The present work aimed to examine the feasibility of using artificial neural network (ANN) based models to obtain accurate estimates of nitrate loads in river basins, which is an important parameter for water quality management. Both Single ANN (SANN) and Ensemble ANN (EANN) models were used to obtain the load estimations for five river basins in the Midwest United States. These basins included the Cuyahoga, Raisin, Sandusky, Muskingum, and Vermilion basins in Michigan and Ohio. Further, canonical correlation analysis (CCA) was applied to the ANN models to improve the performance. The k-fold cross-validation method was then utilized to evaluate the proposed models based on two statistical indices, namely, the rRMSE and rBAIS, and the estimates were compared for four different k values (k = 3, 5, 7, and 10). According to the results, the EANN model seemed to produce better load estimations than the SANN model, and the CCA based EANN model tended to produce the best estimates among all of the proposed models in this study. The box plot data for the rRMSE index were also investigated, and the plot results indicated that increasing values of k tended to generate better estimates. Thus, the use of k = 10 is recommended for load estimations since this value was associated with better performances and less biased estimates.

In aquatic ecosystems, flow is one of the most essential elements of aquatic species. It is necessary to explore the correlation with ecological indices for the management guidelines of aquatic ecosystems using flow because aquatic ecosystem data are limited. This study calculated the flow metrics using the flow and analyzed the correlation between the flow metrics and the ecological index. This study attempted to understand the correlation between the ecologic index and flow metrics. Flow metrics were quantified flow in various ways, depending on the size, frequency, and design of the flow. The characteristics of flow metrics were identified and the correlation with the ecological index was studied. The Pearson correlation coefficient values for 22 watersheds were compared using the flow data from 2008 to 2015 and the ecological index data from the BMI. In watersheds with high imperviousness, the Pearson correlation coefficient was negative, which indicated that the correlation in this study provides basic data for the quantitative evaluation of the river ecosystem by identifying the relationship between imperviousness and BMI. As a result, the highest Pearson correlation coefficient values of flow metrics were related to the flow coefficient of variation (MACV13-16; MHCV; MLCV).

The long short-term memory (LSTM) model has been widely used for a broad range of applications entailing the estimation of variables in different fields to improve water quality management in rivers. The main objectives of this study are (1) to develop a novel LSTM-based model for the estimation of nitrate-N loads, which adversely affect water resources, and (2) to evaluate the performance of the model by comparing it with that of Monte Carlo sub-sampling and the weighted regressions on time discharge and season (WRTDS) model. We evaluated the model performance using various numbers of hidden layers, ranging from one to four, in the LSTM model to determine the appropriate number of hidden layers; furthermore, we applied the sampling frequencies of 6, 12, and 24 to assess their impact. Seven polluted river basins in the United States were used for analysis, and the relative root mean squared error (rRMSE) and the mean percentage error (MPE) metrics were applied for the validation of the model estimates. The proposed model achieved accurate nitrate-N load estimates using three to four hidden layers, and improved model performance was observed when the sampling frequency was increased. The differences among the results obtained using the LSTM model were examined based on a binning technique via a log-log plot of nitrate-N concentration against discharge. The binning analysis showed that the slope obtained from the average rates of discharge and low discharge values apparently influenced the estimates. Furthermore, box plot analyses of the statistical indices such as rRMSE and MPE demonstrate that the LSTM model seems to exhibit better performance than the WRTDS model. The results of the examination demonstrate that the LSTM model may be a good alternative with regard to estimating nitrate-N loads for the control of water quality constituents.

Low-flow quantiles at ungauged locations are generally estimated based on hydrological methods, such as the drainage area ratio and frequency analysis methods. In practice, the drainage area ratio approach is a popular but simple linear model. When hydrologically nonlinear characteristics govern the runoff process, the linear approach leads to significant bias. This study was conducted to develop an improved nonlinear approach using a canonical correlation analysis and neural network (CCA-NN)-based regional frequency analysis (RFA) for low-flow estimation. The jackknife technique was utilized to validate the two methods. The approaches were applied to 33 river basins in South Korea. In this work, we focused on two-year and five-year return periods. For the two-year return period, the BIAS, RMSE, and R² were 0.013, 0.511, and 0.408 with the RFA, respectively, and −0.042, 1.042, and 0.114 with the drainage area ratio method, respectively; whereas for the five-year return period, the respective indices were −0.018, 0.316, and 0.573 with RFA, respectively, and 0.166, 0.536, and 0.044 with the drainage area ratio method, respectively. RFA outperformed the drainage area ratio method based on its high prediction accuracy and ability to avoid the bias problem. This study indicates that machine learning-based nonlinear techniques have the potential for use in estimating reliable low-flows at ungauged sites.

This study examines whether the fluvial flood defense system of Korea is appropriate for risk reduction. Using spatial socioeconomic data and remote sensing, we estimated the potential economic damage that can be caused by the flooding of local streams and rivers along the Nakdong River (the longest river in Korea). For the analysis, a river risk map including return periods (50, 80, 100, and 200 years) and spatial inventories (residential, agricultural, industrial assets, and human lives) was employed to determine flood-prone areas and assess the damage within the inundation areas. A quantitative flood analysis was conducted using an object-based method to estimate the expected annual damage. We then compared the estimated damage for each tributary within the designed return periods and found no correlation. Numerous tributaries with low-defense targets were considered high-risk, while those with high-defense targets were assessed as low-risk. The dataset used in this study covered four damage categories. Among them, flood damage to residential assets appeared to have the highest value, whereas flood damage to industrial assets had the lowest value. The results demonstrate that the Korean government needs to tailor its flood defense policy based on quantitative risk assessments to effectively manage flood risks, especially given the increasing risk of climate change.