Machine learning-based anomaly detection in surface water quality data using ensemble models with residual analysis

Mashkina, IV та Nosenko, TI (2026) Machine learning-based anomaly detection in surface water quality data using ensemble models with residual analysis Scientific Reports, 8 (16). ISSN 2045-2322

Текст I_MASHKINA_T_NOSENKO_Machine learning-based anomaly detection in surface water quality data using ensemble models with.pdf - Опублікована версія Download (1MB)

Анотація

This study addresses the challenge of detecting anomalies in water-quality monitoring data, where traditional approaches often lack sufficient temporal and spatial resolution. A data-driven framework integrating ensemble machine-learning models (Random Forest and XGBoost) with residual-based anomaly detection was developed and evaluated using open surface-water monitoring data from Ukraine for 2022. The models were trained to predict key hydrochemical indicators, including nitrogen concentration and dissolved oxygen, using chemical, spatial, and seasonal features. Model robustness was assessed through 5-fold cross-validation, which demonstrated stable predictive performance for both indicators. Anomalies were identified as statistically significant deviations between observed and predicted values. Recurrent anomaly hotspots were subsequently analyzed and spatially mapped, with hotspot locations independently confirmed by both Random Forest and XGBoost models. The results demonstrate that the proposed framework can effectively identify statistically unusual observations and reveal patially persistent anomaly hotspots across multiple river basins. However, the detected anomalies should be interpreted as statistical deviations rather than confirmed pollution events, as independent pollution-source information was not available. The study highlights the potential of combining ensemble learning, residual analysis, and spatial hotspot identification to support datadriven environmental assessment and monitoring activities.

Тип елементу :	Стаття
Ключові слова:	Artificial intelligence (AI); Machine learning (ML); Anomaly detection; Water pollution monitoring; Ensemble models; Random forest; XGBoost
Типологія:	Статті у базах даних > Scopus > У виданнях Q1 Scopus
Підрозділи:	Факультет інформаційних технологій та математики > Кафедра комп'ютерних наук
Користувач, що депонує:	Ірина Машкіна
Дата внесення:	24 Жов 2026 19:16
Останні зміни:	24 Жов 2026 19:16
URI:	https://elibrary.kubg.edu.ua/id/eprint/59776

Actions (login required)

Перегляд елементу