Applied Water Science最新文献

{"title":"Flood susceptibility mapping using optimized deep learning models: a non-structural framework","authors":"Seyed Vahid Razavi-Termeh,&nbsp;Abolghasem Sadeghi-Niaraki,&nbsp;Mohammadreza Jelokhani-Niaraki,&nbsp;Soo-Mi Choi","doi":"10.1007/s13201-025-02548-5","DOIUrl":"10.1007/s13201-025-02548-5","url":null,"abstract":"<div><p>Floods are among the most destructive natural hazards, demanding accurate and efficient predictive tools for non-structural risk management. This study introduces a novel framework that integrates deep learning models—long short-term memory (LSTM) and recurrent neural network (RNN)—with two metaheuristic optimization algorithms, genetic algorithm (GA) and crow search algorithm (CSA), for flood susceptibility mapping (FSM). The innovation lies in hybridizing deep learning with metaheuristic optimization to enhance predictive accuracy. Using remote sensing and 12 key flood-conditioning factors, we produced high-resolution FSMs for Estahban, Iran. Five hundred and nine historical flood locations were used for model training and validation. The models were designed to predict continuous flood susceptibility values, enabling detailed spatial risk assessment using six developed models. Our findings reveal that optimized models significantly outperformed standalone models in predicting flood-prone areas. The RNN-GA model achieved the highest performance (area under the curve (AUC = 93.2%)), followed closely by LSTM-GA (AUC = 93.1%), RNN-CSA (AUC = 93%), and LSTM-CSA (AUC = 92.9%). Standalone models demonstrated comparatively lower accuracy, with RNN (AUC = 92.7%) and LSTM (AUC = 90%). This research contributes to developing a more effective and sustainable approach to flood management that complements existing structural measures. </p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02548-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of eco-friendly PVA/iron oxide nano-membranes synthesized via green methods for efficient removal of microbial and chemical contaminants from drinking water","authors":"Rizwana Parveen,&nbsp;Farhat Yasmeen,&nbsp;Muhammad Iqbal","doi":"10.1007/s13201-025-02527-w","DOIUrl":"10.1007/s13201-025-02527-w","url":null,"abstract":"<div><p>Ensuring access to clean and safe drinking water is a critical component of a healthy lifestyle. In this study, we report the development of a novel eco-friendly polyvinyl alcohol (PVA)/iron oxide nano-membrane synthesized using a green method for iron oxide nanoparticle production. This work is distinctive in its integration of green-synthesized iron oxide nanoparticles into a flexible, reusable PVA matrix, forming a next-generation membrane with multifunctional water purification capabilities. The nanoparticles, with an average size of 10 ± 9 d.nm, were characterized using SEM, nano zeta sizer, FTIR, and UV–Vis spectroscopy, confirming their nanoscale morphology and functional properties. The fabricated nano-membrane was evaluated for its efficacy in treating drinking water samples from diverse geographic regions of Wah Cantt, Attock, and Taxila, Pakistan, making this one of the few studies to test real-world water samples using green nano-membranes. Results indicated that nano-membrane acts as a highly effective disinfectant against microbes, turbidity decreased by 88.8%, from 40 NTU to 4.48 NTU, sodium content reduced by 28%, from 43 mg/L to 31 mg/L, total hardness decreased by 9.4%, from 519 mg/L to 470 mg/L, nitrate levels dropped by 63.5%, from 49.9 ppm to 18.2 ppm, and pH decreased slightly by 2.6%, from 7.28 to 7.09. This study introduces a sustainable, cost-effective, and scalable approach to membrane-based water purification, providing a valuable framework for the design of future nano-enabled filtration systems. The novelty lies not only in the green synthesis and practical application of the nano-membrane, but also in its demonstrated real-world performance across varied water sources, making it a promising candidate for widespread deployment in resource-limited settings.