Applied Sciences

Research

19 pages, 3053 KB

Open AccessArticle

K-Nearest Neighbors Model to Optimize Data Classification According to the Water Quality Index of the Upper Basin of the City of Huarmey

by Hugo Vega-Huerta, Jean Pajuelo-Leon, Percy De-la-Cruz-VdV, David Calderón, Gisella Luisa Elena Maquen-Niño, Milton E. Rios-Castillo, Adegundo Camara-Figueroa, Rubén Gil-Calvo, Luis Guerra-Grados and Oscar Benito-Pacheco

Appl. Sci. 2025, 15(18), 10202; https://doi.org/10.3390/app151810202 - 19 Sep 2025

Viewed by 542

Abstract

Water quality in Peru is an increasing concern, particularly in the upper Huarmey watershed, which is affected by heavy metal contamination and untreated wastewater. This study proposes an automated classification approach using three supervised machine learning algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), [...] Read more.

Water quality in Peru is an increasing concern, particularly in the upper Huarmey watershed, which is affected by heavy metal contamination and untreated wastewater. This study proposes an automated classification approach using three supervised machine learning algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF)—to assess the water quality based on the Water Quality Index (WQI) of Peru. The experimental results show that KNN outperforms other methods, reaching an accuracy of 95.2%. The proposed system automates and improves the classification accuracy compared with manual methods based on Microsoft Excel. The methodology, performance metrics, dataset characteristics, and geographical context are detailed to ensure replicability. This algorithm assists decision-makers with environmental monitoring and public health protection. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

22 pages, 871 KB

Open AccessArticle

Advanced Graph–Physics Hybrid Framework (AGPHF) for Holistic Integration of AI-Driven Graph- and Physics- Methodologies to Promote Resilient Wastewater Management in Dynamic Real-World Conditions

by Vasileios Alevizos, Nikitas Gerolimos, Zongliang Yue, Sabrina Edralin, Clark Xu, George A. Papakostas, Eleni Vrochidou, George Marnellos and Mousa Mustafa

Appl. Sci. 2025, 15(18), 9905; https://doi.org/10.3390/app15189905 - 10 Sep 2025

Viewed by 560

Abstract

Wastewater treatment is evolving rapidly with the advent of advanced deep-learning AI, graph-based, and physics-informed approaches. This study integrates graph neural networks, physics-informed neural networks, and multi-agent reinforcement learning within a hybrid digital-twin framework, evaluated on multi-scale real-world datasets. The developed models achieved [...] Read more.

Wastewater treatment is evolving rapidly with the advent of advanced deep-learning AI, graph-based, and physics-informed approaches. This study integrates graph neural networks, physics-informed neural networks, and multi-agent reinforcement learning within a hybrid digital-twin framework, evaluated on multi-scale real-world datasets. The developed models achieved over 90% dissolved organic carbon removal and reduced aeration energy by up to 22% while maintaining process stability. The results demonstrate that graph–physics synergies not only boost operational efficiency but also reveal critical trade-offs between energy savings and hydraulic performance. Our findings establish a new benchmark for resilient, low-carbon wastewater treatment, highlighting the transformative role of data-driven system design. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

29 pages, 4733 KB

Open AccessArticle

Water Quality Index (WQI) Forecasting and Analysis Based on Neuro-Fuzzy and Statistical Methods

by Amar Lokman, Wan Zakiah Wan Ismail, Nor Azlina Ab Aziz and Anith Khairunnisa Ghazali

Appl. Sci. 2025, 15(17), 9364; https://doi.org/10.3390/app15179364 - 26 Aug 2025

Viewed by 968

Abstract

Water quality is crucial to the economy and ecology because a healthy aquatic eco-system supports human survival and biodiversity. We have developed the Neuro-Adapt Fuzzy Strategist (NAFS) to improve water quality index (WQI) forecasting accuracy. The objective of the developed model is to [...] Read more.

