An optimized NARX-based model for predicting thermal dynamics and heatwaves in rivers.

The thermal dynamics within river ecosystems represent critical areas of study due to their profound impact on overall aquatic health. With the rising prevalence of heatwaves in rivers, a consequence of climate change, it is imperative to deepen our understanding through comprehensive research efforts. Despite this urgency, there remains a noticeable dearth in studies aimed at refining modeling techniques to precisely characterize the duration and intensity of these events. In response to this gap, the present study endeavors to augment the NARX-based model (Nonlinear Autoregressive network with Exogenous Inputs) to enhance predictive capabilities regarding thermal dynamics and river heatwaves. The optimized NARX-based model included the Bayesian Optimization (BO) algorithm, which allows fine-tuning the number of NARX hidden nodes and lagged input/target values, and the Bayesian Regularization (BR) backpropagation algorithm to improve the NARX calibration process. A long-term dataset spanning from 1991 to 2021, encompassing 18 rivers across the expansive Vistula River Basin, one of Europe's largest river systems, was employed for this study. The performance of the BO-NARX-BR model was compared with that of the widely utilized air2stream model for modeling river water temperature (RWT). The results unequivocally demonstrated the superior performance of the NARX-based model across the calibration and validation periods, and four heatwave years. In the context of river heatwaves, the study revealed an escalating frequency and intensity within the Vistula River Basin. Furthermore, the NARX-based model exhibited superior proficiency in characterizing river heatwaves compared to the air2stream model. This study, as the inaugural examination of river heatwaves in Poland and one of the few globally, furnishes crucial reference points for subsequent research endeavors on this phenomenon.

A novel optimized model based on NARX networks for predicting thermal anomalies in Polish lakes during heatwaves, with special reference to the 2018 heatwave.

In 2018, Europe experienced one of the most severe heatwaves ever recorded. This extreme event's impact on lake surface water temperature (LSWT) in Polish lakes has largely remained unknown. In this study, the impact of the 2018 European heatwave on LSWT in 24 Polish lakes was investigated based on a long-term observed dataset (1987-2020). To capture the LSWT dynamics during the heatwave period and reproduce lake heatwaves, a novel BO-NARX-BR model was developed and evaluated. This model combines the capabilities of the Nonlinear Autoregressive network with Exogenous Inputs (NARX) neural network, the Bayesian Optimization (BO) algorithm for optimizing the number of NARX hidden nodes and lagged input/target values, and the Bayesian Regularization (BR) backpropagation algorithm for the NARX training. The results showed that from April to October 2018, the mean and maximum LSWTs were 2.35 and 3.38 °C warmer than the base-period average (1987-2010) due to the impact of the extreme heatwave. The NARX-based model outperformed another widely used model called air2water in calibration and validation periods. The results also revealed that the BO-NARX-BR model produced significantly better results in capturing lake heatwaves, with computed duration and intensity of lake heatwaves close to the in-situ data. Additionally, LSWT anomaly significantly impacted the duration and intensity of heatwaves that occurred in lakes. Extreme climatic events are gaining increasing importance for the functioning of various elements of the hydrosphere. Such a situation encourages the search for more accurate methods and tools for their prediction. The model applied in the paper corresponds with these assumptions, and its good performance allows for its adaptation to lakes in other regions.

The Relationship between Mortality from Cardiovascular Diseases and Total Drinking Water Hardness: Systematic Review with Meta-Analysis.

BACKGROUND: Interest in water chemical activity, its content, and its impact on human health has greatly increased throughout the last decade. Some studies suggest that drinking water with high hardness may have preventative effects on cardiovascular diseases. This study aims to investigate the association between drinking water hardness and cardiovascular disease (CVD) mortality. METHODS: The study selection process was designed to find the association between drinking water hardness and CVDs mortality. The search included both qualitative and quantitative research and was performed in three databases: Web of Science (Clarivate Analytics, Ann Arbor, MI, USA), PubMed (National Institute of Health, Bethesda, MA, USA), and Scopus (Elsevier, RELX Group plc, London, UK). The project was registered in the International Prospective Register of Systematic Reviews (PROSPERO), registration number: CRD42020213102. RESULTS: Seventeen studies out of a total of twenty-five studies qualitatively analyzed indicated a significant relation between total water hardness and protection from CVD mortality. The quantitative analysis concluded that high drinking water hardness has a significantly lowering effect on mortality from CVDs, however, the heterogeneity was high. CONCLUSIONS: This systematic literature review shows that total water hardness could affect CVD prevention and mortality. Due to the many confounding factors in the studies, more research is needed.

