Wetlands play a vital role in hydrologic and ecologic communities. Since there are few studies conducted for wetland water level prediction due to the unavailability of data, this study developed a water level prediction model using various machine learning models such as artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machine (SVM). The Upo wetland, which is the largest inland wetland in South Korea, was selected as the study area. The daily water level gauge data from 2009 to 2015 were used as dependent variables, while the meteorological data and upstream water level gauge data were used as independent variables. Predictive performance evaluation using RF as the final model revealed 0.96 value for correlation coefficient (CC), 0.92 for Nash–Sutcliffe efficiency (NSE), 0.09 for root mean square error (RMSE), and 0.19 for persistence index (PI). The results indicate that the water level of the Upo wetland was well predicted, showing superior results compared to that of the ANN, which was used in a previous study. The results intend to provide basic data for development of a wetland management method, using water levels of previously ungauged areas.

Rainfall data is frequently used as input and analysis data in the field of hydrology. To obtain adequate rainfall data, there should be a rain gauge network that can cover the relevant region. Therefore, it is necessary to analyze and evaluate the adequacy of rain gauge networks. Currently, a complex network analysis is frequently used in network analysis and in the hydrology field, Pearson correlation is used as strength of link in constructing networks. However, Pearson correlation is used for analyzing the linear relationship of data. Therefore, it is now suitable for nonlinear hydrological data (such as rainfall and runoff). Thus, a possible solution to this problem is to apply mutual information that can consider nonlinearity of data. The present study used a method of statistical analysis known as the Brock–Dechert–Scheinkman (BDS) statistics to test the nonlinearity of rainfall data from 55 Automated Synoptic Observing System (ASOS) rain gauge stations in South Korea. Analysis results indicated that all rain gauge stations showed nonlinearity in the data. Complex networks of these rain gauge stations were constructed by applying Pearson correlation and mutual information. Then, they were compared by computing their centrality values. Comparing the centrality rankings according to different thresholds for correlation showed that the network based on mutual information yielded consistent results in the rankings, whereas the network, which based on Pearson correlation exhibited much variability in the results. Thus, it was found that using mutual information is appropriate when constructing a complex network utilizing rainfall data with nonlinear characteristics.

Climate change and fast urbanization increased rainfall intensity and runoff discharge. These changes lead to the growing possibility of flood damages. In South Korea, a government established the “Comprehensive Flood Prevention Plan (CFPP)” for each of river basin against flood. The plan is based on the combination of structural measures selected by experienced hydrologists. However, it lacks clear criteria. To solving this problem, this study classifies the structural measures and suggests a combination method, which use relationships between measures, to ensure the objectivity of the process in identifying proper measures. For Anyangcheon river basin, two plans are provided; the first is developed by the study, and the other is by the CFPP. Comparing the two plans, the results show that the combination, selected by proposed method in this study, is economically more feasible compared to CFPP. Therefore, this study expected be useful when selecting and combining structural measures for formulating river basin flood prevention plans.

The aim of this study is to evaluate the filtering techniques which can remove the noise involved in the time series. We used the radar rainfall series for evaluating the noise reduction capabilities of LF and KF. In this case, it was difficult to distinguish which filtering technique is better way for noise reduction when the typical statistics such as correlation coefficient and standard error were used. However, when the attractor and the BDS statistic were used for evaluating LF and KF, we could clearly identify that KF is better than LF. In this study, we have shown that the attractor and the BDS statistic can be applied for investigating the characteristics of the noisy series such as noise added chaotic series and radar rainfall.

Recently, the frequency of extreme rainfall event has increased due to the climate change and the impermeable area in an urban watershed has also increased due to the rapid urbanization. Therefore, the flood risk is increasing and we ought to prepare countermeasures for flood damage reduction. For the determination of appropriate measures or alternatives, firstly, this study estimated the frequency based rainfall considering the climate change according to the each target period (reference: 1971∼2010, Target period I: 2011∼2040, Target period II: 2041∼2070, Target period III: 2071∼2100). Then, estimation of expected flood damage in Seom River Basin using MD-FDA. As a result, Minimum and maximum of estimation flood damage are 0.11% and 1.19% when using RCP 4.5 scenario. Also minimum and maximum of estimation flood damage are 0.36% and 1.69% when using RCP 8.5 scenario. Therefore, we may need prepare structural and nonstructural measures for minimizing the future flood damage by predicting the flood damage caused by the climate change.