Water Quality Assessment Using the Random Forest Classification Model

© 2025 Water Environment Federation.

Bibliographische Detailangaben
Veröffentlicht in:Water environment research : a research publication of the Water Environment Federation. - 1998. - 97(2025), 10 vom: 22. Okt., Seite e70197
1. Verfasser: Bouchraki, Faiza (VerfasserIn)
Weitere Verfasser: Hamchaoui, Samir, Ayad, Louiza Lysa, Fetouh, Yanis, Mezhoud, Cherifa, Berreksi, Ali
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:Water environment research : a research publication of the Water Environment Federation
Schlagworte:Journal Article Random Forest automated classification cross‐validation drinking water quality synthetic data
LEADER 01000naa a22002652c 4500
001 NLM394445600
003 DE-627
005 20251023233337.0
007 cr uuu---uuuuu
008 251023s2025 xx |||||o 00| ||eng c
024 7 |a 10.1002/wer.70197  |2 doi 
028 5 2 |a pubmed25n1608.xml 
035 |a (DE-627)NLM394445600 
035 |a (NLM)41126581 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Bouchraki, Faiza  |e verfasserin  |4 aut 
245 1 0 |a Water Quality Assessment Using the Random Forest Classification Model 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 23.10.2025 
500 |a Date Revised 23.10.2025 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a © 2025 Water Environment Federation. 
520 |a This study presents an automated classification model based on the Random Forest model, applied to the assessment of water. A mixed dataset, combining real-world data from field analyses with synthetic data generated according to regulatory thresholds, was used to ensure balanced training of the model. Stratified cross-validation demonstrated satisfactory performance, yielding an average macro F1 score of 0.98 across all classes. Furthermore, evaluation on a test set composed exclusively of real data revealed a strong predictive capability for the majority classes, with an accuracy of 99%. In addition, a dedicated web platform was developed to automate data entry, provide instant classification, and enable dynamic visualization of results. This tool is intended to assist drinking water service managers in monitoring water quality and making rapid decisions in response to detected non-compliances. The results highlight the value of integrating advanced computational approaches into water quality management, while also underscoring the need for continued research on data balancing and validation under real-world conditions 
650 4 |a Journal Article 
650 4 |a Random Forest 
650 4 |a automated classification 
650 4 |a cross‐validation 
650 4 |a drinking water quality 
650 4 |a synthetic data 
700 1 |a Hamchaoui, Samir  |e verfasserin  |4 aut 
700 1 |a Ayad, Louiza Lysa  |e verfasserin  |4 aut 
700 1 |a Fetouh, Yanis  |e verfasserin  |4 aut 
700 1 |a Mezhoud, Cherifa  |e verfasserin  |4 aut 
700 1 |a Berreksi, Ali  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t Water environment research : a research publication of the Water Environment Federation  |d 1998  |g 97(2025), 10 vom: 22. Okt., Seite e70197  |w (DE-627)NLM098214292  |x 1554-7531  |7 nnas 
773 1 8 |g volume:97  |g year:2025  |g number:10  |g day:22  |g month:10  |g pages:e70197 
856 4 0 |u http://dx.doi.org/10.1002/wer.70197  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 97  |j 2025  |e 10  |b 22  |c 10  |h e70197