Water quality is crucial to the economy and ecology because a healthy aquatic eco-system supports human survival and biodiversity. We have developed the Neuro-Adapt Fuzzy Strategist (NAFS) to improve water quality index (WQI) forecasting accuracy. The objective of the developed model is to achieve a balance by improving prediction accuracy while preserving high interpretability and computational efficiency. Neural networks and fuzzy logic improve the NAFS model’s flexibility and prediction accuracy, while its optimized backward pass improves training convergence speed and parameter update effectiveness, contributing to better learning performance. The normalized and partial derivative computations are refined to improve the model. NAFS is compared with ANN, Adaptive Neuro-Fuzzy Inference System (ANFIS), and current machine learning (ML) models such as LSTM, GRU, and Transformer based on performance evaluation metrics. NAFS outperforms ANFIS and ANN, with MSE of 1.678. NAFS predicts water quality better than ANFIS and ANN, with RMSE of 1.295. NAFS captures complicated water quality parameter interdependencies better than ANN and ANFIS using principal component analysis (PCA) and Pearson correlation. The performance comparison shows that NAFS outperforms all baseline models with the lowest MAE, MSE, RMSE and MAPE, and the highest R², confirming its superior accuracy. PCA is employed to reduce data dimensionality and identify the most influential water quality parameters. It reveals that two principal components account for 72% of the total variance, highlighting key contributors to WQI and supporting feature prioritization in the NAFS model. The Breusch–Pagan test reveals heteroscedasticity in residuals, justifying the use of non-linear models over linear methods. The Shapiro–Wilk test indicates non-normality in residuals. This shows that the NAFS model can handle complex, non-linear environmental variables better than previous water quality prediction research. NAFS not only can predict water quality index values but also enhance WQI estimation. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

25 pages, 2934 KB

Open AccessArticle

Appraisal of Industrial Pollutants in Sewage and Biogas Production Using Multivariate Analysis and Unsupervised Machine Learning Clustering

by Wiktor Halecki, Anna Młyńska and Krzysztof Chmielowski

Appl. Sci. 2025, 15(11), 6222; https://doi.org/10.3390/app15116222 - 31 May 2025

Viewed by 659

Abstract

Sewage composition analysis is important for understanding environmental impact and ensuring effective treatment processes. In this study, we employed multivariate analysis techniques to delve into the intricate composition of sewage. Specifically, we utilized Principal Component Analysis (PCA) and Detrended Correspondence Analysis (DCA) to [...] Read more.

Sewage composition analysis is important for understanding environmental impact and ensuring effective treatment processes. In this study, we employed multivariate analysis techniques to delve into the intricate composition of sewage. Specifically, we utilized Principal Component Analysis (PCA) and Detrended Correspondence Analysis (DCA) to uncover patterns and relationships among different types of sewage pollutants. Statistical analysis revealed that treatment stages did not consistently reduce all pollutant concentrations. Mechanical treatment failed to lower chlorides and sulfates, but was effective for ether extract and phenols. Moreover, total mechanical–biological treatment provided a significant, 91% reduction of the ether extract and phenols, while only reducing chlorides by 13% and sulfates by 22%. The multivariate analysis revealed significant differences between raw sewage and mechanically treated sewage. Totally treated sewage stood out as the key factor influencing the pollutants studied, particularly chlorides and sulfates. This finding emphasizes the critical role of comprehensive treatment processes in effective sewage management. Among the analysed substances, chlorides showed the strongest clustering potential, with an average Silhouette coefficient of 0.738, the highest observed. Phenols, on the other hand, exhibited lower Within-Cluster Sum of Squares (WCSS), suggesting their potential as an alternative parameter for evaluation. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

16 pages, 3715 KB

Open AccessArticle

Predicting Wastewater Characteristics Using Artificial Neural Network and Machine Learning Methods for Enhanced Operation of Oxidation Ditch

by Igor Gulshin and Nikolay Makisha

Appl. Sci. 2025, 15(3), 1351; https://doi.org/10.3390/app15031351 - 28 Jan 2025

Cited by 1 | Viewed by 1671

Abstract

This study investigates the operational efficiency of the lab-scale oxidation ditch (OD) functioning in simultaneous nitrification and denitrification modes, focusing on forecasting biochemical oxygen demand (BOD₅) concentrations over a five-day horizon. This forecasting capability aims to optimize the operational regime of [...] Read more.

