Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Evidence from increasing mineralization, micropollutant concentrations, waterborne epidemics, an algal boom, and dissolved organic matter has provided substantial evidence that climate change impacts water quality. While the impact of the extreme hydrological event (EHE) on water quality (WQ) has aroused considerable research interest, research uncertainty has been premised on WQ data scarcity, a short time frame, data non-linearity, data structure, and environmental biases on WQ. This study conceptualized a categorical and periodic correlation using confusion matrices and wavelet coherence for varying standard hydrological drought index (SHDI; 1971–2010) and daily WQ series (1977–2011) of four spatially distinct basins. By condensing the WQ variables using chemometric analyses, confusion matrices were assessed by cascading the SHDI series into 2-, 3-, and 5-phase scenarios. 2-phase revealed an overall accuracy (0.43–0.73), sensitivity analysis (0.52–1.00), and Kappa coefficient (− 0.13 to 0.14), which declines substantially with the phase increase, suggesting the disruptive impact of EHE on WQ. Wavelet coherence depicted the substantial ($${R}_{n}^{2}\left(u,s\right)\ge 0.5$$ R n 2 u , s ≥ 0.5 ) mid- and long-term (8–32 days; 6–128 days) co-movement of streamflow over WQ, confirming the varying sensitivity of WQ variables. Land use/land cover mapping and the Gibbs diagram corroborate the eventful WQ evolution by EHE and their spatial variability concerning landscape transformation. Overall, the study deduced that hydrologic extreme triggers substantial WQ disruption with dissimilar WQ sensitivity. Consequently, suitable chemometric indicators of EHE impacts such as WQ index, nitrate-nitrogen, and Larson index at designated landscapes were identified for extreme chemodynamics impact assessment. This study proffers a recommendation for monitoring and managing the impact of climate change, floods, and drought on water quality.
Evidence from increasing mineralization, micropollutant concentrations, waterborne epidemics, an algal boom, and dissolved organic matter has provided substantial evidence that climate change impacts water quality. While the impact of the extreme hydrological event (EHE) on water quality (WQ) has aroused considerable research interest, research uncertainty has been premised on WQ data scarcity, a short time frame, data non-linearity, data structure, and environmental biases on WQ. This study conceptualized a categorical and periodic correlation using confusion matrices and wavelet coherence for varying standard hydrological drought index (SHDI; 1971–2010) and daily WQ series (1977–2011) of four spatially distinct basins. By condensing the WQ variables using chemometric analyses, confusion matrices were assessed by cascading the SHDI series into 2-, 3-, and 5-phase scenarios. 2-phase revealed an overall accuracy (0.43–0.73), sensitivity analysis (0.52–1.00), and Kappa coefficient (− 0.13 to 0.14), which declines substantially with the phase increase, suggesting the disruptive impact of EHE on WQ. Wavelet coherence depicted the substantial ($${R}_{n}^{2}\left(u,s\right)\ge 0.5$$ R n 2 u , s ≥ 0.5 ) mid- and long-term (8–32 days; 6–128 days) co-movement of streamflow over WQ, confirming the varying sensitivity of WQ variables. Land use/land cover mapping and the Gibbs diagram corroborate the eventful WQ evolution by EHE and their spatial variability concerning landscape transformation. Overall, the study deduced that hydrologic extreme triggers substantial WQ disruption with dissimilar WQ sensitivity. Consequently, suitable chemometric indicators of EHE impacts such as WQ index, nitrate-nitrogen, and Larson index at designated landscapes were identified for extreme chemodynamics impact assessment. This study proffers a recommendation for monitoring and managing the impact of climate change, floods, and drought on water quality.
Accurately identifying groundwater contamination sites is vital for groundwater protection and restoration. This study aims to use a machine learning (ML) approach to identify groundwater contamination sites with total petroleum hydrocarbons (TPH) as target contaminants in a case study of gas stations in China. Firstly, six classical ML algorithms, including logistic regression, decision tree, gradient boosting decision tree (GBDT), random forest, multi-layer perceptron, and support vector machine, were applied to develop the identification models of TPH-contaminated groundwater with 40 features and the performances were compared. The comparison results showed that the GBDT model achieves the best prediction performance, with F1 score of 1 and AUC value of 1. Next, Bayesian optimization optimized GBDT (BO-GBDT) was conducted to further decrease the training time from 19,125 s to 513 s while maintaining the same prediction performance (F1 score = 1, AUC = 1). Finally, Shapley additive explanations (SHAP) analysis was performed on the BO-GBDT model. The SHAP results displayed that the critical feature variables in the BO-GBDT model include wind, population, evaporation, total potassium in the soil, precipitation, and leakage accident. This study demonstrated that BO-GBDT is one satisfactory model to identify groundwater TPH-contamination at gas stations. The method proposed in this study has the potential to be applied to other types of groundwater contamination sites.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.