A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities

Abstract Reduced bacteria concentrations in wastewater is a key indicator of the efficacy of water resource recovery facilities (WRRFs). However, monitoring the presence of bacterial concentrations in real time at each stage of the WRRF is challenging as it requires taking and processing water sampl...

Full description

Saved in:
Bibliographic Details
Main Authors: Fahad Aljehani, Ibrahima N’Doye, Pei-Ying Hong, Mohammad Khalil Monjed, Taous-Meriem Laleg-Kirati
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-82598-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846101253817368576
author Fahad Aljehani
Ibrahima N’Doye
Pei-Ying Hong
Mohammad Khalil Monjed
Taous-Meriem Laleg-Kirati
author_facet Fahad Aljehani
Ibrahima N’Doye
Pei-Ying Hong
Mohammad Khalil Monjed
Taous-Meriem Laleg-Kirati
author_sort Fahad Aljehani
collection DOAJ
description Abstract Reduced bacteria concentrations in wastewater is a key indicator of the efficacy of water resource recovery facilities (WRRFs). However, monitoring the presence of bacterial concentrations in real time at each stage of the WRRF is challenging as it requires taking and processing water samples offline. Although few studies have been proposed to predict bacterial concentrations using data-driven models, generalizing these models to unseen data from different WRRFs remains challenging. This paper proposes a calibration approach based on neural networks to adapt the optimal models across various WRRFs in Saudi Arabia for bacterial estimation at the influent and effluent stages. The calibration relies on the out-of-distribution (OOD) framework of the physiochemical water parameters (e.g., pH, COD, TDS, turbidity, conductivity) with a design threshold chosen based on the data distribution of the received unseen samples. We propose a calibration framework that continues updating the trained neural network model for accurate bacterial concentration estimation upon receiving new samples. We tested the effectiveness of the proposed calibration scheme on four WRRF datasets in Saudi Arabia, comparing the results with before and after calibration without the OOD. Before calibration model was based on a traditional and optimal neural network approach, typically considered the conventional method for building neural networks. After calibration without OOD, the model continued retraining without explicitly checking for OOD condition. The results showed that the proposed calibration framework of the selected baseline WRRF with the OOD scheme improved $$99.68\%$$ and $$56.00\%$$ of the worst-case influent bacteria concentration before calibration and after calibration without OOD, respectively. Similarly, the worst-case effluent bacteria concentration estimation was enhanced by $$99.37\%$$ before calibration and $$33.98\%$$ after calibration without the OOD. Our findings highlight the importance of integrating the calibration framework with neural network approaches to achieve model generalization.
format Article
id doaj-art-36e5a89bb9054f9e8680c43c1cd0f701
institution Kabale University
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-36e5a89bb9054f9e8680c43c1cd0f7012024-12-29T12:21:28ZengNature PortfolioScientific Reports2045-23222024-12-0114111410.1038/s41598-024-82598-yA calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilitiesFahad Aljehani0Ibrahima N’Doye1Pei-Ying Hong2Mohammad Khalil Monjed3Taous-Meriem Laleg-Kirati4Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), King Abdullah University of Science and Technology (KAUST)Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), King Abdullah University of Science and Technology (KAUST)Environmental Science and Engineering Program, Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology (KAUST)Faculty of Science, Umm Al-Qura UniversityNational Institute for Research in Digital Science and Technology (INRIA)Abstract Reduced bacteria concentrations in wastewater is a key indicator of the efficacy of water resource recovery facilities (WRRFs). However, monitoring the presence of bacterial concentrations in real time at each stage of the WRRF is challenging as it requires taking and processing water samples offline. Although few studies have been proposed to predict bacterial concentrations using data-driven models, generalizing these models to unseen data from different WRRFs remains challenging. This paper proposes a calibration approach based on neural networks to adapt the optimal models across various WRRFs in Saudi Arabia for bacterial estimation at the influent and effluent stages. The calibration relies on the out-of-distribution (OOD) framework of the physiochemical water parameters (e.g., pH, COD, TDS, turbidity, conductivity) with a design threshold chosen based on the data distribution of the received unseen samples. We propose a calibration framework that continues updating the trained neural network model for accurate bacterial concentration estimation upon receiving new samples. We tested the effectiveness of the proposed calibration scheme on four WRRF datasets in Saudi Arabia, comparing the results with before and after calibration without the OOD. Before calibration model was based on a traditional and optimal neural network approach, typically considered the conventional method for building neural networks. After calibration without OOD, the model continued retraining without explicitly checking for OOD condition. The results showed that the proposed calibration framework of the selected baseline WRRF with the OOD scheme improved $$99.68\%$$ and $$56.00\%$$ of the worst-case influent bacteria concentration before calibration and after calibration without OOD, respectively. Similarly, the worst-case effluent bacteria concentration estimation was enhanced by $$99.37\%$$ before calibration and $$33.98\%$$ after calibration without the OOD. Our findings highlight the importance of integrating the calibration framework with neural network approaches to achieve model generalization.https://doi.org/10.1038/s41598-024-82598-yWater resource recovery facilitiesBacteria concentration sensingWasserstein generative adversarial network (WGAN)Out-of-distribution (OOD) generalizationCalibration of neural networks
spellingShingle Fahad Aljehani
Ibrahima N’Doye
Pei-Ying Hong
Mohammad Khalil Monjed
Taous-Meriem Laleg-Kirati
A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
Scientific Reports
Water resource recovery facilities
Bacteria concentration sensing
Wasserstein generative adversarial network (WGAN)
Out-of-distribution (OOD) generalization
Calibration of neural networks
title A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
title_full A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
title_fullStr A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
title_full_unstemmed A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
title_short A calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
title_sort calibration framework toward model generalization for bacteria concentration estimation in water resource recovery facilities
topic Water resource recovery facilities
Bacteria concentration sensing
Wasserstein generative adversarial network (WGAN)
Out-of-distribution (OOD) generalization
Calibration of neural networks
url https://doi.org/10.1038/s41598-024-82598-y
work_keys_str_mv AT fahadaljehani acalibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT ibrahimandoye acalibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT peiyinghong acalibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT mohammadkhalilmonjed acalibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT taousmeriemlalegkirati acalibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT fahadaljehani calibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT ibrahimandoye calibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT peiyinghong calibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT mohammadkhalilmonjed calibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities
AT taousmeriemlalegkirati calibrationframeworktowardmodelgeneralizationforbacteriaconcentrationestimationinwaterresourcerecoveryfacilities