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02527-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Circular economy meets water treatment: one-pot synthesis of agricultural waste-based bi-functionalized ordered mesoporous silica for tetracycline removal via systematic adsorption studies","authors":"Wenli Gou,&nbsp;Sameer Alshehri,&nbsp;Niloofar Pirestani,&nbsp;Soroosh Soltani,&nbsp;Ahmadreza Roghanizad,&nbsp;Saeed Shirazian,&nbsp;Roozbeh Soltani","doi":"10.1007/s13201-025-02560-9","DOIUrl":"10.1007/s13201-025-02560-9","url":null,"abstract":"<div><p>This research endeavors to elucidate the process of developing and characterizing a novel plant-derived biogenic-based bi-functionalized MCM-41 (Mobil Composition of Matter No. 41), abbreviated as Bif-MCM-41, prepared through an environmentally friendly one-pot method. The Bif-MCM-41 material was functionalized with two different silane coupling agents with different functional groups to enhance its adsorption properties. XRD and TEM confirmed the mesoporous structure constructed from well-ordered hexagonal arrays of parallel microchannels, while FESEM revealed uniform Bacillus-like (rod-shaped) morphology. The material exhibited a high surface area (988 m² g⁻¹), a pore volume of 0.72 cm³ g^-¹ and a bimodal pore distribution (1.3 nm and 2.5 nm) based on 2D-NLDFT method, confirming a well-developed micro-mesoporous structure. Adsorption studies for tetracycline were conducted under varying conditions, and both linear and nonlinear isotherm and kinetic models were applied to assess adsorption behavior. The maximum Langmuir adsorption capacity reached 765.4 mg g⁻¹ at 293 K. Nonlinear fitting provided a more accurate representation of adsorption behavior, and kinetic studies indicated a pseudo-first-order mechanism, suggesting surface reaction dominance. Thermodynamic analysis confirmed the process as spontaneous and exothermic, driven by <i>π</i>–<i>π</i> stacking and hydrogen bonding. The combination of biogenic synthesis, dual functionalization, and outstanding adsorption performance represents a unique contribution to the development of sustainable adsorbents. This study offers both mechanistic insight and practical relevance, bridging green chemistry with high-efficiency pollutant removal.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02560-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A surrogate approach to model groundwater level in time and space based on tree regressors","authors":"Pedro Martínez-Santos,&nbsp;Víctor Gómez-Escalonilla,&nbsp;Silvia Díaz-Alcaide,&nbsp;Manuel Rodríguez del Rosario,&nbsp;Héctor Aguilera","doi":"10.1007/s13201-025-02572-5","DOIUrl":"10.1007/s13201-025-02572-5","url":null,"abstract":"<div><p>Groundwater is a crucial resource for humans and the environment. Protection of groundwater supplies requires tools to explore and understand the behavior of aquifers. This research presents a machine learning approach to predict groundwater levels in time and space based on tree regressors. Covariates comprise dynamic and static items, including spatial coordinates, aquifer properties, timestamps, recharge and pumping data. Certain dynamic variables also include a subset of lag periods to depict seasonality. Algorithms are tested on a set of climatic scenarios in order to observe their ability to predict stable, declining and recovering groundwater trends. Random forest, ExtraTrees and gradient boosting regression behave rather similarly, with generalization scores in excess of 0.95 for wet, dry and average climatic conditions. Predictive accuracy exceeds 0.85 when comparing their long-term forecasts with unseen predictions computed by means of a calibrated numerical model. Feature importance analysis, coupled with the outcomes of partial dependence plots, suggests that tree regressors are able to capture the relevance of dynamic and static variables, thus making the results extrapolable not only in time, but also in space. Outcomes open up an alternative to model groundwater-related variables without necessarily relying on flow and transport equations. This approach can be readily extrapolated to other settings and might offer a rapid means to obtain useful predictions, provided that enough field data is available.