• The Journal of Engineering Geology
• /
• v.23 no.2
• /
• pp.137-147
• /
• 2013

For the effective management of groundwater resources, it is necessary to predict groundwater level fluctuations in response to rainfall events. In the present study, time series models using artificial neural networks (ANNs) and support vector machines (SVMs) have been developed and applied to groundwater level data from the Gasan, Shingwang, and Cheongseong stations of the National Groundwater Monitoring Network. We designed four types of model according to input structure and compared their performances. The results show that the rainfall input model is not effective, especially for the prediction of groundwater recession behavior; however, the rainfall-groundwater input model is effective for the entire prediction stage, yielding a high model accuracy. Recursive prediction models were also effective, yielding correlation coefficients of 0.75-0.95 with observed values. The prediction errors were highest for Shingwang station, where the cross-correlation coefficient is lowest among the stations. Overall, the model performance of SVM models was slightly higher than that of ANN models for all cases. Assessment of the model parameter uncertainty of the recursive prediction models, using the ratio of errors in the validation stage to that in the calibration stage, showed that the range of the ratio is much narrower for the SVM models than for the ANN models, which implies that the SVM models are more stable and effective for the present case studies.

• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.1021-1029
• /
• 2018

A primary objective of this study is to develop a drought forecasting technique based on groundwater which can be exploit for water supply under drought stress. For this purpose, we explored the lagged relationships between regionalized SGI (standardized groundwater level index) and SPI (standardized precipitation index) in view of the drought propagation. A regional prediction model was constructed using a NARX (nonlinear autoregressive exogenous) artificial neural network model which can effectively capture nonlinear relationships with the lagged independent variable. During the training phase, model performance in terms of correlation coefficient was found to be satisfactory with the correlation coefficient over 0.7. Moreover, the model performance was described by root mean squared error (RMSE). It can be concluded that the proposed approach is able to provide a reliable SGI forecasts along with rainfall forecasts provided by the Korea Meteorological Administration.

• Journal of Soil and Groundwater Environment
• /
• v.14 no.5
• /
• pp.41-50
• /
• 2009

Water levels in groundwater monitoring wells of Jeju Island were analyzed using parametric and non-parametric trend analyses. Number of used monitoring wells in the analysis are 94 among totally 106 monitoring wells and the monitoring period is greater than single year, from 2001 to 2009. For the trend analysis, both parametric (linear regression) and nonparametric (Mann-Kendall trend test and Sen's trend test) methods were adopted. Results of the linear regression analysis on daily basis indicated that about 58.5% of the monitoring wells showed a decreasing trend, and analysis using monthly median indicated that about 79.8% showed a decreasing trend. The Mann-Kendall trend test and Sen's trend test with monthly median values in confidence levels of 95% and 99% showed the same analysis results. In confidence level of 95%, 32% were decreased, 3% were increased and the remains showed no trend. However, in confidence level of 99%, 16% were decreased, 2% were increased and the remains showed no trend. The largest decline rates of water levels were detected mainly at the coast of the northwestern and southwestern parts, which is expected to closely related to the increased pumping in the urban area and tourist resort.

• The Journal of Engineering Geology
• /
• v.25 no.1
• /
• pp.21-33
• /
• 2015

This study tests the potential of detecting small-magnitude earthquakes (~M3.0) and their precursors using a long-term groundwater-monitoring database. In groundwater records from April to June 2012, abnormal changes in water level, temperature, and electrical conductivity were identified in the bedrock monitoring wells of the Gimcheon-Jijwa, Gangjin-Seongjeon, and Gongju-Jeongan stations. These anomalies could be attributed to the M3.1 earthquake that occurred in the Youngdeok area on May 30th, although no linear relationship was found between the scale of changes and the distance between each monitoring station and the epicenter, which is attributed in part to the wide screen design of the monitoring wells. Groundwater monitoring networks designed specifically for monitoring earthquake impacts could provide better information on the safety of underground space and on the security of emergency water-resources in earthquake disaster areas.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2002.04a
• /
• pp.351-356
• /
• 2002

Groundwater recharge rate was estimated by applying the groundwater level fluctuation method utilizing Theis (1937) approach with specific yield estimation technique of Shevenell (1996) and the temperature method using observed data from National Groundwater Observation Stations. Results based on analysis of water level observation data of 10 alluvium wells reveal that the recharge rates for 5 wells of Kum river area range 3.7~25.0% and those for 5 wells of Nakdong river area range 3.6~21.7%. Results obtained from the temperature method based on water temperature data indicated that the upward flow resulted from evapotranspiration is dominant for 4 wells of the Kum river area and 5 wells of the Nakdong river area. The other wells showed the downward flow which is related to groundwater recharge in these areas.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2004.04a
• /
• pp.487-491
• /
• 2004

