RESUMEN
This paper investigates aggregated risks in aquifers, where risk exposures may originate from different contaminants e.g. nitrate-N (NO3-N), arsenic (As), boron (B), fluoride (F), and aluminium (Al). The main goal is to develop a new concept for the total risk problem under sparse data as an efficient planning tool for management through the following methodology: (i) mapping aquifer vulnerability by DRASTIC and SPECTR frameworks; (ii) mapping risk indices to anthropogenic and geogenic contaminants by unsupervised methods; (iii) improving the anthropogenic and geogenic risks by a multi-level modelling strategy at three levels: Level 1 includes Artificial Neural Networks (ANN) and Support Vector Machines (SVM) models, Level 2 combines the outputs of Level 1 by unsupervised Entropy Model Averaging (EMA), and Level 3 integrates the risk maps of various contaminants (nitrate-N, arsenic, boron, fluoride, and aluminium) modelled at Level 2. The methodology offers new data layers to transform vulnerability indices into risk indices and thereby integrates risks by a heuristic scheme but without any learning as no measured values are available for the integrated risk. The results reveal that the risk indexing methodology is fit-for-purpose. According to the integrated risk map, there are hotspots at the study area and exposed to a number of contaminants (nitrate-N, arsenic, boron, fluoride, and aluminium).
Asunto(s)
Arsénico , Agua Subterránea , Contaminantes Químicos del Agua , Monitoreo del Ambiente , Fluoruros , Nitratos/análisis , Arsénico/análisis , Boro , Aluminio , Contaminantes Químicos del Agua/análisisRESUMEN
The objectives of this study were to measure some trace element concentrations in the groundwater of the Khoy area in northwestern Iran, understand their potential origins using multivariate statistical approaches (correlation analysis, cluster analysis and factor analysis), and evaluate their non-carcinogenic human health risks to local residents through drinking water intake. The trace element status of the groundwater and the associated health risks in the study area have not previously been reported. Groundwater water samples were collected from 54 water sources in July 2017 in the study area. Samples were measured for EC, pH, major and minor elements and some trace elements (Fe, Mn, Al, Zn, Cr, Pb, Cd, Co, Ni and As). The levels of EC, F, Cd, Pb, Zn, As and all the major ions except K exceeded permissible levels for drinking water. Multivariate analysis showed that the quality of groundwater was mainly controlled by geogenic factors followed by anthropogenic impacts. Health risk assessment results indicated that Cr and As in the groundwater, with hazard quotient values of 0.0001 and 11.55, respectively, had the lowest and highest impacts of non-carcinogenic risk to adults and children in the area. The high-risk samples were mainly situated in the northeast and southwest of the Khoy plain where the groundwater was saline. The health risk associated with water consumption from the unconfined aquifer was higher than that from the confined aquifer in the study area. Special attention should be paid to groundwater management in the high-risk areas to control factors (e.g., EC, pH and redox) that stimulate the release of trace elements into groundwater.
Asunto(s)
Agua Subterránea/análisis , Metales/análisis , Medición de Riesgo/métodos , Contaminantes Químicos del Agua/análisis , Adulto , Carcinógenos/toxicidad , Niño , Análisis por Conglomerados , Monitoreo del Ambiente/métodos , Agua Subterránea/química , Humanos , Irán , Metales/toxicidad , Análisis Multivariante , Contaminantes Químicos del Agua/toxicidadRESUMEN
Kordkandi-Duzduzan plain is one of the fertile plains of East Azarbaijan Province, NW of Iran. Groundwater is an important resource for drinking and agricultural purposes due to the lack of surface water resources in the region. The main objectives of the present study are to identify the hydrogeochemical processes and the potential sources of major, minor, and trace metals and metalloids such as Cr, Mn, Cd, Fe, Al, and As by using joint hydrogeochemical techniques and multivariate statistical analysis and to evaluate groundwater quality deterioration with the use of PoS environmental index. To achieve these objectives, 23 groundwater samples were collected in September 2015. Piper diagram shows that the mixed Ca-Mg-Cl is the dominant groundwater type, and some of the samples have Ca-HCO3, Ca-Cl, and Na-Cl types. Multivariate statistical analyses indicate that weathering and dissolution of different rocks and minerals, e.g., silicates, gypsum, and halite, ion exchange, and agricultural activities influence the hydrogeochemistry of the study area. The cluster analysis divides the samples into two distinct clusters which are completely different in EC (and its dependent variables such as Na+, K+, Ca2+, Mg2+, SO42-, and Cl-), Cd, and Cr variables according to the ANOVA statistical test. Based on the median values, the concentrations of pH, NO3-, SiO2, and As in cluster 1 are elevated compared with those of cluster 2, while their maximum values occur in cluster 2. According to the PoS index, the dominant parameter that controls quality deterioration is As, with 60% of contribution. Samples of lowest PoS values are located in the southern and northern parts (recharge area) while samples of the highest values are located in the discharge area and the eastern part.