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02572-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Suitability of a classic wastewater treatment plant to purify the collective effluent of Oum El-Bouaghi City, North East Algeria","authors":"Dounia Dib,&nbsp;Miyada Ouanes,&nbsp;Mamoun Fellah,&nbsp;Bachir Khezzani,&nbsp;Dalila Addad,&nbsp;Kenza Kadi,&nbsp;Mounia Ouldjaoui,&nbsp;Abdelkader Khiari,&nbsp;Alejandro Perez-Larios,&nbsp;Benjamin Castañeda-Pimienta,&nbsp;Mariano Aceves-Aldrete,&nbsp;Souren Gregorian,&nbsp;Gamal A. El-Hiti","doi":"10.1007/s13201-025-02497-z","DOIUrl":"10.1007/s13201-025-02497-z","url":null,"abstract":"<div><p>Due to water shortages in semi-arid regions of Algeria, reusing treated waste water for irrigation is necessary. This study aims to demonstrate how the biological treatment methods used in Algerian plants can be applied to the domestic sewage of Oum El-Bouaghi City, located in northeastern Algeria. Twenty-one parameters were monitored to evaluate the effectiveness of the treatment techniques. Over 2 weeks, the samples were continuously collected via an automated sampler (Hach Lange type). We have determined the most critical parameters in wastewater: pH, EC, T, O₂, ORP, BOD₅, COD, MES, MVS, N–NTK, NO₃⁻, NO₂⁻, NH₄⁺, P.T., oils and fats, and metallic elements: Zn, Pb, Cd, Cr, Cu, and Ni. The findings indicate that biological treatment methods effectively purify the effluent of Oum El-Bouaghi City. The BOD₅/COD ranges between 0.47 and 0.55, demonstrating that biological processes can efficiently break down the pollutant load. The inverse ratio (COD/BOD₅) inferior to 3 (1.77 to 2.25) indicates their domestic origin. The results of the PCA projection on the F1*F2 plan show a robust positive correlation between BOD₅ and several organic pollution indicators, as follows: <i>r</i> = 0.94 with COD, MES, and NH₄⁺, <i>r</i> = 0.96 for both NO₃⁻ and NO₂⁻. <i>r</i> = 0.89 for total phosphorus. Similar strong correlations were observed with COD, reflecting the ease of organic compound oxidation via chemical processes. Over-studied heavy metals, chromium stands out as the sole element demonstrating substantial connections with other elements with correlation coefficients of 0.63 to 0.82, showing its reactivity and unstable behavior. These findings emphasize the efficiency of the biological treatment procedures in purifying the effluent of Oum El-Bouaghi city regarding their domestic character.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02497-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigation of the effect of dredging activity on surface intake seawater use for RO desalination plants: Shahid Beheshti, Chabahar Bay, Iran","authors":"Maryam Sazmand,&nbsp;Mir Mahdi Zahedi","doi":"10.1007/s13201-025-02562-7","DOIUrl":"10.1007/s13201-025-02562-7","url":null,"abstract":"<div><p>Surface seawater intakes are popular method in most of seawater reverse osmosis (SWRO) desalination plants which pose fouling-sensitive membranes. Seawater characteristics, especially those near ports, and residential and commercial areas, can be strongly affected by climatic conditions, topology, and human activities such as dredging, fishing, sea traffic, and sewage discharge and consequently are related to the designed pretreatment method and its cost. Therefore, choosing the right location for a SWRO desalination plants is essential to use feed water of appropriate quality and with minimum risk of change. In this research, influence of the dredging process in the Shahid Beheshti port (phase 2) on the characteristics of surface seawater has been investigated as intake water of SWRO desalination plant. Parameters such as temperature, TDS, silt density index (SDI), pH, and chlorophyll a were studied. The results indicate significant changes in some water characteristics in locations very close to the dredging activity, and this is not good news mainly for membrane processes. High amount of SDI and chlorophyll a (as fouling and biofouling indicator) will imply the high fouling possibility near the dredging activity places. </p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02562-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pathway of total petroleum hydrocarbon in a lotic ecosystem: water and sediment of Tigris River, Iraq","authors":"Fikrat M. Hassan,&nbsp;Abdul Hameed M. Jawad Al-Obaidy,&nbsp;Anwar Ridha Noor,&nbsp;Nadhir Alansari","doi":"10.1007/s13201-025-02505-2","DOIUrl":"10.1007/s13201-025-02505-2","url":null,"abstract":"<div><p>The monitoring of lotic ecosystems is an important issue. This study investigated the total petroleum hydrocarbons (THP) in the Tigris River within Baghdad City, Iraq, which is considered the ultimate water supply source of the city. The study included