Accurate pollutant prediction is essential in fields such as meteorology, meteorological disasters, and climate change studies. In this study, long short-term memory (LSTM) and deep neural network (DNN) models were applied to six pollutants and comprehensive air-quality index (CAI) predictions from 2015 to 2020 in Korea. In addition, we used the network method to find the best data sources that provide factors affecting comprehensive air-quality index behaviors. This study had two steps: (1) predicting the six pollutants, including fine dust (PM₁₀), fine particulate matter (PM_2.5), ozone (O₃), sulfurous acid gas (SO₂), nitrogen dioxide (NO₂), and carbon monoxide (CO) using the LSTM model; (2) forecasting the CAI using the six predicted pollutants in the first step as predictors of DNNs. The predictive ability of each model for the six pollutants and CAI prediction was evaluated by comparing it with the observed air-quality data. This study showed that combining a DNN model with the network method provided a high predictive power, and this combination could be a remarkable strength in CAI prediction. As the need for disaster management increases, it is anticipated that the LSTM and DNN models with the network method have ample potential to track the dynamics of air pollution behaviors.

Hydrological time series have been forecasted using various models. A study employed nonlinear dynamical methods, namely the correlation dimension and dynamic vs. stochastic (DVS) algorithm, to analyze daily flow data characteristics. Analysis using the correlation dimension and DVS algorithm revealed that the daily streamflow observed from the St. Johns River near Cocoa, Florida, USA, exhibited chaotic characteristics, whereas the daily inflow to the Soyanggang Dam reservoir showed stochastic properties. However, the nonlinearity of the flows has not been investigated, and the stochastic models have not been fit for flow modeling and forecasting. Therefore, the present study tests the nonlinearity and fits stochastic models of the flow data. In addition, the forecasting results obtained from the DVS algorithm and neural networks were compared with those from the fitted stochastic models. The forecasting results derived from the DVS algorithm and neural networks demonstrated higher accuracy for daily streamflow than for daily inflow. Furthermore, when applying the AR (1) model to daily flow and ARMA (3, 1) model to daily inflow, the results showed that the chaotic nature of the daily streamflow yielded more accurate forecasts. The findings suggest that the dynamic structure inherent in hydrological time series may influence forecasting performance. Notably, the two flows exhibited nonlinearity based on BDS statistics, indicating that nonlinear time-series models may be more appropriate for analysis.

Regarding existing qualitative evaluations for flood risks, the researcher is to use the food risk map made by the flood risk map made by applying extreme rainfall to national, local, and small rivers. The submerged range is the same regardless of rainfall intensity. Therefore, this study prepares a flood risk map by frequency and conducted IBA (Indicator-Based Approach) flood risk assessment from 2016 to 2020 for metropolitan cities. In addition, by calculating climate change through the future flood risk index, the researcher will analyze this trend with the Mann-Kendall method. This study individually prepares a flood risk map according to rainfall intensity by calculating the design flood discharge by frequency. In this case, not only hazard but also changes in the exposure and vulnerability indexes as the area of the flood risk map changes. In the case of exposure and vulnerability, extracted and calculated flood risk map includes the population and the number of buildings, so the index of the relevant items changes according to the area of the flood risk map. This study conducts a future flood risk assessment using the climate change scenario when flood risks for future metropolitan cities can be analyzed and used to cope with environmental changes. In addition, if there is a trend towards increasing at specific rainfall observatories around metropolitan cities through trend analysis, it can be shown as evidence that the probability of rainfall by future frequency is extensively estimated given these characteristics. Using these results, a local government can make a plan to manage flood risks.

Smart water grid technologies have been widely adopted as a key component of digital transformation in water resource management, where real-time household water consumption data collected from smart water meters serve as fundamental inputs. However, these datasets often contain numerous outliers and missing values due to communication errors, which degrade data reliability and hinder accurate analysis. This study proposes an improved framework for outlier detection and missing data imputation tailored to the characteristics of cumulative household water consumption data. The proposed imputation methods were evaluated against conventional approaches using error metrics, and the results demonstrated significant improvements in accuracy, with RMSE values substantially lower than those of the reference method. In addition, prediction models with varying levels of complexity were explored to examine how improved data quality influences forecasting performance. The results indicate that, although data preprocessing enhances data reliability, prediction performance remains limited due to the inherent variability and stochastic nature of household water consumption data. Prediction models with varying levels of complexity were constructed and evaluated using the corrected datasets. The performance of the models varied depending on dataset characteristics, and no single model consistently outperformed others. Overall, this study highlights the critical role of data quality improvement in smart water management systems and provides practical insights into missing data imputation, while suggesting that further advancements in prediction require additional explanatory variables and more sophisticated modeling approaches.

Drought is a complex natural hazard that develops across different temporal scales and may propagate from meteorological drought to hydrological drought. In addition, the physical characteristics of drought do not necessarily correspond directly to how drought is represented in the news media. This study analyzed meteorological and hydrological drought characteristics at the level of the 17 first-level administrative divisions (provinces) of South Korea and compared them with the frequency of drought-related news articles. The Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI), and Streamflow Drought Index (SDI) were calculated at 1-, 3-, 6-, and 12-month timescales using long-term meteorological and streamflow observations. Drought-related news articles published from 2021 to 2025 were retrieved from BIGKinds and processed using explicit cleaning rules, and regions with relatively high frequencies of drought-related news were identified. The spatial agreement between regions with high drought-news frequency and regions with high drought severity derived from each drought index was then evaluated using the top-10 overlap, the Jaccard index, a threshold-based comparison, rank correlation, and permutation tests, and their temporal correspondence was evaluated using monthly rank correlations. In the spatial comparison, the overlap between the top-10 provinces (at most 7 of 10) did not exceed that expected by chance, and this result did not depend on the ranking threshold, the annual aggregation method, the method of counting articles, or normalization by population. In contrast, the monthly number of drought-related articles increased with the number of provinces under drought conditions, most strongly for the 12-month indices (Spearman ρ = 0.42–0.57), and was significantly correlated with the provincial SPI-12 and SPEI-12 values in 8–11 of the 16 provinces. These exploratory results for 2021–2025 suggest that drought-related news coverage follows the temporal evolution of prolonged drought, but that its distribution among provinces cannot be represented by a single drought index or timescale and is only weakly related to the spatial pattern of physical drought severity. News frequency is therefore better interpreted as an indicator of when drought attracts media attention than of where drought is most severe, and its use as complementary information in drought monitoring requires validation against independent drought-impact data.