Asunto(s)
Monitoreo del Ambiente/métodos , Contaminación Química del Agua/estadística & datos numéricos , Agricultura , Análisis por Conglomerados , Ambiente , Agua Subterránea/análisis , Iones/análisis , Irán , Minerales/análisis , Análisis Multivariante , Dióxido de Silicio/análisis , Contaminantes Químicos del Agua/análisis , Calidad del Agua , Recursos HídricosRESUMEN
The critical role of groundwater in meeting diverse needs, including drinking, industrial, and agricultural, highlights the urgency of effective resource management. Excessive groundwater extraction, especially in coastal regions including Urmia Plain in NW Iran, disrupts the equilibrium between freshwater and saline boundaries within aquifers. Influential parameters governing seawater intrusion-groundwater occurrence (G), aquifer hydraulic conductivity (A), the height of groundwater level above the mean sea level (L), distance from the shore (D), impact of the existing status of seawater intrusion (I), and thickness of the saturated aquifer (T)-merge to shape the GALDIT vulnerability index for coastal aquifers. This study enriches the GALDIT framework by incorporating two additional hydrogeological variables: hydraulic gradient (i) and pumping rate (P). This expansion produces seven distinct vulnerability maps (GALDIT, GAiDIT, GAiDIT-P, GALDIT-i, GALDIT-iP, GALDIT-P, GAPDIT). In the Urmia Plain, the traditional GALDIT index reveals vulnerability values ranging from 2 to 8.1, categorized into six classes from negligible to very high vulnerability. However, the modified indices, GAiDIT and GAiDIT-P, yield a three-class categorization, ranging from low to high vulnerability. The introduction of the "i" and "P" parameters in GALDIT-i and GALDIT-iP enhances the precision of vulnerability mapping, altering class distribution and intensifying vulnerability ratings. The eastern, central, and coastal areas of the Urmia Plain demonstrate high to very high vulnerability levels, in contrast to the lower vulnerability observed in the western regions. Both the GALDIT-P (r = 0.82) and GALDIT-iP (r = 0.81) indices show strong correlations with Cl concentration, thereby improving mapping accuracy over the traditional GALDIT index (r = 0.72). A sensitivity analysis highlights the critical influence of the "i" parameter, suggesting its weighting should be revised. Parameter recalibration serves to amplify the significance of "G," "L," "D," and "i" parameters, while diminishing others. The integration of multiple hydrogeological variables considerably enhances the precision of groundwater vulnerability assessments.
