Conjunction of wavelet transform and SOM-mutual information data pre-processing approach for AI-based Multi-Station nitrate modeling of watersheds

Nourani, Vahid; Andalib, Gholamreza; Dąbrowska, Dominika

doi:10.1016/j.jhydrol.2017.03.002

Cited by 34 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that although the term 'groundwater vulnerability to contamination' has been operating since the 60s of the twentieth century (Witkowski and Kowalczyk, 2004), new methods of its assessment are still developing. Methods based on statistical methods (Dąbrowska et al, 2015), including artificial intelligence Nourani et al, 2017a;Nourani et al, 2017b;Połap, 2018;Nourani et al, 2021), geostatistics (Panagopoulos et al, 2006;Dąbrowska et al, 2016), creating a vulnerability map (Witczak et al, 2007) as well as indicator methods (Backman et al, 1998;Gogu and Dassargues, 2000;Kabbour et al, 2006;Talalaj, 2014) are characterized by great popularity and complexity.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Changes in the Quality of Groundwaterin the Region of the Municipal Landfill in Wojkowice

Karkocha¹

2021

ASP.FC

View full text Add to dashboard Cite

Aim of the study. Landfilling is an activity, which may threaten the destruction or contamination of the soil and water environment. Pollution can be generated both by leachate and by landfill gas. Legal conditions impose on landfill managers to monitor groundwater around the landfills. The impacted soils and groundwater show high chlorides, sulphates, heavy metal concentrations especially as compared to natural hydrochemical background values. Monitoring results can be analyzed using pollution indicators. The objective of this study was to determine the quality of groundwater in a landfill in Wojkowice (southern Poland) using the Backman index. Material and methods. The novelty of the paper results from the use of a different range of parameters than initially included in the formula. The results of water quality monitoring for three piezometers from 2013–2020 were considered. The contamination index was calculated separately for each of the analysed water samples, taking into account the electrolytic conductivity and the concentration of total organic carbon (TOC), Cd, Pb, Zn, Cu, Cr and the sum of N-NO3, N-NO2 and N-NH4. Results and conclusions. The Backman index values range in the groundwater samples were –5.3 to 603. The value of the Backman index increases with the increase in the concentration of individual parameters in groundwater. In the case of heavily transformed areas, the water pollution index has high values, exceeding 3. The results of this index indicated that the quality of the groundwater around the landfill is bad. In the future, it is planned to expand the range of parameters for calculating the index.

show abstract

Section: Introductionmentioning

confidence: 99%

Assessment of Changes in the Quality of Groundwaterin the Region of the Municipal Landfill in Wojkowice

Karkocha¹

2021

ASP.FC

View full text Add to dashboard Cite

show abstract

“…Nitrate and other nutrient concentrations have also been widely treated [10][11][12][13][14][15][16][17][18]. Reviews exist on hydrology applications of wavelets [19] and hybrid wavelet-artificial intelligence models in hydrology [20]. Several free software packages are available [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Significance and Causality in Continuous Wavelet and Wavelet Coherence Spectra Applied to Hydrological Time Series

Rodríguez-Murillo

Filella

2020

Hydrology

View full text Add to dashboard Cite

Wavelet transform, wavelet spectra, and coherence are popular tools for studying fluctuations in time series in the form of a bidimensional time and scale representation. We discuss two aspects of wavelet analysis—namely the significance and stochastic/deterministic character of the wavelet spectra. Real-time series of discharge, sodium, and sulfate concentrations in the alpine Rhône River, Switzerland, are used to illustrate these issues. First, the consequences of using an arbitrary stochastic process (usually, AR (1)) instead of the best-fitted general ARMA process in the evaluation of the significance of wavelet spectra are analyzed. Using a general ARMA instead of AR (1) decreases the significance level of the differences in wavelet power spectra (WPS) of ARMA and AR (1) compared to the WPS of the time series in all cases studied and points to a possible systematic overestimation of significance in many published studies. Besides, the significance of particular patches in the spectra is affected by multiple testing. A (conservative) way to circumvent this problem, using global wavelet spectra and global coherence spectra, is evaluated. Finally, we discuss the issue of causality and investigated it in the three measured time series mentioned above. Even if the use of the best fitted ARMA pointed to no deterministic features being present in the corrected series studied (i.e., stochastic processes are dominant in the three data series), coherence spectra between variables allowed to reveal cause-effect relationships between two “coherent” variables and/or the existence of a common effect on both variables. Therefore, such type of analysis provides a useful tool to better understand data causal relationships.