For tile hydrogeological data of the National Groundwater Monitoring Wells(NGMW), a statistical analysis is made to reveal aquifer characteristics of the country. Results of the pumping and recovery test are classified into 4～5 types by the pattern of drawdown and residual drawdown curves. The analysis of aquifer characteristics shows that the hydraulic conductivity of alluvial aquifers is greater than that of fractured-rock aquifers. The hydraulic conductivity of alluvial aquifers slightly increases as the distance to the discharge area decreases. 77.5% of the NGMWs, where the distance to the discharge area is more than 100m, shows the constant head boundary. This result suggests that the fractured and the alluvial aquifers are fairly interconnected, and water can be supplied from one aquifer to tile other where pumping tests are performed. It is analyzed that the wells showing the impermeable boundary are influenced by small scale of aquifers, poor aquifer transmissivities, and impermeable layers.

• Journal of the Korean Geophysical Society
• /
• v.4 no.1
• /
• pp.71-84
• /
• 2001

A study was initiated to investigate whether the groundwaters being discharged into the sea could be used as a possible water resources. This paper presents a preliminary information about the groundwaters being discharged along the shoreline of East Sea. Major discharge sites were selected primarily on the basis of the informaion on surface temperatures of the sea. Hydrogeologic and geographic conditions were also considered in selecting the major discharge sites. The development possibility of the discharging groundwater were estimated roughly, considering populations, industries and social development compatibilities of the selected areas. Groundwater dams and linked usage with surface water were suggested as possible development methods for the groundwaters.. Based on this study, we selected about 60 sites as the major discharge areas and tentatively recommended 6 sites as optimal sites for development of groundwaters being discharged into the sea. However, detailed in-situ hydrogeologic surveys are required prior to the final decision.

• Journal of the Korean GEO-environmental Society
• /
• v.11 no.6
• /
• pp.57-67
• /
• 2010

Specific yield is an essential parameter of the water table fluctuation method for recharge calculation. Specific yield is not easily estimated because of limited availability of aquifer test data and soil samples at National Groundwater Monitoring Stations in South Korea. The linear relationship between rainfall and water level rise was used to estimate the specific yields of aquifer for 34 shallow monitoring wells which were grouped into three clusters. In the case of Cluster-1 and Cluster-2, this method was not applicable because of low cross correlation between rainfall and water level rise and also a long lag time of water level rise to rainfall. However, the specific yields for 19 monitoring wells belonging to Cluster-3, which have relatively high cross correlation and short lag time, within 2 days after rainfall, range from 0.06 to 0.27 with mean value of 0.17. These values are within the general range for sand and gravel sediments and similar to those from aquifer test data. A detailed field survey is required to identify monitoring sites that are not greatly affected by pumping, stream flow, evapotranspiration, or delayed response of water levels to rainfall, because these factors may cause overestimation of specific yield estimates.

• Journal of the Korean GEO-environmental Society
• /
• v.11 no.3
• /
• pp.5-16
• /
• 2010

Groundwater quality monitoring wells, which is over 2,000 in South Korea, were managed to observe groundwater quality since the early 1990s. Groundwater was sampled and analyzed biannually from 781 monitoring wells located in the areas with a high possibility of pollution. The average concentrations of cyanide, mercury, phenols, hexavalent chromium, trichloroethylene, tetrachloroethylen, and 1.1.1-trichloroethane for 12 years' data of detected cases were above the groundwater quality standard, but the average concentrations of the general quality items such as pH, electric conductivity, nitrate-nitrogen, and chloride, are below the standard. To compare a quality trend for each land-use type of the monitoring site, Sen's method is used for four quality items; chloride, nitrate-nitrogen, pH, and electric conductivity. The upward trend for these items is remarkable in urbideareas and industrial complexes and this trend continues still strongly after 2001. The deviation in a trend slopes of monitoring wells becomes bigger in the mid-2000s. In conclusion, trend analysis using existing monitoring data cidebe effective to forecast the future water quality condition and the solid action to protect groundwater quality should be done in advance using a result of trend analysis.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1235-1240
• /
• 2019

It is well known that the ground water level changes rapidly before and after the earthquake, and the variation of ground water level prediction is used to predict the earthquake. In this paper, we predict the ground water level in Miryang City using ANFIS algorithm for earthquake prediction. For this purpose, this paper used precipitation and temperature acquired from National Weather Service and data of underground water level from Rural Groundwater Observation Network of Korea Rural Community Corporation which is installed in Miryang city, Gyeongsangnam-do. We measure the prediction accuracy using RMSE and MAPE calculation methods. As a result of the prediction, the periodic pattern was predicted by natural factors, but the change value of ground water level was changed by other variables such as artificial factors that was not detected. To solve this problem, it is necessary to digitize the ground water level by numerically quantifying artificial variables, and to measure the precipitation and pressure according to the exact location of the observation ball measuring the ground water level.