Since predicting rapidly fluctuating water levels is very important in water resource engineering, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) were used to evaluate water-level-prediction accuracy at Hangang Bridge Station in Han River, South Korea, where seasonal fluctuations were large and rapidly changing water levels were observed. The hydrological data input to each model were collected from the Water Resources Management Information System (WAMIS) at the Hangang Bridge Station, and the meteorological data were provided by the Seoul Observatory of the Meteorological Administration. For high-accuracy high-water-level prediction, the correlation between water level and collected hydrological and meteorological data was analyzed and input into the models to determine the priority of the data to be trained. Multivariate input data were created by combining daily flow rate (DFR), daily vapor pressure (DVP), daily dew-point temperature (DDPT), and 1-hour-max precipitation (1HP) data, which are highly correlated with the water level. It was possible to predict improved high water levels through the training of multivariate input data of LSTM and GRU. In the prediction of water-level data with rapid temporal fluctuations in the Hangang Bridge Station, the accuracy of GRU’s predicted water-level data was much better in most multivariate training than that of LSTM. When multivariate training data with a large correlation with the water level were used by the GRU, the prediction results with higher accuracy ($R^2=0.7480–0.8318$; $NSE=0.7524–0.7965$; $MRPE=0.0807–0.0895$) were obtained than those of water-level prediction results by univariate training.

Recently, developing countries have steadily been pushing for the construction of stream-oriented smart cities, breaking away from the existing old-town-centered development in the past. Due to the accelerating effects of climate change along with such urbanization, it is imperative for urban rivers to establish a flood warning system that can predict the amount of high flow rates of accuracy in engineering, compared to using the existing Computational Fluid Dynamics (CFD) models for disaster prevention. In this study, in the case of streams where missing data existed or only small observations were obtained, the variation in flow rates could be predicted with only the appropriate deep learning models, using only limited time series flow data. In addition, the selected deep learning model allowed the minimum number of input learning data to be determined. In this study, the time series flow rates were predicted by applying the deep learning models to the Han River, which is a highly urbanized stream that flows through the capital of Korea, Seoul and has a large seasonal variation in the flow rate. The deep learning models used are Convolution Neural Network (CNN), Simple Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Gated Recurrent Unit (GRU). Sequence lengths for time series runoff data were determined first to assess the accuracy and applicability of the deep learning models. By analyzing the forecast results of the outflow data of the Han River, sequence length for 14 days was appropriate in terms of the predicted accuracy of the model. In addition, the GRU model is effective for deep learning models that use time series data of the region with large fluctuations in flow rates, such as the Han River. Furthermore, through this study, it was possible to propose the minimum number of training data that could provide flood warning system with an effective flood forecasting system although the number of input data such as flow rates secured in new towns developed around rivers was insufficient.

The methods for improving the accuracy of water level prediction were proposed in this study by selecting the Gated Recurrent Unit (GRU) model, which is effective for multivariate learning at the Paldang Bridge station in Han River, South Korea, where the water level fluctuates seasonally. The hydrological data (i.e., water level and flow rate) for Paldang Bridge station were entered into the GRU model; the data were provided by the Water Resources Management Information System (WAMIS), and the meteorological data for Seoul Meteorological Observatory and Yangpyeong Meteorological Observatory were provided through the Korea Meteorological Administration. Correlation analysis was used to select the training data for hydrological and meteorological data. Important input data affecting the daily water level (DWL) were daily flow rate (DFR), daily vapor pressure (DVP), daily dew point temperature (DDPT), and 1 h max precipitation (1HP), and were used as the multivariate learning data for water level prediction. However, the DWL prediction accuracy did not improve even if the meteorological data from a single meteorological observatory far from the DWL prediction point were used as the multivariate learning data. Therefore, in this study, methods for improving the predictive accuracy of DWL through multivariate learning that effectively utilize meteorological data from each meteorological observatory were presented. First, it was a method of arithmetically averaging meteorological data for two meteorological observatories and using it as the multivariate learning data for the GRU model. Second, a method was proposed to use the meteorological data of the two meteorological observatories as multivariate learning data by weighted averaging the distances from each meteorological observatory to the water level prediction point. Therefore, in this study, improved water level prediction results were obtained even if data with some correlation between meteorological data provided by two meteorological observatories located far from the water level prediction point were used.

This study analyzed the elements of previously published stream restoration guidelines by clarifying the definition of stream restoration classified for various purposes. The purpose of this study was to establish a sustainable integrated design framework for stream restoration that supplemented the limited scope of application and the resulting problems. Stream restoration procedures were established using the method of securing water resources applied with the integrated watershed management in order to effectively and feasibly recover the modified stream, to resolve the water shortage problem, and to effectively restore the ecosystem due to climate change. An 11-step stream restoration procedure was established in three phases including the pre-restoration design phase, the restoration design phase, and the detailed design phase. Furthermore, the three stages were classified into hydrologic and hydraulic plan, geomorphic and sediment transport plan, and ecological and environmental plan depending on the direction of stream restoration, and the procedure for stream restoration was proposed to prevent river restoration from being biased toward a specific goal. An integrated design framework for stream restoration could be established by allowing the proposed stream restoration design procedures (e.g., three phases and three plans) and the elements to be carried out using numerical models for an effective design in establishing river restoration plans. Lastly, it was possible to quantify the problems of existing stream restoration by applying this stream restoration framework to the existing river restoration project and guideline report. As a result, the existing stream restoration project could be used as base data that could provide directions to supplement the weaknesses of the existing stream restoration project and provide directions for the new river restoration projects in the future.

Drought flow as the minimum flow rate required for restoration of the Mokgamcheon stream was calculated by the Storm Water Management Model (SWMM) V.5.0. The adequacy of drought flow to guarantee the minimum ecological environment was assessed using suitable low-flows not exceeding the maximum pollution concentration of the ecosystem calculated by Design FLOWs (DFLOW) V.4.1. Fish flows, which provide proper ecological habitat for fish, were calculated using Physical HABitat SIMulation (PHABSIM) V.1.5.2 to provide proper ecological habitat for target fishes such as Carassius auratus and Zacco platypus. The monthly expected instream flows were determined as the largest value between drought flow and fish flow. In most cases, instream flows were determined by drought flows exceeding fish flows that satisfy the condition of species habitat, but in the case of Carassius auratus, drought flows were less than fish flows in April, September, and October. Thus, structural measures for the supply of additional discharge were required. Instead, when natural environment-friendly instream structures, such as stepping stones were used, affordable ecological restoration that met the preferred conditions for discharge and depth of Carassius auratus was possible. The stepping stones were assessed using River2D V.0.95a to measure their effectiveness compared to other structural measures that would be costly and time-consuming to secure shortage of fish flow. Finally, the stability of the habitat was assessed through flood analysis; in case of a flood discharge of 5.2 m³/s obtained from time-series analysis, it was evaluated that the stability of habitats could be reasonable.