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.

Prediction models of heavy rain damage using machine learning based on big data were developed for the Seoul Capital Area in the Republic of Korea. We used data on the occurrence of heavy rain damage from 1994 to 2015 as dependent variables and weather big data as explanatory variables. The model was developed by applying machine learning techniques such as decision trees, bagging, random forests, and boosting. As a result of evaluating the prediction performance of each model, the AUC value of the boosting model using meteorological data from the past 1 to 4 days was the highest at 95.87% and was selected as the final model. By using the prediction model developed in this study to predict the occurrence of heavy rain damage for each administrative region, we can greatly reduce the damage through proactive disaster management.

Accurate runoff prediction is one of the important tasks in various fields such as agriculture, hydrology, and environmental studies. Recently, with massive improvements of computational system and hardware, the deep learning-based approach has recently been applied for more accurate runoff prediction. In this study, the long short-term memory model with sequence-to-sequence structure was applied for hourly runoff predictions from 2015 to 2019 in the Russian River basin, California, USA. The proposed model was used to predict hourly runoff with lead time of 1–6 h using runoff data observed at upstream stations. The model was evaluated in terms of event-based performance using the statistical metrics including root mean square error, Nash-Sutcliffe Efficiency, peak runoff error, and peak time error. The results show that proposed model outperforms support vector machine and conventional long short-term memory models. In addition, the model has the best predictive ability for runoff events, which means that it can be effective for developing short-term flood forecasting and warning systems. The results of this study demonstrate that the deep learning-based approach for hourly runoff forecasting has high predictive power and sequence-to-sequence structure is effective method to improve the prediction results.

Recently, urban areas have experienced frequent, large-scale flooding, a situation that has been aggravated by climate change. This study aims to improve the urban drainage system to facilitate climate change adaptation. A methodology and a series of mitigation strategies are presented to efficiently improve the urban drainage system in light of climate change. In addition, we assess the impact of climate change and predict the scale of potential future flood damage by applying the methodology and mitigation strategies to urban areas. Based on the methodology presented, urban flood prevention measures for Gyeyang-gu (Province), Incheon, Korea, was established. The validity of the proposed alternatives is verified by assessing the economic feasibility of the projects to reduce flood damage. We expect that the methodology presented will aid the decision-making process and assist in the development of reasonable strategies to improve the urban drainage system for adaptation to climate change.

Since its recurrence in 1986, scrub typhus has been occurring annually and it is considered as one of the most prevalent diseases in Korea. Scrub typhus is a 3rd grade nationally notifiable disease that has greatly increased in Korea since 2000. The objective of this study is to construct a disease incidence model for prediction and quantification of the incidences of scrub typhus. Using data from 2001 to 2010, the incidence Artificial Neural Network (ANN) model, which considers the time-lag between scrub typhus and minimum temperature, precipitation and average wind speed based on the Granger causality and spectral analysis, is constructed and tested for 2011 to 2012. Results show reliable simulation of scrub typhus incidences with selected predictors, and indicate that the seasonality in meteorological data should be considered.