Contaminant Source Identification Research Articles

Regional Groundwater Water Quality Assessment and Contamination Source Identification by a Self-Organizing Map and Entropy Method in Pinggu Basin, Northeast Beijing

Groundwater quality assessment is important for understanding the suitability of groundwater resources for various purposes. Although many different methods have been proposed for this purpose, few methods have considered the spatial variation of groundwater components during the assessments. In this study, we proposed to combine the self-organizing map (SOM) and entropy-based weight determining method to assess groundwater quality. Totally, 955 water samples taken from 58 wells during 2010–2017 were used in the study. 22 hydrochemical components (K+, Na+, Ca2+, Mg2+, NH4+, Cl−, SO42-, F−, NO3−, Fe2+, Fe3+, Al, etc.) were used in the assessment for each sample. These sampling points can be classified into five clusters, which may be affected by four different sources: landfill sources (cluster 3), industrial and agricultural sources (cluster 5), and domestic sewage discharge sources (clusters 1, 2, and 4). The scores of the water quality of the five clusters that were calculated by the entropy method are 0.2658, 0.2634, 0.5737, 0.2608, and 0.5718, indicating that the groundwater affected by domestic sewage discharge sources (clusters 1, 2, and 4) are better than other two sources (clusters 3 and 5) in the study area. The results of this study provide insights for the protection of groundwater resources and the treatment of groundwater pollution in the future.

Contaminant source identification in groundwater by means of artificial neural network

In a desired environmental protection system, groundwater may not be excluded. In addition to the problem of over-exploitation, in total disagreement with the concept of sustainable development, another not negligible issue concerns the groundwater contamination. Mainly, this aspect is due to intensive agricultural activities or industrialized areas. In literature, several papers have dealt with transport problem, especially for inverse problems in which the release history or the source location are identified. The innovative aim of the paper is to develop a data-driven model that is able to analyze multiple scenarios, even strongly non-linear, in order to solve forward and inverse transport problems, preserving the reliability of the results and reducing the uncertainty. Furthermore, this tool has the characteristic of providing extremely fast responses, essential to identify remediation strategies immediately. The advantages produced by the model were compared with literature studies. In this regard, a feedforward artificial neural network, which has been trained to handle different cases, represents the data-driven model. Firstly, to identify the concentration of the pollutant at specific observation points in the study area (forward problem); secondly, to deal with inverse problems identifying the release history at known source location; then, in case of one contaminant source, identifying the release history and, at the same time, the location of the source in a specific sub-domain of the investigated area. At last, the observation error is investigated and estimated. The results are satisfactorily achieved, highlighting the capability of the ANN to deal with multiple scenarios by approximating nonlinear functions without the physical point of view that describes the phenomenon, providing reliable results, with very low computational burden and uncertainty.

Application of the complementary ensemble empirical mode decomposition for the identification of simulation model parameters and groundwater contaminant sources

Identification of groundwater contaminant sources (GCSs) relies on actual observed data, and the observed data directly affects the accuracy of the identification results. However, the observed data inevitably contains noise due to accidental and systematic errors, and the identification results of GCSs based on the observed data containing noise are usually not reliable. This seriously restricts the rational design of contamination remediation plans and contamination risk assessment. To solve this problem, complementary ensemble empirical mode decomposition (CEEMD) was applied to the joint identification of simulation model parameters and GCSs information in this study for the first time. The wavelet analysis and CEEMD methods were used to reduce the noise in observed concentrations respectively, and the noise reduction effect of the two methods was compared and analyzed. Then the simulated concentrations, observed concentrations and noise-reduced observed concentrations with the best noise reduction effect were then applied to identify simulation model parameters and GCSs information, respectively, after which the corresponding identification results were compared and analyzed. The results showed that CEEMD could reduce the noise contained in the observed concentrations more effectively and make it closer to the actual values when compared with the wavelet analysis method. The accuracy of identification results based on the noise-reduced observed concentrations by was improved. As the noise contained in the observed concentrations increased, the noise reduction effect of the CEEMD decreased. Nevertheless, the accuracy of the identification results based on the noise-reduced observed concentrations was still higher than that of those based on the observed concentrations with the same intensity noise without denoising.