This study investigates the operational efficiency of the lab-scale oxidation ditch (OD) functioning in simultaneous nitrification and denitrification modes, focusing on forecasting biochemical oxygen demand (BOD₅) concentrations over a five-day horizon. This forecasting capability aims to optimize the operational regime of aeration tanks by adjusting the specific load on organic pollutants through active sludge dosage modulation. A comprehensive statistical analysis was conducted to identify trends and seasonality alongside significant correlations between the forecasted values and various time lags. A total of 20 time lags and the “month” feature were selected as significant predictors. These models employed include Multi-head Attention Gated Recurrent Unit (MAGRU), long short-term memory (LSTM), Autoregressive Integrated Moving Average–Long Short-Term Memory (ARIMA–LSTM), and Prophet and gradient boosting models: CatBoost and XGBoost. Evaluation metrics (Mean Squared Error (MSE), Mean Absolute Error (MAE), Symmetric Mean Absolute Percentage Error (SMAPE), and Coefficient of Determination (R²)) indicated similar performance across models, with ARIMA–LSTM yielding the best results. This architecture effectively captures short-term trends associated with the variability of incoming wastewater. The SMAPE score of 1.052% on test data demonstrates the model’s accuracy and highlights the potential of integrating artificial neural networks (ANN) and machine learning (ML) with mechanistic models for optimizing wastewater treatment processes. However, residual analysis revealed systematic overestimation, necessitating further exploration of significant predictors across various datasets to enhance forecasting quality. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

21 pages, 3297 KB

Open AccessArticle

Machine Learning Methods for the Prediction of Wastewater Treatment Efficiency and Anomaly Classification with Lack of Historical Data

by Igor Gulshin and Olga Kuzina

Appl. Sci. 2024, 14(22), 10689; https://doi.org/10.3390/app142210689 - 19 Nov 2024

Cited by 10 | Viewed by 3514

Abstract

This study examines an algorithm for collecting and analyzing data from wastewater treatment facilities, aimed at addressing regression tasks for predicting the quality of treated wastewater and classification tasks for preventing emergency situations, specifically filamentous bulking of activated sludge. The feasibility of using [...] Read more.

This study examines an algorithm for collecting and analyzing data from wastewater treatment facilities, aimed at addressing regression tasks for predicting the quality of treated wastewater and classification tasks for preventing emergency situations, specifically filamentous bulking of activated sludge. The feasibility of using data obtained under laboratory conditions and simulating the technological process as a training dataset is explored. A small dataset collected from actual wastewater treatment plants is considered as the test dataset. For both regression and classification tasks, the best results were achieved using gradient-boosting models from the CatBoost family, yielding metrics of SMAPE = 9.1 and ROC-AUC = 1.0. A set of the most important predictors for modeling was selected for each of the target features. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

32 pages, 4909 KB

Open AccessArticle

Non-Linear Saturated Multi-Objective Pseudo-Screening Using Support Vector Machine Learning, Pareto Front, and Belief Functions: Improving Wastewater Recycling Quality

by George Besseris

Appl. Sci. 2024, 14(21), 9971; https://doi.org/10.3390/app14219971 - 31 Oct 2024

Cited by 2 | Viewed by 1301

Abstract

Increasing wastewater treatment efficiency is a primary aim in the circular economy. Wastewater physicochemical and biochemical processes are quite complex, often requiring a combination of statistical and machine learning tools to empirically model them. Since wastewater treatment plants are large-scale operations, the limited [...] Read more.