Asunto(s)
Agua Subterránea , Salinidad , Agua Subterránea/química , Irán , Monitoreo del Ambiente/métodos , Agua de Mar/químicaRESUMEN
ABSTRACT: Tuberculosis (TB) remains a significant global health concern and kills millions of people every year. While TB can affect any organ in the body, breast TB is relatively uncommon. This study presents a comprehensive review of literature spanning 23 years, with a focus on cases of breast TB in Iran. Among the 96 cases found, the majority (89.6%) fell within the age range of 20-60, with a striking prevalence among women (98.9%). Common symptoms included pain and palpable mass, each presenting in approximately 60.4% of cases. Notably, only a quarter of patients had a confirmed history of exposure to a known TB case. Left breast involvement was more prevalent (58.3%), with ipsilateral lymph node enlargement observed in 40.6% of cases. Given the clinical presentation of breast TB, which often leads to misdiagnosis, a significant proportion of cases (68.7%) were diagnosed through excisional biopsy. Following a standard 6-month regimen of anti-TB drugs, relapse occurred in only 4.2% of cases. This study highlights the need for heightened awareness and vigilance in diagnosing breast TB, especially in regions with a high burden. Although breast TB poses diagnostic challenges, with prompt identification and treatment, the prognosis is generally favorable, with a low incidence of relapse.
Asunto(s)
Tuberculosis , Humanos , Irán/epidemiología , Femenino , Tuberculosis/epidemiología , Tuberculosis/diagnóstico , Tuberculosis/tratamiento farmacológico , Tuberculosis/microbiología , Adulto , Antituberculosos/uso terapéutico , Prevalencia , Enfermedades de la Mama/microbiología , Enfermedades de la Mama/diagnóstico , Enfermedades de la Mama/patología , Enfermedades de la Mama/epidemiología , Enfermedades de la Mama/tratamiento farmacológico , Persona de Mediana Edad , Adulto Joven , Masculino , Mama/patología , Mama/microbiologíaRESUMEN
Water quality variables, including chlorophyll-a (Chl-a), play a pivotal role in comprehending and evaluating the condition of aquatic ecosystems. Chl-a, a pigment present in diverse aquatic organisms, notably algae and cyanobacteria, serves as a valuable indicator of water quality. Thus, the objectives of this study encompass: (1) the assessment of the predictive capabilities of four deep learning (DL) models - namely, recurrent neural network (RNN), long short-term memory (LSTM), gated recurrence unit (GRU), and temporal convolutional network (TCN) - in forecasting Chl-a concentrations; (2) the incorporation of these DL models into ensemble models (EMs) employing genetic algorithm (GA) and non-dominated sorting genetic algorithm (NSGA-II) to harness the strengths of each standalone model; and (3) the evaluation of the efficacy of the developed EMs. Utilizing data collected at 15-min intervals from Small Prespa Lake (SPL) in Greece, the models employed hourly Chl-a concentration lag times, extending up to 6 h, as models' inputs to forecast Chla (t+1). The proposed models underwent training on 70% of the dataset and were subsequently validated on the remaining 30%. Among the standalone DL models, the GRU model exhibited superior performance in Chl-a forecasting, surpassing the RNN, LSTM, and TCN models by 8%, 2%, and 2%, respectively. Furthermore, the integration of DL models through single-objective GA and multi-objective NSGA-II optimization algorithms yielded hybrid models adept at effectively forecasting both low and high Chl-a concentrations. The ensemble model based on NSGA-II outperformed standalone DL models as well as the GA-based model across a range of evaluation indices. For instance, considering the R-squared metric, the study's findings demonstrated that the EM-NSGA-II stands out with exceptional effectiveness compared to DL and EM-GA models, showcasing improvements of 14% (RNN), 8% (LSTM), 6% (GRU), 8% (TCN), and 3% (EM-GA) during the testing phase.
Asunto(s)
Aprendizaje Profundo , Calidad del Agua , Ecosistema , Redes Neurales de la Computación , Algoritmos , PredicciónRESUMEN
Chennai, the capital city of Tamil Nadu in India, has experienced several instances of severe flooding over the past two decades, primarily attributed to persistent heavy rainfall. Accurate mapping of flood-prone regions in the basin is crucial for the comprehensive flood risk management. This study used the GIS-MCDA model, a multi-criteria decision analysis (MCDA) model that incorporated geographic information system (GIS) technology to support decision making processes. Remote sensing, GIS, and analytical hierarchy technique (AHP) were used to identify flood-prone zones and to determine the weights of various factors affecting flood risk, such as rainfall, distance to river, elevation, slope, land use/land cover, drainage density, soil type, and lithology. Four groups (zones) were identified by the flood susceptibility map including high, medium, low, and very low. These zones occupied 16.41%, 67.33%, 16.18%, and 0.08% of the area, respectively. Historical flood events in the study area coincided with the flood risk classification and flood vulnerability map. Regions situated close to rivers, characterized by low elevation, slope, and high runoff density were found to be more susceptible to flooding. The flood susceptibility map generated by the GIS-MCDA accurately described the flood-prone regions in the study area.