measurement of THP concentrations, distribution, and origins of total petroleum hydrocarbons (TPHs) in various matrices (water, sediment, and macrophyte) in Tigris River within Baghdad City, in addition to some environmental factors during two seasons (dry and wet) for October 2020 to April 2021. The sampling was collected from three sites along the river. Thirteen compounds were identified in the current investigation from total petroleum hydrocarbons (TPHs), including hexatriacontane, tetracontane, tetratetracontane, undecane, dodecane, hexane, nonane, tetradecane, hexadecane, eicosane, dortiacontane, decane, and octadecane. TPHs concentrations were arranged in the following order macrophyte &gt; sediment &gt; water, and the oil refinery (site 2) was the most hydrocarbon contamination due to its anthropogenic activity. The highest results varied: 54.8 mg/L for hexatriacontane in water, 258.8 mg/g for hexadecane and nonane in sediment, while macrophyte was 393 mg/g for hexadecane. The origin of TPHs in different matrices in the current investigation was pyrogenic (Anthropogenic) according to the portion of low molecular weight/high molecular weight (LMW/HMW). The oil refinery site is considered a risk site by the increasing concentration of TPHs. The THPs pollution is beside other environmental problems in Iraq need to find a quick solution to save the river.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02505-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Green walnut husk and pomegranate peel for nickel removals from industrial wastewater by absorption process: batch and column experiments","authors":"Fereshteh Nourmohammadi Dehbalaei,&nbsp;Zahra Akbari,&nbsp;Mohammad Sajjad Abdi,&nbsp;Seyed Taghi Omid Naeeni","doi":"10.1007/s13201-025-02570-7","DOIUrl":"10.1007/s13201-025-02570-7","url":null,"abstract":"<div><p>Biosorption studies were conducted using batch and column experiments to analyze the adsorption of nickel ions onto green walnut husk and pomegranate peel, two low-cost, eco-friendly biosorbents. While previous research has explored the biosorption of various heavy metals, this study uniquely compares the efficiency of these agricultural waste materials for nickel removal under different operational conditions, including particle size, pH, biosorbent dose, and initial nickel concentration. The results showed that the optimum pH for both adsorbents ranged from 4 to 6, and the adsorption process reached equilibrium within approximately 1 h. Based on the Langmuir isotherm, the maximum adsorption capacities for green walnut husk and pomegranate peels were 99 mg/g and 11.4 mg/g, respectively, indicating that both adsorbents effectively removed nickel from wastewater. In the study, the adsorption data were fitted to three linear adsorption isotherm models: Langmuir, Freundlich, and Temkin. Among linear adsorption isotherms, the observed data for both adsorbents were better fitted by the Freundlich isotherm (<i>R</i>²_{(pomegranate peel)} = 0.97 and <i>R</i>²_{(green walnut husk)} = 0.99). Among the five nonlinear adsorption kinetic models tested, the pseudo-second-order model with <i>R</i>² = 1 was the most suitable for modeling. The separation factor for both adsorbents was below one across all concentrations confirming favorable adsorption. The negative value of the Gibbs free energy change indicates that the adsorption process was spontaneous. In addition, the Gibbs free energy values absorbed for both biosorbents revealed that the absorption process in green walnut husks was physisorption, whereas for pomegranate peels, both physisorption and chemisorption occurred spontaneously. Based on column studies, the dose–response curve best matches the breakthrough curve data.