A stacked machine learning model for multi-step ahead prediction of lake surface water temperature.

Lake surface water temperature is one of the most important physical and ecological indices of lakes, which has frequently been used as the indicator to evaluate the impact of climate change on lakes. Knowing the dynamics of lake surface water temperature is thus of great significance. The past decades have witnessed the development of different modeling tools to forecast lake surface water temperature, yet, simple models with fewer input variables, while maintaining high forecasting accuracy are scarce. Impact of forecast horizons on model performance has seldom been investigated. To fill the gap, in this study, a novel machine learning algorithm by stacking multilayer perceptron and random forest (MLP-RF) was employed to forecast daily lake surface water temperature using daily air temperature as the exogenous input variable, with the Bayesian Optimization procedure applied for tuning the hyperparameters. Prediction models were developed using long-term observed data from eight Polish lakes. The MLP-RF stacked model showed very good forecasting capabilities for all lakes and forecast horizons, far better than shallow multilayer perceptron neural network, a model coupling wavelet transform and multilayer perceptron neural network, non-linear regression and air2water models. A reduction in model performance was observed as the forecast horizon increased. However, the model also performs well with a forecast horizon of several days (e.g., 7 days ahead, testing stage: R2 - [0.932, 0.990], RMSE °C - [0.77, 1.83], MAE °C - [0.55, 1.38]). In addition, the MLP-RF stacked model has proven to be reliable for both intermediate temperatures and minimum and maximum peaks. The model proposed in this study will be useful to the scientific community in predicting lake surface water temperature, thus contributing to studies on such sensitive aquatic ecosystems as lakes.

Heavy metals in lake surface sediments in protected areas in Poland: concentration, pollution, ecological risk, sources and spatial distribution.

This paper presents the state and spatial distribution of surface sediment contamination of 77 lakes in Poland by Cr, Ni, Cd, Pb, Zn, and Cu. The analyzed lakes were located within a network of nature protection areas in the territory of the European Union (EU). Spatial distribution of the heavy metals (HMs), factors favoring the delivery/accumulation of HMs in surface sediments, and pollution sources were analyzed. The results indicate the contamination of lake sediments by HMs, but the potentially toxic effects of HMs are only found in single lakes. The spatial distribution of Cr indicates predominant impacts of point sources, while for Pb, Ni, and Zn, the impact of non-point sources. The analysis showed the presence of areas with very high values of particular HMs (hot spots) in the western part of Poland, while a group of 5 lakes with very low values of Ni, Pb, and Zn (cold spots) was identified in the central part of Poland. Principal component analysis showed that presence of wetlands is a factor limiting HMs inflow to lakes. Also, lower HMs concentrations were found in lake surface sediments located in catchments with a higher proportion of national parks and nature reserves. Higher HMs concentrations were found in lakes with a high proportion of Special Protection Areas designated under the EU Birds Directive. The positive matrix factorization analysis identified four sources of HMs. High values of HMs concentrations indicate their delivery from industrial, urbanized, and agricultural areas. However, these impacts overlap, which disturbs the characteristic quantitative profiles assigned to these pollution sources.

Heavy Metals in River Sediments: Contamination, Toxicity, and Source Identification-A Case Study from Poland.

