Cargando…

Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring

To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables a...

Descripción completa

Detalles Bibliográficos
Autores principales: Paepae, Thulane, Bokoro, Pitshou N., Kyamakya, Kyandoghere
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9920320/
https://www.ncbi.nlm.nih.gov/pubmed/36772100
http://dx.doi.org/10.3390/s23031061
_version_ 1784887040887750656
author Paepae, Thulane
Bokoro, Pitshou N.
Kyamakya, Kyandoghere
author_facet Paepae, Thulane
Bokoro, Pitshou N.
Kyamakya, Kyandoghere
author_sort Paepae, Thulane
collection PubMed
description To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation—including proper experimental settings or hyperparameter optimization—improved the root mean squared errors by 23–63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms’ performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average.
format Online
Article
Text
id pubmed-9920320
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99203202023-02-12 Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring Paepae, Thulane Bokoro, Pitshou N. Kyamakya, Kyandoghere Sensors (Basel) Article To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation—including proper experimental settings or hyperparameter optimization—improved the root mean squared errors by 23–63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms’ performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average. MDPI 2023-01-17 /pmc/articles/PMC9920320/ /pubmed/36772100 http://dx.doi.org/10.3390/s23031061 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Paepae, Thulane
Bokoro, Pitshou N.
Kyamakya, Kyandoghere
Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring
title Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring
title_full Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring
title_fullStr Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring
title_full_unstemmed Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring
title_short Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring
title_sort data augmentation for a virtual-sensor-based nitrogen and phosphorus monitoring
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9920320/
https://www.ncbi.nlm.nih.gov/pubmed/36772100
http://dx.doi.org/10.3390/s23031061
work_keys_str_mv AT paepaethulane dataaugmentationforavirtualsensorbasednitrogenandphosphorusmonitoring
AT bokoropitshoun dataaugmentationforavirtualsensorbasednitrogenandphosphorusmonitoring
AT kyamakyakyandoghere dataaugmentationforavirtualsensorbasednitrogenandphosphorusmonitoring