Asunto(s)
Monitoreo del Ambiente , Inundaciones , India , Monitoreo del Ambiente/métodos , Sistemas de Información Geográfica , RíosRESUMEN
Water shortage in arid and semi-arid areas like Iran makes groundwater contamination a crucial issue. In the Khoy aquifer, NW Iran, contaminants (e.g., arsenic (As), nitrate (NO3-), lead (Pb), and zinc (Zn)) may originate from both geological and anthropogenic sources. The objectives of the study are to (1) employ soft modeling framework to abstract available hydrogeochemical information into a perceptual model and (2) build a conceptual model using the risk cells (RCs) by applying the following two steps: (i) study Origin-Source-Pathways-Receptor-Consequence (OSPRC) as a risk system; and (ii) apply "soft modeling" as a set of diverse and classical tools including graphical representations, geological surveys, and multivariate statistical analysis to validate the information by evaluating their convergence or divergence behaviors among different tools used for investigating the groundwater contaminants. According to the perceptual model, the Khoy aquifer contains four RCs. RC4 (southern of plain) and RC2 (northern of the plain) contain high levels of As, while RC2 contains high amounts of Zn. In RC1 (northern of plain) and RC3 (middle of plain), a high concentration of Pb is detected, while in RC3 and RC4, there is a high concentration of NO3-. It was found that a soft modeling approach can only identify the dominant hydrogeochemical processes for each RC as a descriptive model, rather than the use of quantitative models if sufficient data are available.
Asunto(s)
Arsénico , Agua Subterránea , Contaminantes Químicos del Agua , Arsénico/análisis , Monitoreo del Ambiente , Agua Subterránea/análisis , Irán , Plomo/análisis , Nitratos/análisis , Compuestos Orgánicos , Agua/análisis , Contaminantes Químicos del Agua/análisis , Zinc/análisisRESUMEN
Trace element (TE) pollution in groundwater resources is one of the major concerns in both developing and developed countries as it can directly affect human health. Arsenic (As), Barium (Ba), and Rubidium (Rb) can be considered as TEs naturally present in groundwater due to water-rock interactions in Campania Plain (CP) aquifers, in South Italy. Their concentration could be predicted via some readily available input variables using an algorithm like the iterative classifier optimizer (ICO) for regression, and novel hybrid algorithms with additive regression (AR-ICO), attribute selected classifier (ASC-ICO) and bagging (BA-ICO). In this regard, 244 groundwater samples were collected from water wells within the CP and analyzed with respect to the electrical conductivity, pH, major ions and selected TEs. To develop the models, the available dataset was divided randomly into two subsets for model training (70% of the dataset) and evaluation (30% of the dataset), respectively. Based on the correlation coefficient (r), different input variables combinations were constructed to find the most effective one. Each model's performance was evaluated using common statistical and visual metrics. Results indicated that the prediction of As and Ba concentrations strongly depends on HCO3-, while Na+ is the most effective variable on Rb prediction. Also, the findings showed that the most powerful predictive models were those that used all the available input variables. According to models' performance evaluation metrics, the hybrid ASC-ICO outperformed other hybrid (BA- and AR-ICO) and standalone (ICO) algorithms to predict As and Ba concentrations, while both hybrid ASC- and BA-ICO models had higher accuracy and lower error than other algorithms for Rb prediction.
