Effectiveness of groundwater heavy metal pollution indices studies by deep-learning

Singha, Sudhakar; Pasupuleti, Srinivas; Singha, Soumya S.; Kumar, Suresh

doi:10.1016/j.jconhyd.2020.103718

Cited by 58 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various techniques have been developed for decoding the complex record of natural and anthropogenic impacts of PTEs and other trace elements in groundwater. The most important methods that have been used and will continue to dominate in these studies are multivariate statistics (i.e., principal component analysis, hierarchical cluster analysis, non-metric multidimensional scaling) (Papazotos et al 2019;Vasileiou et al 2019) association cluster maps) (Vasileiou et al 2019;Quino-Lima et al 2020), and machine learning algorithms (Singha et al 2020;Yaseen 2021), which allow the advanced analysis of large databases that include many parameters, as it is happening in hydrogeochemical studies. In addition, an alternative approach, that has been increasingly used in recent years, is the combined use of suitable stable isotopic signatures (e.g., δ 53 Cr, 87 Sr/ 86 Sr, 206 Pb/ 204 Pb, 207 Pb/ 204 Pb, 208 Pb/ 204 Pb δ 11 B, δ 15 N, and δ 18 O) that can help to distinguish the origin of PTEs in water resources (Puig et al 2017;Kruk et al 2020;Perraki et al 2021).…”

Section: Resultsmentioning

confidence: 99%

“…In recent years, emphasis has been placed on the investigation and co-occurrence of pollutants in an aquifer. Typical examples of new issues that need further investigation are the co-existence of As with fluoride (F − ) (Kumar et al 2020;Alarcón-Herrera et al 2020) and Cr(VI) with nitrate (NO 3 − ) (Papazotos et al 2019;Vasileiou et al 2019), which are increasingly mentioned in the updated literature. Taking into account the last relationship and especially the impact of NO 3 − in groundwater, the relatively neglected role of agricultural activities in the elevated groundwater concentrations of Cr(VI) and other PTEs highlights the role of nitrogen (N)-or/and phosphorous (P)-bearing fertilizers (Kubier et al 2019;Papazotos et al 2019;Vasileiou et al 2019;Papazotos et al 2020;Perraki et al 2021), providing to the researchers a "hot" topic with many open questions to study in the coming years about the multifold role of fertilizers in the occurrence and mobilization of PTEs in groundwater.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Potentially toxic elements in groundwater: a hotspot research topic in environmental science and pollution research

Papazotos

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

A scientometric analysis based on the Scopus database was conducted to provide insight into research activities on the occurrence of potentially toxic elements (PTEs) (As, Cd, Co, Cr, Cu, Hg, Ni, Pb, Sb, and Zn) in groundwater during 1970-2019. The selection of these PTEs was based on their significance concerning their reference frequency in environmental science and pollution research (ESPR) studies and their toxicity to living organisms. The analysis utilizes data about the quantity, type, journal, geographical, institutional, and funding patterns of publications. The results indicate that the publications' annual output has increased over the years, and especially after 2000, it presents a remarkable growth rate. The most studied PTEs were As and Pb; nevertheless, the research on the rest of PTEs cannot be neglected as it shows continuously increasing trends over time. The evolution of instrumentation and the dissemination of contamination case studies that affect a large part of the world population contributed significantly to the scientific community and relative stakeholders' interest. According to the analysis, the USA and China are the two principal countries with the most considerable contribution, producing the most research regarding the number of publications, research institutions, and funding sponsors. China owns the most influential research institution (i.e., Chinese Academy of Sciences) and largest funding sponsor (i.e., National Natural Science Foundation of China; ≈5% of global funding) on a worldwide scale due to its investment in research and development (R&D) and is expected to become the greatest force in the future.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Potentially toxic elements in groundwater: a hotspot research topic in environmental science and pollution research

Papazotos

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…To prevent the inverse effect of input variables with differing scales, the data from the input variables and heavy metal concentrations were normalized to the same scale. Data normalization was used to ensure rapid convergence and to acquire the lowest mean square error (MSE) values possible [45]. The normalized values of each input and output were achieved using Equation (1).…”