A multitechnique approach for the identification of multiple contamination sources near a polluted industrial site

AbstractDegraded land requires rapid and suitable remedial actions, thus appropriate and fast methodological approaches for estimating the spatial distribution of contaminants are needed. In this context, a methodological approach combining isotopic measurements, heavy metals concentrations mapping, X‐ray diffraction, and cluster analysis, was applied to characterize a polluted industrial site where the contamination due to improper waste disposal could have spread also into the surrounding fields. This approach was applied to a set of representative topsoil (from 15 to 30 cm depth) and subsoil (from 130 to 150 cm depth) samples, selected either inside or outside the contaminated site. The X‐ray diffraction analysis highlighted that only the mineralogy of the subsoil below the buried waste was noticeably altered, while the concentration mapping highlighted that the levels of several heavy metals on the edge of the contaminated site, at both depths, were very similar to those found in the samples from the outside. Based on these findings, Pb was used as a tracer for heavy metal pollution by its stable isotopes' analysis. The cluster analysis of the isotopic measurements revealed that only the contamination detected inside the industrial site could be attributed to the pollutants migration from the buried waste. Conversely, the contaminants concentrations found in the topsoil samples taken outside the site could be ascribed to contamination sources other than the polluted waste present inside the site.

Contamination characteristics, source identification, and source-specific health risks of heavy metal(loid)s in groundwater of an arid oasis region in Northwest China

Heavy metal(loid)s accumulation in groundwater has posed serious ecological and health concerns worldwide. Source-specific risk apportionment is crucial to prevent and control potential heavy metal(loid)s pollution in groundwater. However, there is very limited comprehensive information on the health risk apportionment for groundwater heavy metal(loid)s in arid regions. Thus, the Zhangye Basin, a typical arid oasis region in Northwest China, was selected to investigate the contamination characteristics, possible pollution sources, and source-specific health risks of groundwater heavy metal(loid)s. The heavy metal pollution index (HPI), the Nemerow index (NI), and the contamination degree (CD) were adopted to assess the pollution level of heavy metal(loid)s; then source-specific health risk was apportioned integrating the absolute principal component scores-multiple linear regression (APCS-MLR) with health risk assessment. Noticeable accumulation of Mn, Fe, and As was observed in this region with especially Fe/As in 12.68%/2.11% of the samples revealing significant enrichment. Approximately 3.5% of the groundwater samples caused moderate or higher pollution level based on the HPI. The APCS-MLR model was more physically applicable for the current research than the positive matrix factorization (PMF) model. Industrial-agricultural activity factor (12.56%) was the major source of non-cancer (infants: 59.15%, children: 64.87%, teens: 64.06%, adults: 64.02%) and cancer risks (infants: 77.36%, children: 77.35%, teens: 77.40%, adults: 77.41%). Industrial-agricultural activities should be given priority to control health risks of heavy metal(loid)s in groundwater. These findings provide fundamental and significant information for mitigating health risks caused by heavy metal(loid)s in groundwater of typical arid oasis regions by controlling priority sources.

Spatial distribution, pollution assessment, and source identification of heavy metals in the Yellow River

The discharge of pollutants into the Yellow River has been strictly controlled since 2013 due to the severe pollution. Thus, the overall water quality of the Yellow River has been becoming better year by year. However, the contamination status and source identification of heavy metals from the entire Yellow River remains unclear. Our results demonstrated that heavy metal contents in sediments showed little changes over time, whereas significant alleviation was observed in surface water compared to the reported metal concentrations before 2013. No heavy metal contamination was observed in surface water, and the distribution of all heavy metals in surface water fluctuated along the mainstream without a significant spatial difference. Heavy metals in sediments were assessed as low to moderate contamination degree. The majority of heavy metal concentrations were higher in the upstream and midstream than that in the downstream. Besides anthropogenic activities, the natural contribution from soil erosion of the Loess Plateau was also an important source of heavy metals in the Yellow River sediments. Our results highlight that control of anthropogenic activities and soil erosion of the Loess Plateau are necessary measures to reduce heavy metals in the Yellow River.

An Adaptive Surrogate-Assisted Simulation-Optimization Method for Identifying Release History of Groundwater Contaminant Sources

The simulation-optimization method, integrating the numerical model and the evolutionary algorithm, is increasingly popular for identifying the release history of groundwater contaminant sources. However, due to the usage of computationally intensive evolutionary algorithms, traditional simulation-optimization methods always require thousands of simulations to find appropriate solutions. Such methods yield a prohibitive computational burden if the simulation involved is time-consuming. To reduce general computation, this study proposes a novel simulation-optimization method for solving the inverse contaminant source identification problems, which uses surrogate models to approximate the numerical model. Unlike many existing surrogate-assisted methods using the pre-determined surrogate model, this paper presents an adaptive surrogate technique to construct the most appropriate surrogate model for the current numerical model. Two representative cases about identifying the release history of contaminant sources are used to investigate the accuracy and robustness of the proposed method. The results indicate that the proposed adaptive surrogate-assisted method effectively identifies the release history of groundwater contaminant sources with a higher degree of accuracy and shorter computation time than traditional methods.

Characterization of groundwater contamination: A transformer-based deep learning model

Identification of groundwater contaminant sources in a highly-heterogenous geosystems results in a high-dimensional inverse problem and is often solved based on a surrogate model to alleviate the computational burden. Surrogate modeling through deep learning has a great potential for learning complex nonlinear relationships between model inputs and outputs. Most of the developed surrogates, however, can only estimate the contaminant concentration fields at a limit number of time-steps with a relatively large lag. In this paper, a transformer-based surrogate model is developed to provide a detailed release history of contaminant, which allows more accurate analyzing the distributions and planning. As such, a Koopman-operator-based convolutional autoencoder is trained and fixed prior to the training of transformer. Here, the encoder converts the concentration fields into a one-dimensional embedding space and the transformer is trained on this space to learn the system dynamics and predict the embedding feature at next time step, which is reconstructed back to the original space with the decoder. The proposed surrogate model is tested on a complex problem and the results demonstrate that the proposed transformer-based surrogate can efficiently provide an accurate estimation of the evolution of contaminant concentration field at a greater number of time-steps compared to the previous works.

Adenovirus in fishery harbours and identification of contamination sources

Adenoviruses (AdVs) are a major cause of clinical infections and have been proposed as indicators of water quality. However, quantitative data on the environmental prevalence of AdVs is lacking. We investigated the prevalence, distribution, seasonal occurrence, quantity, and genotype of AdVs in 13 fishing harbours in Taiwan. AdVs in the water samples were isolated by membrane filtration and the AdV DNA was extracted. Next, AdVs were detected using nested polymerase chain reaction. Genotyping and phylogenetic analysis were performed to identify various AdV genotypes present in the water samples. The F species human AdV (HAdV) serotype 41 (63.6%) and C species porcine AdV (PAdV) serotype 5 (33.3%) were more prevalent than the other serotypes. The prevalence of AdVs was highest in the fall, followed by in the spring and summer. Among the fishing harbours, the highest detection rate of AdVs was observed in Yenpudongang in all seasons. However, Puoziliao was the only site at which AdVs were not detected during the study period. AdV detection at sampling sites may be correlated with sewage and livestock wastewater discharge via outflow of nearby rivers to fishing ports. Statistical analysis (Mann–Whitney U test) based on data from water quality indicators revealed that the presence of AdVs was significantly associated with the heterotrophic plate count, pH, and salinity. Human and swine population data from nearby local townships and river/drainage basins were collected from the Taiwan Central Government's website. The data were analyzed using Spearman's rank correlation coefficient to determine the relationship between the prevalence of AdVs, HAdVs, and PAdVs in fishing harbours, and microbial water quality indicators. Statistical evidence indicated that the detection levels of HAdVs and PAdVs in fishing harbours were mainly associated with human and swine populations in the corresponding river/drainage basin, respectively. Additionally, the swine population in the river/drainage basin was positively correlated with microbial water quality indicators.

Connecting microbial, nutrient, physiochemical, and land use variables for the evaluation of water quality within mixed use watersheds

As non-point sources of pollution begin to overtake point sources in watersheds, source identification and complicating variables such as rainfall are growing in importance. Microbial source tracking (MST) allows for identification of fecal contamination sources in watersheds; when combined with data on land use and co-occuring variables (e.g., nutrients, sediment runoff) MST can provide a basis for understanding how to effectively remediate water quality. To determine spatial and temporal trends in microbial contamination and correlations between MST and nutrients, water samples (n = 136) were collected between April 2017 and May of 2018 during eight sampling events from 17 sites in 5 mixed-use watersheds. These samples were analyzed for three MST markers (human – B. theta; bovine – CowM2; porcine – Pig2Bac) along with E. coli, nutrients (nitrogen and phosphorus species), and physiochemical paramaters. These water quality variables were then paired with data on land use, streamflow, precipitation and management practices (e.g., tile drainage, septic tank density, tillage practices) to determine if any significant relationships existed between the observed microbial contamination and these variables. The porcine marker was the only marker that was highly correlated (p value <0.05) with nitrogen and phosphorus species in multiple clustering schemes. Significant relationships were also identified between MST markers and variables that demonstrated temporal trends driven by precipitation and spatial trends driven by septic tanks and management practices (tillage and drainage) when spatial clustering was employed.

Identification of Water Contamination Sources Using Hydrochemical and Isotopic Studies—The Kozłowa Góra Reservoir Catchment Area (Southern Poland)

The application of combined research methods, such as hydrochemical and isotopic analyses, facilitates understanding of the origin of water constituents and migration of contaminants in the aquatic environment. The presented study attempts to identify contamination sources affecting water quality within the Kozłowa Góra reservoir catchment area (southern Poland). A total of 100 water samples were collected from surface water (the Brynica river, streams, and the reservoir) and groundwater (a Quarternary aquifer) in four time periods. During fieldwork, the physicochemical parameters were measured (temperature, pH, electrical conductivity, redox potential, and dissolved oxygen). The chemical analysis included the determination of major ions (HCO3−, SO42−, Cl−, Ca2+, Mg2+, Na+, and K+), nutrients (NO3−, NO2−, NH4+, and PO43−), and total organic carbon. The study was complemented by isotopic analysis of sulphur and oxygen in sulphate, which enabled a more precise identification of stressors affecting water quality in different parts of the catchment area. Chemical and isotopic results (δ34S = 4.38–13.99‰; δ18O 3.59–13.30‰) revealed that wastewater discharges and agricultural activities have a significant influence on the chemistry of the Brynica River and other streams. At some sampling points, a lower quality of water was manifested by elevated concentrations of NO3− (up to 22.6 mg/L) and several other ions (e.g., up to 114 mg/L for Cl−, up to 51.52 mg/L for NH4+, and 12.5 mg/L for PO43−). The quality of groundwater was deteriorated mainly by infiltration of sewage from leaky septic tanks. The level of groundwater contamination varied depending on the location, as higher concentrations of major ions and values of electrical conductivity were observed in residential areas. The Brynica river, streams, and groundwater recharge the drinking water reservoir, and thus its quality depends on these sources. A dilution of water and the presence of biochemical processes led to a reduction of contaminant concentrations in the Kozłowa Góra reservoir (down to 3.5 mg/L for NO3−, 32 mg/L for Cl−, 0.21 mg/L for NH4+, and &lt;0.05 mg/L for PO43−) compared to water in the river and streams supplying the reservoir. The study revealed the role of wastewater discharge and agricultural activities in the evolution of surface water chemistry. The results will be used in further research on the origin and migration of other substances in water, including microcontaminants.

Surface Water Quality Assessment and Contamination Source Identification Using Multivariate Statistical Techniques: A Case Study of the Nanxi River in the Taihu Watershed, China

Understanding the spatiotemporal patterns of water quality is crucial because it provides essential information for water pollution control. The spatiotemporal variations in water quality for the Nanxi River in the Taihu watershed of China were evaluated by a water quality index (WQI) and multivariate statistical techniques; additionally, the potential sources of contamination were identified. The data set included 22 water quality parameters collected during the monitoring period from 2015 to 2020 for 14 monitoring stations. WQI assessment revealed that approximately 85% of monitoring stations were classified as “medium-low” water quality, and most showed continuous improvement in water quality. Cluster analysis divided the 14 monitoring stations into three clusters (low contamination, medium contamination and high contamination). Discriminant analysis identified pH, petroleum, volatile phenol, chemical oxygen demand, total phosphorus, F, S, fecal coliform, SO4, Cl, NO3-N, total hardness, NO2-N and NH3 as important parameters affecting spatial variations. Factor analysis identified four potential contamination source types: nutrient, organics, feces and oil. This study demonstrated the usefulness of multivariate statistical techniques in assessing large data sets, identifying contamination source types, and better understanding spatiotemporal variations in water quality to restore and protect water resources.

Entity aware sequence to sequence learning using LSTMs for estimation of groundwater contamination release history and transport parameters

Groundwater contaminant sources identification and parameter estimation using the simulation–optimization (S/O) approach require numerous runs of the computationally expensive simulation model through the optimization algorithm. The computational cost can be effectively reduced by using a surrogate model which can accurately approximate the simulation model. With the advent of deep learning, Long Short-Term Memory (LSTM) networks, which are suitable to learn sequential data, are being increasingly applied to regression problems involving time dependencies. However, for the simultaneous contaminant source identification and parameter estimation problem, the surrogate model requires to establish a relationship between release histories at the source locations to concentration measurements at observation points subject to given values of aquifer parameters. In this study, a novel deep neural network framework Entity Aware Sequence to sequence learning using Long Short-Term Memory (EAS-LSTM) is proposed as a surrogate model which takes both sequential i.e., release histories at the source locations at different stress periods and static variables i.e., transport parameters as inputs to predict breakthrough curves (BTCs) at observation points. The proposed surrogate model is applied to a heterogeneous field scale aquifer with 4 zones. The Mean Squared Error (MSE) using EAS-LSTM is 0.0033 ppm2 which is significantly better than that of Kriging and Support Vector Regression (SVR) which are 0.048 ppm2 and 1.302 ppm2 respectively. Comparison of EAS-LSTM model performance with Kriging and SVR based models demonstrates its higher accuracy. Further, the optimization algorithms for inverse modelling, the performances of Multiverse Optimizer (MVO), Grey wolf optimization (GWO) and Particle swarm optimization (PSO) are investigated. It is observed that the combination of EAS-LSTM and MVO provides better results in comparison to other surrogate simulation optimization (SSO) models.

Joint identification of contaminant source characteristics and hydraulic conductivity in a tide-influenced coastal aquifer

Coastal aquifers are a vital water source for the more than one billion people living in coastal regions around the globe. Due to the intensity of economic activities and density of population, these aquifers are highly susceptible not only to seawater intrusion, but also to anthropogenic contamination, which may contaminate the aquifer and submarine groundwater discharge. Identification and localization of contaminant source characteristics are needed to reduce contamination. The techniques of contaminant source identification are based on numerical models that require the knowledge of the hydrodynamic properties of aquifers. Thus, the challenging topic of contaminant source and aquifer characterization (CSAC) is widely developed in the literature. However, most of the existing studies are concerned with inland aquifers with relatively uniform groundwater flow. Coastal aquifers are influenced by density-driven seawater intrusion, tidal forces, and water injection and abstraction wells. These phenomena create complex flow and transport patterns, which render the CSAC especially challenging and may explain why CSAC has never been addressed in coastal settings. The presented study aims to provide an efficient methodology for the simultaneous identification of contaminant source characteristics and aquifer hydraulic conductivity in coastal aquifers. For this purpose, the study employs numerical modeling of density-dependent flow and multiple-species solute transport, to develop trained and validated artificial neural network metamodels, and then employs these metamodels in a version of the ensemble Kalman filter (EnKF) termed the ‘constrained restart dual EnKF (CRD-EnKF)’ algorithm. We show that this variant of the EnKF can be successfully applied to CSAC in the complex setting of coastal aquifers. Furthermore, the study analyzes the influence of common issues in CSAC monitoring, such as the effect of non-ideal monitoring network distributions, measurement errors, and multi-level vs. single level monitoring wells.

Differential Organic Contaminant Ionization Source Detection and Identification in Environmental Waters by Nontargeted Analysis.

The development of nontargeted analysis (NTA) methods to assess environmental contaminants of emerging concern, which are not commonly monitored, is paramount, especially when no previous knowledge on the identity of the pollution source is available. We compared complementary ionization techniques, namely electrospray ionization (ESI) and atmospheric pressure chemical ionization (APCI), in the detection and identification of organic contaminants in tap and surface waters from South Florida. Furthermore, the performance of a simple rationalized NTA method was assessed by analyzing 10 complex mixtures as part of the US Environmental Protection Agency's Non-targeted Analysis Collaborative Trial interlaboratory study, where limitations of the NTA approach have been identified (e.g., number of employed databases, false positives). Different water bodies displayed unique chemical features that can be used as chemical fingerprints for source tracking and discrimination. The APCI technique detected at least threefold as many chemical features as ESI in environmental water samples, corroborating the fact that APCI is more energetic and can ionize certain classes of compounds that are traditionally difficult to ionize by liquid chromatography-mass spectrometry. Kendrick mass defect plots and Van Krevelen diagrams were applied to elucidate unique patterns and theoretical chemical space regions of anthropogenic organic compounds belonging to homologous series or similar classes covered by ESI and APCI. Overall, APCI and ESI were established as complementary, expanding the detected NTA chemical space which would otherwise be underestimated by a single ionization source operated in a single polarity setting. Environ Toxicol Chem 2022;41:1154-1164. © 2021 SETAC.

Transport-based source tracking of contaminants in a karst aquifer: Model implementation, proof of concept, and application to event-based field data

Identification and location of contamination sources is crucial for water resource protection — especially in karst aquifers which provide 25% of the world´s population with water but are highly vulnerable to contamination. Transport-based source tracking is proposed and verified here as a complementary approach to microbial and chemical source tracking in karst aquifers for identifying and locating such sources of contamination and for avoiding ambiguities that might arise from using one method alone. The transport distance is inversely modelled from contaminant breakthrough curves (BTC), based on analytical solutions of the 1D two-region non-equilibrium advection dispersion equation using GNU Octave. Besides the BTC, the model requires reliable estimates of transport velocity and input time. The model is shown to be robust, allows scripted based, automated 2D sensitivity analyses (interplay of two parameters), and can be favourable when distributed numerical models are inappropriate due to insufficient data. Sensitivity analyses illustrate that the model is highly sensitive to the input time, the flow velocity, and the fraction of the mobile fluid region. A conclusive verification approach was performed by applying the method to synthetic data, tracer tests, and event-based field data. Transport distances were correctly modelled for a set of artificial tracer tests using a discharge-velocity relationship that could be established for the respective karst catchment. For the first time such an approach was shown to be applicable to estimate the maximum distance to the contamination source for coliform bacteria in karst spring water combined with microbial source tracking. However, prediction intervals for the transport distance can be large even in well-studied karst catchments mainly related to uncertainties in the flow velocity and the input time. Using a maximum transport distance is proposed to account for less permeable, “slower” pathways. In general, transport-based source tracking might be used wherever transport can be described by the 1D two-region non-equilibrium model, e.g. rivers and fractured or porous aquifers.

Microbiome-based source identification of microbial contamination in nebulizers used by inpatients

Nebulizers are essential for the delivery of aerosolized medication for respiratory patients in hospital. Microbial contamination of nebulizers increases the risk of healthcare-associated infections, presenting the critical need to identify sources of contamination in order to develop effective infection prevention and control practices in hospitals. Using an innovative microbiome-based cultivation-independent microbial source identification technique, the hospital indoor environment was identified as a significant source contributing to microbial contaminants in nebulizers, providing important information to develop strategies for targeted decontamination and enhance the effectiveness of infection prevention and control practices.

Non-point contaminant source identification in an aquifer using the ensemble smoother with multiple data assimilation

Proper identification of groundwater contaminant sources is vital to assess groundwater contamination. However, the majority of previous studies focuses on point source identification; only a few works have been conducted for non-point source parameter identification. Here, we employ the ensemble smoother with multiple data assimilation (ES-MDA) to simultaneously identify the spatial architecture of non-point contaminant sources and the related release information. Three different shapes of non-point contaminant sources are considered, an ellipse, a circle, and an irregular shape. We test the applicability of the ES-MDA for the simultaneous identification using three scenarios in a synthetic confined aquifer by assimilating concentration observations from all-time steps multiple times. The results demonstrate that the ES-MDA is capable to accurately identify both regular and irregular non-point contaminant source information; the accuracy of the identification can be improved by increasing the number of iterations.

Smart water grid technology based on deep learning: a review

In recent years, the development of deep learning technology has made breakthroughs in computer vision, natural language processing and other fields. The Smart Water Grid (SWG) technology based on deep learning has also been a hot area of research in recent years. It has achieved better performance in the related detection and prediction of urban pipe networks. Therefore, this survey paper presents an extensive review of the application of deep learning to several different issues related to the SWG. This paper emphasises feasibility studies and summarises the state-of-the-art development in this field from a technical point of view, which consists of pipeline leakage and burst detection, contamination source identification and water demand forecasting. Furthermore, this paper also proposes challenges and future directions in these key research areas, demonstrating that deep learning-based SWG technology is still an emerging and encouraging research field.

Quantitative Identification of Groundwater Contamination Sources by Combining Isotope Tracer Technique with Pmf Model in an Arid Area of Northwestern China

Quantitative Identification of Groundwater Contamination Sources by Combining Isotope Tracer Technique with Pmf Model in an Arid Area of Northwestern China