Asunto(s)
Agua Subterránea , Oligoelementos , Contaminantes Químicos del Agua , Algoritmos , Monitoreo del Ambiente , Oligoelementos/análisis , Contaminantes Químicos del Agua/análisis , Pozos de AguaRESUMEN
In this study, the modified SINTACS method, a rating-based groundwater vulnerability approach, was applied to data from the Campanian Plain, southern Italy, to identify groundwater vulnerable areas accurately. To mitigate the subjectivity of SINTACS rating and weighting schemes, a modified SINTACS model was formulated by optimizing parameter ratings using the Wilcoxon rank-sum test, and the weight scores using the evolutionary algorithms including artificial bee colony (ABC) and genetic algorithm (GA) methods. The validity of the models was verified by analyzing the correlation coefficient between the vulnerability index and nitrate (NO3) and sulfate (SO4) concentrations found in the groundwater. The correlation coefficients between the pollutant concentrations and the relevant vulnerability index increased significantly from - 0.35 to 0.43 for NO3 and from - 0.28 to 0.33 for SO4 after modifying the ratings and weights of typical SINTACS. Besides, a multi-pollutant vulnerability map considering both NO3 and SO4 pollutants was produced by amalgamating the best calibrated vulnerability maps based on the obtained correlation values (i.e., the Wilcoxon-ABC-based SINTACS vulnerability map for NO3 and the Wilcoxon-GA-based SINTACS vulnerability map for SO4). The resultant multi-pollutant vulnerability map coincided significantly with a land use map of the study area, where anthropogenic activities represented the main sources of pollution.
Asunto(s)
Contaminantes Ambientales , Agua Subterránea , Contaminantes Químicos del Agua , Algoritmos , Monitoreo del Ambiente , Italia , Nitratos/análisis , Contaminantes Químicos del Agua/análisisRESUMEN
The DRASTIC technique is commonly used to assess groundwater vulnerability. The main disadvantage of the DRASTIC method is the difficulty associated with identifying appropriate ratings and weight assignments for each parameter. To mitigate this issue, ratings and weights can be approximated using different methods appropriate to the conditions of the study area. In this study, different linear (i.e., Wilcoxon test and statistical approaches) and nonlinear (Genetic algorithm [GA]) modifications for calibration of the DRASTIC framework using nitrate (NO3 ) concentrations were compared through the preparation of groundwater vulnerability maps of the Meshqin-Shahr plain, Iran. Twenty-two groundwater samples were collected from wells in the study area, and their respective NO3 concentrations were used to modify the ratings and weights of the DRASTIC parameters. The areas found to have the highest vulnerability were in the eastern, central, and western regions of the plain. Results showed that the modified DRASTIC frameworks performed well, compared to the unmodified DRASTIC. When measured NO3 concentrations were correlated with the vulnerability indices produced by each method, the unmodified DRASTIC method performed most poorly, and the Wilcoxon-GA-DRASTIC method proved optimal. Compared to the unmodified DRASTIC method with an R2 of 0.22, the Wilcoxon-GA-DRASTIC obtained a maximum R2 value of 0.78. Modification of DRASTIC parameter ratings was found to be more efficient than the modification of the weights in establishing an accurately calibrated DRASTIC framework. However, modification of parameter ratings and weights together increased the R2 value to the highest degree.
Asunto(s)
Agua Subterránea , Monitoreo del Ambiente , Irán , Modelos Teóricos , Nitratos/análisisRESUMEN
While it remains the primary source of safe drinking and irrigation water in northwest Iran's Maku Plain, the region's groundwater is prone to fluoride contamination. Accordingly, modeling techniques to accurately predict groundwater fluoride concentration are required. The current paper advances several novel data mining algorithms including Lazy learners [instance-based K-nearest neighbors (IBK); locally weighted learning (LWL); and KStar], a tree-based algorithm (M5P), and a meta classifier algorithm [regression by discretization (RBD)] to predict groundwater fluoride concentration. Drawing on several groundwater quality variables (e.g., Ca 2 + , Mg 2 + , Na + , K + , HCO 3 - , CO 3 2 - , SO 4 2 - , and Cl - concentrations), measured in each of 143 samples collected between 2004 and 2008, several models predicting groundwater fluoride concentrations were developed. The full dataset was divided into two subsets: 70% for model training (calibration) and 30% for model evaluation (validation). Models were validated using several statistical evaluation criteria and three visual evaluation approaches (i.e., scatter plots, Taylor and Violin diagrams). Although Na+ and Ca2+ showed the greatest positive and negative correlations with fluoride (r = 0.59 and -0.39, respectively), they were insufficient to reliably predict fluoride levels; therefore, other water quality variables, including those weakly correlated with fluoride, should be considered as inputs for fluoride prediction. The IBK model outperformed other models in fluoride contamination prediction, followed by KStar, RBD, M5P, and LWL. The RBD and M5P models were the least accurate in terms of predicting peaks in fluoride concentration values. Results of the current study can be used to support practical and sustainable management of water and groundwater resources.
