model was developed using water quality data obtained from six monitoring locations within four drainage basins under the management of the Umgeni Water Board in the KwaZulu-Natal Province of South Africa. The dataset comprises 416 samples randomly divided into training, testing, and validation sets using a proportional split of 70:15:15%. The Broyden–Fletcher–Goldfarb–Shanno (BFGS) technique was utilised to conduct backpropagation training and adjust synapse weights. The dependent variables are the WQI scores from the universal water quality index (UWQI) model developed specifically for South African river basins. The ANN demonstrated enhanced efficiency through an overall correlation coefficient (R) of 0.985. Furthermore, the neural network attained R-values of 0.987, 0.992, and 0.977 for the training, testing, and validation intervals. The ANN model achieved a Nash–Sutcliffe efficiency (NSE) value of 0.974 and coefficient of determination (R2) of 0.970. Sensitivity analysis provided additional validation of the preparedness and computational competence of the ANN model. The typical target-to-output error tolerance for the ANN model is 0.242, demonstrating an adequate predictive ability to deliver results comparable with the target UWQI, having the lowest and highest index ratings of 75.995 and 94.420, respectively. Accordingly, the three-layer neural network is scientifically sound, with index values and water quality evaluations corresponding to the UWQI results. The current research project seeks to document the processes used and the outcomes obtained.

show abstract

Water quality modelling using principal component analysis and artificial neural network

Cited by 33 publications

References 62 publications

Impact of the Citrus Industry on the Water Quality of the Filobobos River in Veracruz, Mexico

Impact of the Citrus Industry on the Water Quality of the Filobobos River in Veracruz, Mexico

Application of Correlation Analysis Based on Principal Components in the Study of Global Temperature Changes

Artificial Neural Network (ANN)-Based Water Quality Index (WQI) for Assessing Spatiotemporal Trends in Surface Water Quality—A Case Study of South African River Basins

Contact Info

Product

Resources

About