This study investigated the spatial distribution, contamination, potential ecological risks and quantities of pollutant sources of six heavy metals (HMs) in sediments of 47 rivers. The catchments of the investigated rivers are situated in Poland, but some of them are located in Slovakia, the Czech Republic, and Germany. Cluster analysis was applied to analyze the spatial distribution of Cd, Cr, Cu, Ni, Pb, and Zn in river sediments. Moran I and Getis-Ord Gi* statistics were calculated to reveal the distribution pattern and hotspot values. Principal component analysis (PCA) and positive matrix factorization (PMF) were used to identify pollution sources. Furthermore, geochemical indices and sediment quality guidelines allowed us to assess sediment contamination and potential toxic effects on aquatic biota. The results showed that in 1/3rd of the rivers, the HM pattern and concentrations indicate sediment contamination. The EF, PLI, and MPI indices indicate that concentrations were at a rather low level in 2/3rd of the analyzed rivers. Only in individual rivers may the HMs have toxic effects on aquatic biota. Spatial autocorrelation analysis using the Moran I statistic revealed a random and dispersed pattern of HMs in river sediments. PCA analysis identified two sources of HMs' delivery to the aquatic environment. Cr, Cu, Ni, Pb, and Zn originate from point and non-point sources, while Cd concentrations have a dominant natural origin. The PMF identified three sources of pollution. Among them, urban pollution sources are responsible for Cu delivery, agricultural pollution for Zn, and industrial pollution for Ni and Cr. Moreover, the analysis showed no relationship between catchment land-use patterns and HM content in river sediments.

Least square support vector machine-based variational mode decomposition: a new hybrid model for daily river water temperature modeling.

Machines learning models have recently been proposed for predicting rivers water temperature (Tw) using only air temperature (Ta). The proposed models relied on a nonlinear relationship between the Tw and Ta and they have proven to be robust modelling tools. The main motivation for this study was to evaluate how the variational mode decomposition (VMD) contributed to the improvement of machines learning performances for river Tw modelling. Measured data collected at five stations located in Poland from 1987 to 2014 were acquired and used for the analysis. Six machines learning models were used and compared namely, K-nearest neighbor's regression (KNNR), least square support vector machine (LSSVM), generalized regression neural network (GRNN), cascade correlation artificial neural networks (CCNN), relevance vector machine (RVM), and locally weighted polynomials regression (LWPR). The six models were developed according to three scenarios. First, the models were calibrated using only the Ta as input and obtained results show that the models were able to predict consistently water temperature, showing a high determination coefficient (R2) and Nash-Sutcliffe efficiency (NSE) with values near or above 0.910 and 0.915, respectively, and in overall the six models worked equally without clear superiority of one above another. Second, the air temperature was combined with the periodicity (i.e., day, month and year number) as input variable and a significant improvement was achieved. Both models show their ability to accurately predict river Tw with an overall accuracy of 0.956 for R2 and 0.955 for NSE values, but the LSSVM2 have some advantages such as a small errors metrics, and high fitting capabilities and it slightly surpasses the others models. Thirdly, air temperature was decomposed into several intrinsic mode functions (IMF) using the VMD method and the performances of the models were evaluated. The VMD parameters appeared to cause much influence on the prediction accuracy, exhibiting an improvement of about 40.50% and 39.12% in terms of RMSE and MAE between the first and the third scenarios, however, some models, i.e., GRNN and KNNR have not benefited from the VMD. This research has demonstrated the high capability of the VMD algorithm as a preprocessing approach in improving the accuracies of the machine learning models for river water temperature prediction.

Ecological and Health Risk Assessments of Heavy Metals Contained in Sediments of Polish Dam Reservoirs.

This study aimed at investigating the distribution of heavy metals (HMs: Zn, Pb, Cd, Ni, Cr, and Cu) in the bottom sediments of 28 reservoirs covered area of Poland. The paper evaluates the pollution of sediments with HMs and their potential toxic effects on aquatic organisms and human health on the basis of results provided by the Chief Inspectorate of Environmental Protection in Poland. The average concentrations of HMs in the bottom sediments of the reservoirs were as follows: Cd < Ni < Cr < Cu < Pb < Zn. (0.187, 7.30, 7.74, 10.62, 12.47, and 52.67 mg∙dm−3). The pollution load index values were from 0.05 to 2.45. They indicate contamination of the bottom sediments in seven reservoirs. The contamination-factor values suggest pollution with individual HMs in 19 reservoirs, primarily Cr, Ni, Cu, and Pb. The analysis showed that only two reservoirs had the potential for toxic effects on aquatic organisms due to high concentrations of Cd and Pb. The hazard index values for all the analyzed HMs were less than one. Therefore, there was no non-carcinogenic risk for dredging workers. The reservoirs were divided into two groups in terms of composition and concentration values. Reservoirs with higher concentrations of HMs in bottom sediments are dispersed, suggesting local pollution sources. For the second group of reservoirs, HMs' concentrations may be determined by regional pollution sources. The analysis showed that Pb, Zn, and Cd concentrations are higher in older reservoirs and those with higher proportions of artificial areas in their catchments. Concentrations of Ni, Cu, and Cr are higher in reservoirs in south Poland and those with higher Schindler's ratios.

