• Journal of Korea Water Resources Association
• /
• v.57 no.10
• /
• pp.673-686
• /
• 2024

Groundwater is an important water resource used for various purposes along with surface water. Jeju Island relies on groundwater for most of its water use, so predicting and managing groundwater volume is very important for sustainable use of groundwater. In this study, precipitation data from the Baekrokdam Climate Change Observatory was additionally used to accurately predict groundwater levels. We compared and analyzed the improvement in monthly groundwater level prediction performance of the ANN and LSTM models for two observation wells located in the mid-mountainous area of the Pyoseon watershed in Jeju Island. As a result, when Baekrokdam precipitation data was not used, the NSE values of the two artificial intelligence models were over 0.871, showing very high groundwater level prediction performance. The LSTM model showed relatively higher prediction performance at high and low groundwater levels than the ANN model. We found that the prediction performance decreases as the variation characteristics of the groundwater level become more complex. When Baekrokdam precipitation data was additionally used, the NSE values of the two artificial intelligence models were above 0.907, indicating improved prediction performance, and the NSE value was improved by up to 0.036. This means that when additional rainfall in the upstream area is used, the artificial intelligence model can more appropriately interpret the fluctuating characteristics of the groundwater level. In addition, the additional use of Baekrokdam precipitation data further helped improve groundwater level prediction for observation well, where groundwater level prediction is relatively difficult, and artificial intelligence models, which have relatively low groundwater level prediction performance. In particular, when Baekrokdam precipitation data was additionally used for a specific observation well, the groundwater level prediction performance of the ANN model was improved to a level comparable to that of the LSTM model. The methods and results of this study can be useful in future research using artificial intelligence models.

• Journal of the Korean earth science society
• /
• v.21 no.1
• /
• pp.81-92
• /
• 2000

The purpose of this study is to elucidate the characteristic of this study is of attitudinal variation of water quality for nine representative springs in the Halla mountain region. The evolutional processes of the spring water also have been studied. Results of hydrogeochemical analyses show that Gwaneumsa spring is very high in pH. The spring waters from Yungsil, Namguksunwon, Sungpanark Oremok and Gwaneumsa which springs situated lower than 1000m in altitude are relatively high concentrations in chloride, sulphate, nitrate nitrogen and sodium ions, indicating that they are affected by surrounding pollution sources. The concentrations of bicarbonate, sulphate and hydrogen ions in spring waters increase when the precipitation increases, whereas the concentrations of nitrate nitrogen, chloride and calcium ions decrease with increasing amounts of precipitation. The magnesium, sodium and electrical conductivity are nearly independent of the precipitation. The spring waters in the Halla mountain region belong to the groups of sodium or potassium type and bicarbonate type, except the Baegrogdam and Wiseorm spring water.

• Journal of the Korean Society of Groundwater Environment
• /
• v.5 no.2
• /
• pp.66-79
• /
• 1998

This study purposes to elucidate the characteristics of local water quality and the evolutional process of the spring water have been studied with the samples from 55 selected springs, from the coast region to the Baegrogdam, a caldera lake of Halla mountain in Cheju Island. Results of hydrochemical analyses in the 55 spring water show that Gwaneumsa is pollued with high hydrogen concentration, and spring waters from Yusuarmchun, Jangsumul, Dukjisemmul, Sinch'onk'nmul, Youngchunsa, Woonyangchun, Harwontongmul, Dongheamul, Seakdalsengsu, Andukkyekok, Dotimul, Kinmul, Harkangmul and Jungkeummul are polluted by the pollution sources from the surface surrounding ground. Spring waters of Samyang3suwon, Meungbusa, Sernurungmul, Tosanmul, Jungkeummul, Kwakgimul, Aewolharmul, Konemul and Nokgomul are also polluted from the sea water intrusion. The electrical conductivity, pH and the concentration of nitrate nitrogen and bicarbonate increase when the precipitation increases, but the concentration of sodium, chloride and sulphate decrease when the precipitation increases. The concentrations of potassium, magnessium and calcium are nearly independent of the precipitaion. Quality characteristics of spring water show complicated group of spring water through piper's trilinear diagram. The high mountain region consists of groups of sodium or potassium type and bicarbonate type; the middle mountain region consists of groups of sodium or potassium type and no dominant type; the low mountain consists of groups of no dominant type and sulfate or nitrate type; the coast region consists of groups of sodium or potassium type and chloride type or no dominant type. These characteristics indicate that the spring waters are changed from bicarbonate type in the high and middle mountain regions into non-bicarbonate type in the coastal region, as the precipitated waters flow downslope.