Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors

The present study analyses the possibility of assessing water quality using the water quality index (WQI) through the application of four different machine learning algorithms (ML): neural network models (NNM), random forest (RF), k-nearest neighbor (KNN), and linear regression (LR). Water quality w...

Full description

Saved in:
Bibliographic Details
Main Authors: Natalia Walczak, Zbigniew Walczak
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Ecological Indicators
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1470160X25004868
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717890126708736
author Natalia Walczak
Zbigniew Walczak
author_facet Natalia Walczak
Zbigniew Walczak
author_sort Natalia Walczak
collection DOAJ
description The present study analyses the possibility of assessing water quality using the water quality index (WQI) through the application of four different machine learning algorithms (ML): neural network models (NNM), random forest (RF), k-nearest neighbor (KNN), and linear regression (LR). Water quality was determined based on 5 indicators: P, COD, BOD5, N total, and total suspended solids TS. The possibility of predicting water quality (WQI index) based on the reduced number of predictors was then analyzed. It was estimated which indicators have the most significant impact on WQI values. The performance of models using different algorithms, as well as those trained on full and reduced data sets, was compared. The models demonstrate high performance in WQI prediction, achieving an R2 of 0.999 (for NNM and LR) for the entire dataset, 0.988 (KNN) for the dataset using only three types of predictors, and 0.941 for the dataset using only two predictors (RF). The construction and training of ML models for reduced sets and types of predictors will enable early water quality estimation based on only a few selected parameters. The implementation of ML algorithms will enable more effective water quality management and significantly improve the precision of predictions for critical water parameters.
format Article
id doaj-art-a98d58b7e0c74a38aaf2fab2aad37d96
institution DOAJ
issn 1470-160X
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Ecological Indicators
spelling doaj-art-a98d58b7e0c74a38aaf2fab2aad37d962025-08-20T03:12:32ZengElsevierEcological Indicators1470-160X2025-06-0117511355610.1016/j.ecolind.2025.113556Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictorsNatalia Walczak0Zbigniew Walczak1Department of Hydraulic and Sanitary Engineering, Poznan University of Life Sciences, ul. Wojska Polskiego 28, 60-637 Poznan, Poland; Corresponding author.Department of Construction and Geoengineering, Poznan University of Life Sciences, ul. Wojska Polskiego 28, 60-637 Poznan, PolandThe present study analyses the possibility of assessing water quality using the water quality index (WQI) through the application of four different machine learning algorithms (ML): neural network models (NNM), random forest (RF), k-nearest neighbor (KNN), and linear regression (LR). Water quality was determined based on 5 indicators: P, COD, BOD5, N total, and total suspended solids TS. The possibility of predicting water quality (WQI index) based on the reduced number of predictors was then analyzed. It was estimated which indicators have the most significant impact on WQI values. The performance of models using different algorithms, as well as those trained on full and reduced data sets, was compared. The models demonstrate high performance in WQI prediction, achieving an R2 of 0.999 (for NNM and LR) for the entire dataset, 0.988 (KNN) for the dataset using only three types of predictors, and 0.941 for the dataset using only two predictors (RF). The construction and training of ML models for reduced sets and types of predictors will enable early water quality estimation based on only a few selected parameters. The implementation of ML algorithms will enable more effective water quality management and significantly improve the precision of predictions for critical water parameters.http://www.sciencedirect.com/science/article/pii/S1470160X25004868Reservoir water qualityWQIMachine learning MLPCA
spellingShingle Natalia Walczak
Zbigniew Walczak
Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
Ecological Indicators
Reservoir water quality
WQI
Machine learning ML
PCA
title Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
title_full Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
title_fullStr Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
title_full_unstemmed Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
title_short Assessing the feasibility of using Machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
title_sort assessing the feasibility of using machine learning algorithms to determine reservoir water quality based on a reduced set of predictors
topic Reservoir water quality
WQI
Machine learning ML
PCA
url http://www.sciencedirect.com/science/article/pii/S1470160X25004868
work_keys_str_mv AT nataliawalczak assessingthefeasibilityofusingmachinelearningalgorithmstodeterminereservoirwaterqualitybasedonareducedsetofpredictors
AT zbigniewwalczak assessingthefeasibilityofusingmachinelearningalgorithmstodeterminereservoirwaterqualitybasedonareducedsetofpredictors