Causes of variations of trace and rare earth elements concentration in lakes bottom sediments in the Bory Tucholskie National Park, Poland.

The objective of this study was to analyse spatial variability of the trace elements (TEs) and rare earth elements (REEs) concentration in lake bottom sediments in Bory Tucholskie National Park (BTNP); Poland. The following research questions were posed: which factors have a fundamental impact on the concentration and spatial variability of elements in bottom sediments, which of the elements can be considered as indicators of natural processes and which are related to anthropogenic sources. The research material was sediments samples collected from 19 lakes. The concentrations of 24 TEs and 14 REEs were determined. The analyses were carried out using the inductively coupled plasma mass spectrometry (ICP-QQQ). Cluster analysis and principal component analysis were used to determine the spatial variability of the TEs and REEs concentrations, indicate the elements that are the indicators of natural processes and identify potential anthropogenic sources of pollution. The geochemical background value (GBV) calculations were made using 13 different statistical methods. However, the contamination of bottom sediments was evaluated by means of the index of geo-accumulation, the enrichment factor, the pollution load index, and the metal pollution index. The BTNP area is unique because of its isolation from the inflow of pollutants from anthropogenic sources and a very stable land use structure over the last 200 years. This study shows high variability of TE and REE concentrations in lake sediments. The values of geochemical indices suggest low pollution of lakes bottom sediments. It was found that TEs originated mainly from geogenic sources. However, the concentrations of Li, Ni, Sc, Se, Be, Se, Ag, Re, Tl, Cd, Sb and U may be related to the impact of point sources found mainly in the Ostrowite Lake. Almost all REEs concentrations were strongly correlated and their presence was linked to with geochemical processes. The elements allowing to identify natural processes and anthropogenic pollution sources were Cr, Co, Cu, Ag, Cd, Zn, Bi, Re, Ba, Al and Rb in TEs group and Nd, Gd, Yb, Lu, Eu, Dy and Ce in REEs group. The analysis shows high spatial variability of TE and REE concentrations in lake sediments. The values of geochemical indices point to low pollution of lakes sediments. The anthropogenic sources only for two lakes had an impact on concentrations of selected TEs and REEs. The analyses allowed to identify elements among TEs and REEs documenting geochemical processes and those indicating anthropogenic sources of pollution.

Application of multivariate statistical approach to identify trace elements sources in surface waters: a case study of Kowalskie and Stare Miasto reservoirs, Poland.

The paper reports the results of measurements of trace elements concentrations in surface water samples collected at the lowland retention reservoirs of Stare Miasto and Kowalskie (Poland). The samples were collected once a month from October 2011 to November 2012. Al, As, Cd, Co, Cr, Cu, Li, Mn, Ni, Pb, Sb, V, and Zn were determined in water samples using the inductively coupled plasma with mass detection (ICP-QQQ). To assess the chemical composition of surface water, multivariate statistical methods of data analysis were used, viz. cluster analysis (CA), principal components analysis (PCA), and discriminant analysis (DA). They made it possible to observe similarities and differences in the chemical composition of water in the points of water samples collection, to uncover hidden factors accounting for the structure of the data, and to assess the impact of natural and anthropogenic sources on the content of trace elements in the water of retention reservoirs. The conducted statistical analyses made it possible to distinguish groups of trace elements allowing for the analysis of time and spatial variation of water in the studied reservoirs.