Prediction of DO Concentration in Nakdong River Estuary through Case Study Based on Long Short Term Memory Model

In this study, we carried out case study to predict dissolved oxygen (DO) concentration of Nakdong river estuary with LSTM model. we aimed to figure out a optimal model condition and appropriate predictor for prediction in dissolved oxygen concentration with model parameter and predictor as cases. Model parameter case study results showed that Epoch = 300 and Sequence length = 1 showed higher accuracy than other conditions. In predictor case study, it was highest accuracy where DO and Temperature were used as a predictor, it was caused by high correlation between DO concentration and Temperature. From above results, we figured out an appropriate model condition and predictor for prediction in DO concentration of Nakdong river estuary.

Evolution of Depositional Environments in Response to the Holocene Sea-Level Change in the Lower Delta Plain of Nakdong River Delta, Korea

The Nakdong River delta, located in southeastern Korea, preserves thick and wide sediments, which are suitable for the high-resolution study of the evolution of depositional environments in the lower delta plain area. This study traces the Holocene evolution of the Nakdong River delta using deep drill core (ND-3; 46.60 m thick) sediments from the present delta plain. Sedimentary units of the sediments were classified based on grain size compositions and sedimentary structures: (A) alluvial zone, (B) estuarine zone, (C) shallow marine, (D) prodelta, (E) delta front, and (F) delta plain. The weathered sediment, paleosol, was observed at 43.16 m below the surface. There is an unconformity (43.10 m) to separate a Pleistocene sediment layer in the lowermost part differentiating from a Holocene sediment layer in the upper part of the core. The shallow marine sedimentary unit (32.20~23.50 m), in which grain size decreases upward is overlain by the prodelta unit (23.50~15.10 m), which consists of fine-grained sediments and relatively homogeneous sedimentary facies. The boundary between the delta front unit (15.10~8.00 m) and the delta plain unit (8.00~0.00 m) appears to lie at 8.0 m, and the variation in grain size is different; coarsening upward in the delta front unit and fining upward in the delta front unit, respectively. These sediments are characterized by a lot of sand–mud couplets and mica flakes aligned along with cross-stratification, which may be deposited in relatively high-energy environments. Until 13 cal ka BP, the sea level was 70 m below the present level and the drilling site might be located onshore. At 10 cal ka BP, the sea level was located 50 m below the present level and the drilling site might be moved to an estuarine environment. From 8 to 6 cal ka BP, a transgression phase occurred as a result of coastline invasion by the rapid rise of the sea level. Thus, the drilling site was drowned in a shallow marine environment. After 6 cal ka BP, the sea level reached the present level, and, since then, progradation might begin to form, primarily by more sediment input. After this period, the progradation phase continues as the sediments have advanced and the delta grows.

Assessment of Water Quality Target Attainment and Influencing Factors Using the Multivariate Log-Linear Model in the Nakdong River Basin, Republic of Korea

Because identifying the factors affecting water quality is challenging, water quality assessment of an individual component based on the arithmetic mean method cannot adequately support management policies. Therefore, in this study, we assessed the water quality target attainment at 24 sites in the Nakdong River Basin by applying multivariate log-linear models to identify factors influencing water quality, including flow and season. The temporal and seasonal water quality trend and flow were also analyzed using the calculated model coefficients. Specifically, weekly data on biological oxygen demand (BOD), total phosphorous (TP), and flow during 2013–2018 were used to investigate the 2018 water quality target attainment level for this river. The significance and suitability of the models were analyzed using the F-test, root mean squared error (RMSE), mean absolute percent error (MAPE), and adjusted R2 values. All 24 models applied in this study showed statistical significance and suitability for the prediction of BOD and TP concentrations. Moreover, flow was identified as the main factor affecting water quality and had a predominant effect on BOD and TP concentrations in tributaries and the main stream, respectively. Furthermore, among the 24 sites, BOD and TP targets were evidently attained at 18 and 17 sites, respectively.