Increasing wastewater treatment efficiency is a primary aim in the circular economy. Wastewater physicochemical and biochemical processes are quite complex, often requiring a combination of statistical and machine learning tools to empirically model them. Since wastewater treatment plants are large-scale operations, the limited opportunities for extensive experimentation may be offset by miniaturizing experimental schemes through the use of fractional factorial designs (FFDs). A recycling quality improvement study that relies on non-linear multi-objective multi-parameter FFD (NMMFFD) datasets was reanalyzed. A published NMMFFD ultrafiltration screening/optimization case study was re-examined regarding how four controlling factors affected three paper mill recycling characteristic responses using a combination of statistical and machine learning methods. Comparative machine learning screening predictions were provided by (1) quadratic support vector regression and (2) optimizable support vector regression, in contrast to quadratic linear regression. NMMFFD optimization was performed by employing Pareto fronts. Pseudo-screening was applied by decomposing the replicated NMMFFD dataset to single replicates and then testing their replicate repeatability by introducing belief functions that sought to maximize credibility and plausibility estimates. Various versions of belief functions were considered, since the novel role of the three process characteristics, as independent sources, created a high level of conflict during the information fusion phase, due to the inherent divergent belief structures. Correlations between two characteristics, but with opposite goals, may also have contributed to the source conflict. The active effects for the NMMFFD dataset were found to be the transmembrane pressure and the molecular weight cut-off. The modified adjustment was pinpointed to the molecular weight cut-off at 50 kDa, while the optimal transmembrane pressure setting persisted at 2.0 bar. This mixed-methods approach may provide additional confidence in determining improved recycling process adjustments. It would be interesting to implement this approach in polyfactorial wastewater screenings with a greater number of process characteristics. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

30 pages, 4844 KB

Open AccessArticle

by George Besseris

Appl. Sci. 2023, 13(21), 11926; https://doi.org/10.3390/app132111926 - 31 Oct 2023

Cited by 1 | Viewed by 1445

Abstract

Water scarcity is a challenging global risk. Urban wastewater treatment technologies, which utilize processes based on single-stage ultrafiltration (UF) or nanofiltration (NF), have the potential to offer lean-and-green cost-effective solutions. Robustifying the effectiveness of water treatment is a complex multidimensional characteristic problem. In [...] Read more.

Water scarcity is a challenging global risk. Urban wastewater treatment technologies, which utilize processes based on single-stage ultrafiltration (UF) or nanofiltration (NF), have the potential to offer lean-and-green cost-effective solutions. Robustifying the effectiveness of water treatment is a complex multidimensional characteristic problem. In this study, a non-linear Taguchi-type orthogonal-array (OA) sampler is enriched with an emergent stigmergic clustering procedure to conduct the screening/optimization of multiple UF/NF aquametric performance metrics. The stochastic solver employs the Databionic swarm intelligence routine to classify the resulting multi-response dataset. Next, a cluster separation measure, the Davies–Bouldin index, is used to evaluate input and output relationships. The self-organized bionic-classifier data-partition appropriateness is matched for signatures between the emergent stigmergic clustering memberships and the OA factorial vector sequences. To illustrate the proposed methodology, recently-published multi-response multifactorial L₉(3⁴) OA-planned experiments from two interesting UF-/NF-membrane processes are examined. In the study, seven UF-membrane process characteristics and six NF-membrane process characteristics are tested (1) in relationship to four controlling factors and (2) to synchronously evaluate individual factorial curvatures. The results are compared with other ordinary clustering methods and their performances are discussed. The unsupervised robust bionic prediction reveals that the permeate flux influences both the UF-/NF-membrane process performances. For the UF process and a three-cluster model, the Davies–Bouldin index was minimized at values of 1.89 and 1.27 for the centroid and medoid centrotypes, respectively. For the NF process and a two-cluster model, the Davies–Bouldin index was minimized for both centrotypes at values close to 0.4, which was fairly close to the self-validation value. The advantage of this proposed data-centric engineering scheme relies on its emergent and self-organized clustering capability, which retraces its appropriateness to the fractional factorial rigid structure and, hence, it may become useful for screening and optimizing small-data wastewater operating conditions. Full article

(This article belongs to the Special Issue AI in Wastewater Treatment)

► Show Figures

Figure 1

Journal Menu

Journal Browser

AI in Wastewater Treatment

Share This Special Issue

Special Issue Editor

Special Issue Information

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI