•Several advanced data-driven models are adopted for water table level estimations.•Regression preprocessing is used to detrend/deseasonalize water table level data.•Preprocessing boosts efficient ...detection of hydrologically stressed aquifer condition.•Preprocessing strategy improves monitoring and surveilling of groundwater resources.
In this study, several advanced data-driven models are adopted for estimating water table levels in conjunction with a proposed data preprocessing procedure that includes detrending, deseasonalization, normalization, outlier exclusion, and formatting. To verify the proposed strategy, a non-linear auto-regressive exogenous model based on deep neural networks (NARX-DNNs), a long-short term memory (LSTM) model, a gated recurrent unit (GRU) model, and a reference model based on an auto-regressive exogenous (ARX) model are comparatively applied to water table level time series from the Jindo Uisin and Pohang Gibuk monitoring wells (years 2005–2014). To test the developed preprocessing method, estimates with and without the proposed detrending and deseasonalization (DTDS) are compared quantitatively. In the comparative applications, all four models show reasonable prediction accuracies. In addition, it is found that the estimations from the NARX and LSTM models are superior to those of the other models in terms of prediction accuracy, regardless of whether DTDS is adopted. In both data sets, there is water table level depression during 2014 due to drought throughout the entire Korean peninsula. In multiple analyses, stressed aquifer conditions are identified through estimations based on differences between estimates and observations, where the differences are found to be more obvious with DTDS preprocessing. Thus, by using the proposed preprocessing method, hydrologically stressed conditions in an aquifer can be effectively noticed at an earlier stage. The results show that the advanced data-driven models can be more effective when adopted in conjunction with the proposed preprocessing method and successfully utilized for monitoring and management of groundwater resources.
•A method to evaluate hydraulic properties using the groundwater level (GL).•Extraction of informative features of GL conditioning with a precipitation pattern.•The feature extraction was based on a ...conditional variational autoencoder.•The uncertainty due to different precipitation patterns was reduced.•Efficient estimation for the properties of an aquifer.
In this study, a method of aquifer hydrologic property estimation incorporating the deep learning method was developed to improve the estimation efficiency of a process-based model based on groundwater level fluctuation (GLF) patterns. As a reference study, a data-driven method suggested by Jeong et al. (2020) was considered; the uncertainty of the GLF patterns resulting from different yearly patterns of precipitation, which were considered as noise in the previous study, was effectively discarded using the newly proposed method of applying the conditional variational autoencoder (CVAE). The CVAE was used to acquire the specific GLF patterns under certain identical precipitation patterns for all the monitoring stations. The data-driven hydrologic property estimation model was developed to predict two hydrologic parameters (ρ and k) of the process-based model using the generated GLF patterns from the CVAE network as the input variables. The actual GLF and precipitation data that were acquired from nationwide groundwater monitoring stations in South Korea were applied to validate the developed method. It was found that the estimated and target hydrologic properties were highly correlated (correlation coefficients CC: 0.9833 and 0.9589 for ρ and k, respectively), which significantly improved the results when compared to the previous study (CC: 0.7207 and 0.8663 for α/n and k, respectively). Consequently, the developed model can contribute to a more accurate hydrologic property estimation of aquifers. Additionally, it can facilitate efficient groundwater development planning since the manual fitting of the process-based model by an expert is not required.
Leakage of stored CO2 from a designated deep reservoir could contaminate overlying shallow potable aquifers by dissolution of arsenic-bearing minerals. To elucidate CO2 leakage-induced arsenic ...contamination, 2D multispecies reactive transport models were developed and CO2 leakage processes were simulated in the shallow groundwater aquifer. Throughout a series of numerical simulations, it was revealed that the movement of leaked CO2 was primarily governed by local flow fields within the shallow potable aquifer. The induced low-pH plume caused dissolution of aquifer minerals and sequentially increased permeabilities of the aquifer; in particular, the most drastic increase in permeability appeared at the rear margin of CO2 plume where two different types of groundwater mixed. The distribution of total arsenic (∑As) plume was similar to the one for the arsenopyrite dissolution. The breakthrough curve of ∑As monitored at the municipal well was utilized to quantify the human health risk. In addition, sensitivity studies were conducted with different sorption rates of arsenic species, CO2 leakage rates, and horizontal permeability in the aquifer. In conclusion, the human health risk was influenced by the shape of ∑As plume, which was, in turn, affected by the characteristics of CO2 plume behavior such as horizontal permeability and CO2 leakage rate.
In this study, a data-driven response surface method using the results acquired from the numerical simulation is developed to evaluate the potential storage capacity of groundwater due to the ...construction of a groundwater dam. The hydraulic conductivities of alluvium and basement rock, depth and slope of the channel are considered as the natural conditions of the location for groundwater dam construction. In particular, the probability models of the hydraulic conductivities and the various types of geometry of the channel are considered to ensure the reliability of the numerical simulation and the generality of the developed estimation model. As the results of multiple simulations, it can be seen that the hydraulic conductivity of basement rock and the depth of the channel greatly influence to the groundwater storage capacity. In contrast, the slope of the channel along the groundwater flow direction shows a relatively lower impact on the storage capacity. Based on the considered natural conditions and the corresponding numerical simulation results, the storage capacity estimation model is developed applying an artificial neural network as the nonlinear regression model for training. The developed estimation model shows a high correlation coefficient (>0.9) between the simulated and the estimated storage amount. This result indicates the superiority of the developed model in evaluating the storage capacity of the potential location for groundwater dam construction without the numerical simulation. Therefore, a more objective and efficient comparison for the storage capacity between the different potential locations can be possibly made based on the developed estimation model. In line with this, the proposed method can be an effective tool to assess the optimal location of groundwater dam construction across Korea. 본 연구에서는 다양한 지하댐 입지조건에 대한 수치 모사 결과에 인공신경망 기반 반응 표면법을 적용함으로써 지하댐 건설에 따른 지하수 저류 가능량을 객관적으로 비교 및 평가할 수 있는 예측 모델을 구축하였다. 입지조건으로 기반암 및 충적층의 수리전도도, 하도의 깊이, 하도의 지하수 유동 방향으로의 경사가 고려되었다. 다양한 시나리오를 이용한 몬테카를로 기반 수치 모사 결과를 종합한 결과, 암반층 수리전도도 및 하도의 깊이가 지하댐 저유 효율에 가장 큰 영향을 미치는 것을 확인할 수 있었으며, 하도의 지하수 유동 방향으로의 경사도가 가장 미약한 영향력을 가지는 것을 확인할 수 있었다. 이와 같은 수치 모사 결과를 기반으로 설정된 입지조건과 이의 결과를 입력 및 출력으로 하는 인공신경망 기반 예측 모델을 구축하였다. 인공신경망 기반 예측 모델의 성능 평가 결과, 모델을 통해 예측된 저유량과 실제 수치 모사를 통해 산정된 저유량 간의 상관성이 0.9 이상의 높은 수치를 보임을 확인하였다. 따라서, 본 연구를 통해 개발된 비선형 예측 모델이 지하댐 개발 대상 지역에 대한 수치 모사 수행 없이 지하댐 건설에 따른 저유량을 즉각적으로 산정하는 데 효과적으로 활용될 수 있을 것으로 판단된다. 또한, 개발된 예측 모델은 서로 다른 지역의 저유 가능량을 보다 객관적이고 효율적으로 비교하는데 이용될 수 있다. 따라서 개발된 모델은 국내 전 지역에 대하여 지하댐 개발 최적 입지를 선정하기 위한 효율적 도구로 활용될 수 있을 것으로 기대된다.
Groundwater contains naturally occurring radioactive materials (NORMs) through water–rock interactions. Although a recent study found that the NORMs are accumulated into the filters utilized in ...bottled mineral-water facilities, the accumulation mechanism and effects have rarely been studied. This study is, therefore, conducted to determine the mechanism of NORM accumulation in filters during water treatment processes and to provide a first estimate of the level of radiological risk for workers in five bottled-mineral-water facilities. The level of Rn-222 decreased dramatically at the first filters (FF) encountered after passing through water storage tanks, while surface radiation sharply increased. The increase of radioactivity on the FF was mainly caused by the accumulation of short-lived radon progenies through decay processes inside the water tanks. Although the estimated radiological risk was lower under certain circumstances compared to the public dose limit of 1 mSv yr−1, the radiological risk should be properly managed in case of direct and/or close handling of the used filters during filter replacement procedures.
A precise estimation of groundwater fluctuation is studied by considering delayed recharge flux (DRF) and unsaturated zone drainage (UZD). Both DRF and UZD are due to gravitational flow impeded in ...the unsaturated zone, which may nonnegligibly affect groundwater level changes. In the validation, a previous model without the consideration of unsaturated flow is benchmarked. The model is calibrated using multiyear groundwater data, and consistent model parameter statistics are obtained and validated. The estimation capability of the new model is superior to the benchmarked model as indicated by the significantly improved representation of groundwater level with physically interpretable model parameters.
Plain Language Summary
Although there are a few available methods that can be applied for estimating groundwater level based on the precipitation time series, the methods are mostly limited when incorporating unsaturated gravitational flow. The hydraulics of the unsaturated zone is affected significantly by seasonally varying climatic condition (especially in temperate regions); and therefore, the pattern of water table (WT) response is different for different climatic periods. The authors believe that there have been almost no studies that address this issue. The purpose of this study is to develop a mathematical model that is more versatile in representing various water table responses to precipitation. An additional objective of the study is to show that the effect of the unsaturated gravitational flow variable on climatic conditions must be included in water table estimations.
Key Points
A mathematical model of water table fluctuation in response to precipitation considering unsaturated gravitational flow is proposed
The new model effectively represents water table responses due to delayed recharge flux and unsaturated zone drainage
The new model is comparatively validated with an existing model based on actual data, and superior estimation capability is confirmed
In this study, a method has been proposed to improve the performance of hydraulic property estimation model developed by Jeong et al. (2020). In their study, low-dimensional features of the annual ...groundwater level (GWL) fluctuation patterns extracted based on a Denoising autoencoder (DAE) was used to develop a regression model for predicting hydraulic properties of an aquifer. However, low-dimensional features of the DAE are highly dependent on the precipitation pattern even if the GWL is monitored at the same location, causing uncertainty in hydraulic property estimation of the regression model. To solve the above problem, a process for generating the GWL fluctuation pattern for conditioning the precipitation is proposed based on a conditional variational autoencoder (CVAE). The CVAE trains a statistical relationship between GWL fluctuation and precipitation pattern. The actual GWL and precipitation data monitored on a total of 71 monitoring stations over 10 years in South Korea was applied to validate the effect of using CVAE. As a result, the trained CVAE model reasonably generated GWL fluctuation pattern with the conditioning of various precipitation patterns for all the monitoring locations. Based on the trained CVAE model, the low-dimensional features of the GWL fluctuation pattern without interference of different precipitation patterns were extracted for all monitoring stations, and they were compared to the features extracted based on the DAE. Consequently, it can be confirmed that the statistical consistency of the features extracted using CVAE is improved compared to DAE. Thus, we conclude that the proposed method may be useful in extracting a more accurate feature of GWL fluctuation pattern affected solely by hydraulic characteristics of the aquifer, which would be followed by the improved performance of the previously developed regression model. 본 연구에서는 Jeong et al. (2020)의 연구에서 수행된 지하수위 변동 패턴의 저차원 특징추출 과정의 문제점을 분석하고, 이에 대한 개선방안이 제안된다. 해당 연구에서는 Denoising autoencoder (DAE)를 이용해 전국의 연 단위 지하수위 변동 자료로부터 저차원 특징이 추출되며, 추출된 자료를 이용해 대수층의 수리 특성값을 예측하는 회귀 모델이 개발되었다. 그러나 특정 지역의 연도별 강수 패턴이 달라질 경우, 지하수위 변동 패턴 및 저차원 특징 또한 달라지며, 이에 따라 동일 지역임에도 불구하고 저차원 특징으로부터 추정되는 수리 특성값이 다양하게 나타날 수 있다. 이러한 문제를 해결하기 위해, 본 연구에서는 조건부 생성 모델인 Conditional variational autoencoder (CVAE)를 이용하였으며, 전국 71개 지역에서 10년 동안 획득된 지하수위 자료와 강수 자료 간 상관관계가 학습되었다. 학습된 모델을 통해 모든 지역에 대해 동일 강수 조건이 적용될 때의 지하수위 자료가 생성되었으며, 생성된 지하수위 자료로부터 저차원 특징이 추출되었다. CVAE를 이용해 동일 강수 조건으로 생성된 지하수위 자료의 저차원 특징과 기존 DAE를 통해 추출된 저차원 특징이 비교되었으며, 그 결과 CVAE를 이용해 추출된 저차원 특징 간 거리가 저차원 공간상에서 보다 가깝게 분포하는 것이 확인되었다. 따라서 제안된 방법을 이용할 경우 대수층 특성에만 영향을 받는 지역별 지하수위 자료 및 저차원 특징이 효과적으로 추출될 수 있으며, 이를 통해 기존 개발된 회귀 모델의 성능이 개선될 수 있을 것으로 판단된다.