Asunto(s)
Agua Subterránea , Contaminantes Químicos del Agua , Monitoreo del Ambiente , Fluoruros/análisis , India , Contaminantes Químicos del Agua/análisis , Calidad del AguaRESUMEN
Developing a reliable groundwater vulnerability and contamination risk map is very important for groundwater management and protection. This study aims to compare various modified DRASTIC vulnerability frameworks based on rate calibration using the Wilcoxon rank-sum test (WRST), frequency ratio (FR) and weight optimization using the correlation coefficient (CC), the analytic hierarchy process (AHP), and genetic algorithms (GA), as well as to introduce, for the first time, an aggregated approach based on a bagging ensemble to develop a combined modified DRASTIC model. This research was conducted in the Khoy plain, NW Iran. To develop a typical DRASTIC map, seven DRASTIC data layers were generated, weighted, and then overlaid in ArcGIS. The nitrate (NO3) concentrations at 54 sites in the study area were used to validate the models by calculating the correlation coefficient (r) between the vulnerability/risk indices and NO3 concentrations. The calculated r value for the typical DRASTIC was 0.12. A sensitivity analysis reveals that the impact of the vadose zone and conductivity parameters with mean variation indices of 22.2 and 7.5%, respectively, have the highest and lowest influence on aquifer vulnerability. The r values increased for all the optimized frameworks. The results show that the WRST and GA methods are the most effective methods for calibration and optimization of DRASTIC rates and weights, with the WRST-GA-DRASTIC model obtaining an r value of 0.64. A bagging ensemble model was employed to combine the advantages of each standalone model. The bagging ensemble model yields an r value of 0.67. The ensemble model has the potential to increase the r value further than both the standalone optimized frameworks and the typical DRASTIC approach. In terms of spatial distribution class area (%), the bagging ensemble-DRASTIC model demonstrates that the moderate and low contamination risk classes with 16.4 and 23.1% of the total area cover the lowest and highest parts of the plain.
Asunto(s)
Agua Subterránea/análisis , Hidrología/métodos , Contaminación del Agua/análisis , Algoritmos , Calibración , Irán , Modelos Estadísticos , Modelos Teóricos , Nitratos/análisisRESUMEN
Accurate prediction of water quality parameters plays a crucial and decisive role in environmental monitoring, ecological systems sustainability, human health, aquaculture and improved agricultural practices. In this study a new hybrid two-layer decomposition model based on the complete ensemble empirical mode decomposition algorithm with adaptive noise (CEEMDAN) and the variational mode decomposition (VMD) algorithm coupled with extreme learning machines (ELM) and also least square support vector machine (LSSVM) was designed to support real-time environmental monitoring of water quality parameters, i.e. chlorophyll-a (Chl-a) and dissolved oxygen (DO) in a Lake reservoir. Daily measurements of Chl-a and DO for June 2012-May 2013 were employed where the partial autocorrelation function was applied to screen the relevant inputs for the model construction. The variables were then split into training, validation and testing subsets where the first stage of the model testing captured the superiority of the ELM over the LSSVM algorithm. To improve these standalone predictive models, a second stage implemented a two-layer decomposition with the model inputs decomposed in the form of high and low frequency oscillations, represented by the intrinsic mode function (IMF) through the CEEMDAN algorithm. The highest frequency component, IMF1 was further decomposed with the VMD algorithm to segregate key model input features, leading to a two-layer hybrid VMD-CEEMDAN model. The VMD-CEEMDAN-ELM model was able to reduce the root mean square and the mean absolute error by about 14.04% and 7.12% for the Chl-a estimation and about 5.33% and 4.30% for the DO estimation, respectively, compared with the standalone counterparts. Overall, the developed methodology demonstrates the robustness of the two-phase VMD-CEEMDAN-ELM model in identifying and analyzing critical water quality parameters with a limited set of model construction data over daily horizons, and thus, to actively support environmental monitoring tasks, especially in case of high-frequency, and relatively complex, real-time datasets.