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02570-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145144162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surface functionalization of cellulose nanocrystals derived from waste newspaper for highly efficient Mn (VII) sorption","authors":"F. M. Mohamed,&nbsp;Mohamed R. El-Aassar,&nbsp;B. Y. Eweida,&nbsp;A. M. Abdullah,&nbsp;H. A. Hamad,&nbsp;M. F. Alrakshy,&nbsp;Mohamed. Abdel Rafea,&nbsp;R. E. Khalifa","doi":"10.1007/s13201-025-02565-4","DOIUrl":"10.1007/s13201-025-02565-4","url":null,"abstract":"<div><p>This study aims to produce functionalized cellulose nanocrystals (FCNCs) by preparing and functionalizing cellulose nanocrystals (CNCs) from eco-friendly newspapers utilizing a straightforward two-step reaction with an anionic polymer (poly hydrex 6161). FCNCs' structure is described using FTIR, XRD, and SEM. A pseudo-second-order model was used to describe the sorption kinetics of Mn(VII) onto FCNCs, and the results of the linear and nonlinear regression analyses agreed well (R2 &gt; 0.999). Additionally, a number of intervening diffusion types, including intra-particle diffusion, were linked to the regulating phase in the Mn(VII) sorption process. The linear versions of the Freundlich, DR, and Langmuir isotherms were also used to examine the Mn(VII) equilibrium data; the results showed that the Langmuir fits the data better, with an R2 value of 0.9981. This validates the uniform properties of Mn(VII) sorption on the surface of FCNCs with exceptional removal capacities (qmax = 384.615) in both linear and nonlinear modes, in an orderly mode. The spontaneous and endothermic nature of the Mn(VII) sorption process at 288–328 K was confirmed by the thermodynamic parameters ΔH°, ΔS°, and ΔG°. On the other hand, the E value of 1461 kJ mol⁻¹according to D-R isotherm calculation, which was greater than 8 kJ mol⁻¹, indicated chemisorption. To ascertain the adsorption mechanism on the FCNCs, techniques such as ion exchange, pore filling, complexation interaction, and electrostatic interaction can be employed. The hybrid FCNCs were able to easily execute at least six adsorption–desorption recycles. The hybrid composite's unique characteristics make it a very promising enhanced adsorbent with great promise for heavy metal removal in wastewater treatment on an industrial scale.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02565-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145143065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A three stage attention enabled stacked deep CNN-BiLSTM (ASDCBNet) model for end-to-end monitoring of wastewater treatment plant","authors":"S. Ullas,&nbsp;B. Uma Maheswari,&nbsp;Seshaiah Ponnekant,&nbsp;T. M. Mohan Kumar","doi":"10.1007/s13201-025-02575-2","DOIUrl":"10.1007/s13201-025-02575-2","url":null,"abstract":"<div><p>Rapid urbanization and industrialization have drastically increased wastewater generation, leading to a decline in water quality and threatening both ecosystems and public health. With over 40% of the global population lacking access to clean water, the role of wastewater treatment plants (WWTPs) has become crucial in removing contaminants and safeguarding the environment. However, traditional WWTPs face challenges including high operational costs, manual monitoring dependencies, and inefficiencies in real-time quality control. To address these challenges, this work proposes an automated WWTP monitoring system ASDCBNet powered by deep learning. The system comprises three integrated components: a CNN-BiLSTM-based inflow forecasting model, an attention-enabled sensor health monitoring module, and a CNN-based outflow water quality classification model. The proposed model achieved high forecasting accuracy, with RMSE and MAE values of 95.23 m³/day (1.36%) and 80.23 m³/day (1.15%), respectively, on inflow volumes ranging from 7000 to 10,000 m³/day. Furthermore, the model achieved an exceptionally low mean absolute percentage error of just 0.05%, highlighting its ability to effectively handle variability in the data, ensuring high accuracy in inflow volume forecasting. The model outperforms sensor health monitoring and prediction with an average accuracy of 96.6%, and finally, outflow analyses have reported the prediction accuracy as 98.7%. The model has demonstrated excellent overall performance in statistical analysis, with a Bias of 0.02, a high correlation coefficient of 0.98, a Nash–Sutcliffe Efficiency of 0.85, and a low Thiel’s U-statistic of 0.12. The model's practical application in real-world WWTPs can enhance operational efficiency, reduce manual labor, and improve water quality management by providing accurate, real-time insights.</p></div>","PeriodicalId":8374,"journal":{"name":"Applied Water Science","volume":"15 8","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s13201-025-02575-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145143062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}