This paper presents two data-driven virtual sensors to estimate the time-series of the probability of high-concentration occurrence of naturally occurring radioactive materials (NORMs; 238U and ...222Rn) in groundwater based on the in-situ groundwater quality monitoring data and geological information. The random forest was applied to estimate the NORM concentration based on the actual in-situ groundwater quality data, rock type, and the aquifer depth. Additionally, this study proposes three data sampling techniques (i.e., under-sampling, synthetic minority over-sampling, and a complex sampling) to improve the model applicability and accuracy. The developed models were validated using the actual data acquired from 201 locations in South Korea. The models for 238U and 222Rn showed estimation accuracies of 85% and 80%, respectively; the models with over-sampling showed better performance. All the results verified the usefulness of the developed models as virtual sensors for providing immediate information on the in-situ presence of NORMs in groundwater.
Display omitted
•Naturally occurring radioactive material (NORMs) in groundwater can be problematic.•Virtual sensor for in-situ estimating the probability of high-concentration of NORMs.•Major geochemical factors for NORMs were evaluated using statistical analyses.•Methods for solving data imbalance problem in training virtual sensor were proposed.•Major factors for the estimation were consistent with the statistical analysis result.
In this study, the impact of clustered groundwater usage facilities and the proper amount of groundwater usage in the Daejeong-Hangyeong watershed of Jeju island were evaluated based on the ...data-driven analysis methods. As the applied data, groundwater level data; the corresponding precipitation data; the groundwater usage amount data (Jeoji, Geumak, Seogwang, and English-education city facilities) were used. The results show that the Geumak usage facility has a large influence centering on the corresponding location; the Seogwang usage facility affects on the downstream area; the English-education usage facility has a great impact around the upstream of the location; the Jeoji usage facility shows an influence around the up- and down-streams of the location. Overall, the influence of operating the clustered groundwater usage facilities in the watershed is prolonged to approximately 5km. Additionally, the appropriate groundwater usage amount to maintain the groundwater base-level was analyzed corresponding to the precipitation. Considering the recent precipitation pattern, there is a need to limit the current amount of groundwater usage to 80%. With increasing the precipitation by 100mm, additional groundwater development of approximately 1,500m3-1,900m3 would be reasonable. All the results of the developed data-driven estimation model can be used as useful information for sustainable groundwater development in the Daejeong-Hangyeong watershed of Jeju island. 본 연구에서는 자료기반 분석 기법을 이용하여 제주 대정-한경 유역의 군집형 지하수 이용 관정의 영향력을 평가하고 지하수 자원을 효율적으로 관리하기 위한 도구를 개발하였다. 분석을 위해 대정-한경 유역 내 총 19개 지하수위 관측공의 지하수위 자료, 총 3개 기상 관측소로부터 측정된 강수량 자료, 및 총 4개의 군집형 지하수 이용 관정(저지, 금악, 서광, 및 영어교육도시)으로부터 획득한 이용량 자료가 이용되었다. 먼저, 각 지하수위 관측공에 대하여 강수량 및 이용량 자료를 입력변수로 하는 자료 기반 지하수위 예측모델을 개발하였다. 이때, 과거의 장기적 변동특성을 효과적으로 학습에 이용하기 위하여 누적 장단기 메모리 모델을 이용하였다. 모든 관측 공에 대하여 지하수위 예측모델을 개발하고, 이용량 입력변수에 대한 섭동 민감도 분석을 수행하여 각 군집형 관정의 공간적 영향력을 분석하였다. 금악 수원은 해당 수원 중심으로 영향이 크고, 서광 수원은 하류 지역을 중심으로 영향이 큰 것으로 나타났으며, 영어교육도시는 수원의 상류 지역 중심, 저지 수원은 수원 상류 및 하류 중심으로 영향이 나타났다. 그리고 유역 내 군집형 수원의 영향력은 대략 5km인 것으로 나타났다. 추가적으로, 학습된 예측모델을 기반으로 군집형 이용 관정의 영향 범위에 포함되는 지하수위 관측공에 대해 강수량 대비 배경 지하수위 회복을 위한 적정 지하수 이용량을 산정하였다. 최근의 강수 패턴을 적용하였을 때, 현재 지하수 이용량을 기존의 80%로 제한할 필요성이 있는 것으로 나타났으며, 강수량이 100mm 증가하였을 때, 대략 1,500 m3에서 1,900 m3의 추가적인 취수가 가능할 것으로 평가되었다. 본 연구를 통해 도출된 대정-한경 유역 지하수 거동특성 평가 결과와 자료기반 분석 도구들은 대정-한경 유역의 지속 가능한 지하수 개발을 위한 유용한 정보로 활용될 수 있을 것으로 판단된다.
PDF