RESUMEN
Constructing accurate and reliable groundwater risk maps provide scientifically prudent and strategic measures for the protection and management of groundwater. The objectives of this paper are to design and validate machine learning based-risk maps using ensemble-based modelling with an integrative approach. We employ the extreme learning machines (ELM), multivariate regression splines (MARS), M5 Tree and support vector regression (SVR) applied in multiple aquifer systems (e.g. unconfined, semi-confined and confined) in the Marand plain, North West Iran, to encapsulate the merits of individual learning algorithms in a final committee-based ANN model. The DRASTIC Vulnerability Index (VI) ranged from 56.7 to 128.1, categorized with no risk, low and moderate vulnerability thresholds. The correlation coefficient (r) and Willmott's Index (d) between NO3 concentrations and VI were 0.64 and 0.314, respectively. To introduce improvements in the original DRASTIC method, the vulnerability indices were adjusted by NO3 concentrations, termed as the groundwater contamination risk (GCR). Seven DRASTIC parameters utilized as the model inputs and GCR values utilized as the outputs of individual machine learning models were served in the fully optimized committee-based ANN-predictive model. The correlation indicators demonstrated that the ELM and SVR models outperformed the MARS and M5 Tree models, by virtue of a larger d and r value. Subsequently, the r and d metrics for the ANN-committee based multi-model in the testing phase were 0.8889 and 0.7913, respectively; revealing the superiority of the integrated (or ensemble) machine learning models when compared with the original DRASTIC approach. The newly designed multi-model ensemble-based approach can be considered as a pragmatic step for mapping groundwater contamination risks of multiple aquifer systems with multi-model techniques, yielding the high accuracy of the ANN committee-based model.
RESUMEN
Accurate prediction of groundwater level (GWL) fluctuations can play an important role in water resources management. The aims of the research are to evaluate the performance of different hybrid wavelet-group method of data handling (WA-GMDH) and wavelet-extreme learning machine (WA-ELM) models and to combine different wavelet based models for forecasting the GWL for one, two and three months step-ahead in the Maragheh-Bonab plain, NW Iran, as a case study. The research used totally 367 monthly GWLs (m) datasets (Sep 1985-Mar 2016) which were split into two subsets; the first 312 datasets (85% of total) were used for model development (training) and the remaining 55 ones (15% of total) for model evaluation (testing). The stepwise selection was used to select appropriate lag times as the inputs of the proposed models. The performance criteria such as coefficient of determination (R2), root mean square error (RMSE) and Nash-Sutcliffe efficiency coefficient (NSC) were used for assessing the efficiency of the models. The results indicated that the ELM models outperformed GMDH models. To construct the hybrid wavelet based models, the inputs and outputs were decomposed into sub-time series employing different maximal overlap discrete wavelet transform (MODWT) functions, namely Daubechies, Symlet, Haar and Dmeyer of different orders at level two. Subsequently, these sub-time series were served in the GMDH and ELM models as an input dataset to forecast the multi-step-ahead GWL. The wavelet based models improved the performances of GMDH and ELM models for multi-step-ahead GWL forecasting. To combine the advantages of different wavelets, a least squares boosting (LSBoost) algorithm was applied. The use of the boosting multi-WA-neural network models provided the best performances for GWL forecasts in comparison with single WA-neural network-based models.