show abstract

“…There is a num ber of meth ods en abling the as sess ment of ground wa ter vul ner a bil ity to con tam i na tion (Vrba and Zaporozec, 1994;Zwahlen, 2004;Civita, 2010;Wachniew et al, 2016), in clud ing es ti ma tion meth ods, pa ram e ter meth ods (Golds cheider, 2003;Kabbour et al, 2006;Oke et al, 2016;Hermanowski and Ignaszak, 2017), rank ing meth ods (Fos ter, 1987), meth ods of math e mat i cal and hydrogeochemical mod elling (Witkowski et al, 2003), tracer meth ods (Leibundgut et al, 2009), ar ti fi cial neu ral net works (Nourani et al, 2011(Nourani et al, , 2013(Nourani et al, , 2017a, hydrochemical meth ods, and sta tis ti cal and geostatistical meth ods (Troiano et al, 1999;Lambrakis et al, 2004;Panagopoulos et al, 2006;Bhuiyan et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

A multi-method approach to groundwater risk assessment: a case study of a landfill in southern Poland

Sołtysiak

Dąbrowska

Jałowiecki

et al. 2018

Self Cite

View full text Add to dashboard Cite

Es ti mat ing ground wa ter vul ner a bil ity to pol lu tion is based on the quan ti ta tive and qual i ta tive as sess ment of the de gree of expo sure to the pol lu tion. This ar ti cle at tempts to as sess ground wa ter vul ner a bil ity to pol lu tion in the area of a com plex of landfill sites lo cated in the sup ply area of one of the im por tant ground wa ter res er voirs in south ern Po land. Two dy namic leach ing tests and two static tests were car ried out on two dif fer ent sam ples of slag from one of the met al lur gi cal land fills dur ing var ious pe ri ods of stor age (15 year old waste and freshly de pos ited waste). Trans port equa tions were based on the data from a col umn ex per i ment. The advection-dis per sion equa tion for col umn leach ing was em ployed, which con firmed the sim u la tion pa ram e ters through ex per i men ta tion. The re sults of the leach ing tests on chlo rides showed that they are leached from the land fill over a pe riod of ~60-90 years from the mo ment of de pos it ing the waste. The seep age time for the Qua ter nary aqui fer is 1-7 years and, for the Tri as sic aqui fer, 5-40 years. The Backman's con tam i na tion in dex (1998) val ues ex ceeded 25, while a high threat to ground wa ter is ob served when the con tam i na tion in dex value equals 3. The use of all the afore men tioned meth ods de ter mined the most vul ner a ble area. Key words: vul ner a bil ity, leach ing tests, con tam i na tion in dex, land fills.

show abstract

Conjunction of wavelet transform and SOM-mutual information data pre-processing approach for AI-based Multi-Station nitrate modeling of watersheds

Cited by 34 publications

References 35 publications

Assessment of Changes in the Quality of Groundwaterin the Region of the Municipal Landfill in Wojkowice

Assessment of Changes in the Quality of Groundwaterin the Region of the Municipal Landfill in Wojkowice

Significance and Causality in Continuous Wavelet and Wavelet Coherence Spectra Applied to Hydrological Time Series

A multi-method approach to groundwater risk assessment: a case study of a landfill in southern Poland

Contact Info

Product

Resources

About