Section: Data Pre-processingmentioning

confidence: 99%

Neuro-Particle Swarm Optimization Based In-Situ Prediction Model for Heavy Metals Concentration in Groundwater and Surface Water

Jesus

Senoro

Cruz

et al. 2022

Toxics

View full text Add to dashboard Cite

Limited monitoring activities to assess data on heavy metal (HM) concentration contribute to worldwide concern for the environmental quality and the degree of toxicants in areas where there are elevated metals concentrations. Hence, this study used in-situ physicochemical parameters to the limited data on HM concentration in SW and GW. The site of the study was Marinduque Island Province in the Philippines, which experienced two mining disasters. Prediction model results showed that the SW models during the dry and wet seasons recorded a mean squared error (MSE) ranging from 6 × 10−7 to 0.070276. The GW models recorded a range from 5 × 10−8 to 0.045373, all of which were approaching the ideal MSE value of 0. Kling–Gupta efficiency values of developed models were all greater than 0.95. The developed neural network-particle swarm optimization (NN-PSO) models for SW and GW were compared to linear and support vector machine (SVM) models and previously published deterministic and artificial intelligence (AI) models. The findings indicated that the developed NN-PSO models are superior to the developed linear and SVM models, up to 1.60 and 1.40 times greater than the best model observed created by linear and SVM models for SW and GW, respectively. The developed models were also on par with previously published deterministic and AI-based models considering their prediction capability. Sensitivity analysis using Olden’s connection weights approach showed that pH influenced the concentration of HM significantly. Established on the research findings, it can be stated that the NN-PSO is an effective and practical approach in the prediction of HM concentration in water resources that contributes a solution to the limited HM concentration monitored data.

show abstract

“…The smaller the RMSE, the better the performance of the algorithm. R 2 shows the relationship between the predicted value and the actual value [31]. Performance metrics are as follows [32].…”

Section: Performance Analysismentioning

confidence: 99%

Hourly electricity consumption estimation methodology based on the metaheuristic algorithms

Ağır

2022

Preprint

View full text Add to dashboard Cite

Estimation of electricity consumption is very difficult as it depends on meteorological factors such as temperature, pressure and wind. Accurate estimation of electricity consumption is very important in terms of cost, time, energy savings, energy management and storage. In this study, Extreme learning machine (ELM) and Artificial Neural Network (ANN) are used to estimate the hourly electricity consumption of a city. ELM and ANN algorithms were simulated for 10 different neurons and 5 different activation functions. For the results of ELM and ANN algorithms, the significance test of the correlation coefficient was performed using statistical methods. In addition, the effects of the changes in the number of neurons and activation functions of ELM and ANN algorithms on performance were examined. It showed that the MSE, RMSE, R and R^2 values in the best performance of the ELM algorithm were 4.476e-06,0.0021,0.9999 and 0.9998. The ANN algorithm is MSE, RMSE, R and R^2 of values 5.22e-06,0.0023,0.9993 and 0.9986 respectively. While the correlation limits of the ELM algorithm at the 95% confidence interval are 0.9946 < ρ < 1.0052, the correlation limits at the 95% confidence interval of the ANN algorithm are 0.9921 < ρ < 1.0027. Neuron selection in ELM and ANN algorithms affected the performance by 1.49% and 0.34%, respectively. The activation function selection in the ELM and ANN algorithms affected the performance by 1.33% and 2.36%, respectively. The results showed that the ELM algorithm was successful in predicting energy consumption, short training time, low iteration number, good correlation limits, and significant activation selection.

show abstract

Effectiveness of groundwater heavy metal pollution indices studies by deep-learning

Cited by 58 publications

References 49 publications

Potentially toxic elements in groundwater: a hotspot research topic in environmental science and pollution research

Potentially toxic elements in groundwater: a hotspot research topic in environmental science and pollution research

Neuro-Particle Swarm Optimization Based In-Situ Prediction Model for Heavy Metals Concentration in Groundwater and Surface Water

Hourly electricity consumption estimation methodology based on the metaheuristic algorithms

Contact Info

Product

Resources

About