In this study, the visibility of South Korea was predicted (VIS_RF) using a random forest (RF) model based on ground observation data from the Automated Synoptic Observing System (ASOS) and air pollutant data from the European Centre for Medium-Range Weather Forecasts (ECMWF) Copernicus Atmosphere Monitoring Service (CAMS) model. Visibility was predicted and evaluated using a training set for the period 2017–2018 and a test set for 2019. VIS_RF results were compared and analyzed using visibility data from the ASOS (VIS_ASOS) and the Unified Model (UM) Local Data Assimilation and Prediction System (LDAPS) (VIS_LDAPS) operated by the Korea Meteorological Administration (KMA). Bias, root mean square error (RMSE), and correlation coefficients (R) for the VIS_ASOS and VIS_LDAPS datasets were 3.67 km, 6.12 km, and 0.36, respectively, compared to 0.14 km, 2.84 km, and 0.81, respectively, for the VIS_ASOS and VIS_RF datasets. Based on these comparisons, the applied RF model offers significantly better predictive performance and more accurate visibility data (VIS_RF) than the currently available VIS_LDAPS outputs. This modeling approach can be implemented by authorities to accurately estimate visibility and thereby reduce accidents, risks to public health, and economic losses, as well as inform on urban development policies and environmental regulations.

Our study analyzed the occurrence frequency and distribution of seedable clouds around the Korean Peninsula in order to better secure water resources. Cloud products from the Communication, Ocean, and Meteorological Satellite (COMS), including cloud fraction, cloud top height, cloud top temperature, cloud phase, cloud top pressure, cloud optical thickness, and rainfall intensity, were used. Daytime hourly data between 0900 and 1800 local standard time (LST) observed from December 2016 to November 2019 was used. Seedable clouds occurring within this period were evaluated based on seasonal cloud phases, occurrence frequency, and cloud characteristics according to land, sea, and cloud type. These clouds exhibited varying average occurrence frequencies in different seasons. Sc (stratocumulus) clouds exhibited the highest occurrence frequency for all seasons, with an average of 63%, followed by Cu (cumulus) at 15%, As (altostratus) at 13%, and Ac (altocumulus) at 6%. We determined that low-level clouds primarily occurred around the Korean Peninsula, and the occurrence frequency of stratiform clouds was highest for water phase seedable clouds, while the occurrence frequency of cumuliform clouds was highest for ice phase seedable clouds. We believe that precipitation enhancement experiments could be suitable for western and eastern seas around the Korean Peninsula as well as for mountainous regions on land.

This study calculated the augmentation of water resources that can be achieved through precipitation enhancement and the ensuing economic benefits by conducting precipitation enhancement experiments using atmospheric aircraft in the catchment areas of 21 multipurpose dams in Korea. The maximum number of precipitation enhancement experiments to be carried out was estimated based on the frequency of occurrence of seedable clouds near each dam, using geostationary satellite data. The maximum quantity of water that can be obtained was calculated considering the mean precipitation enhancement and probability of success, as determined from the results of experiments conducted in South Korea during 2018–2019. The effective area of seeding was assumed 300 km². In addition, the amount of hydroelectric power generation possible was determined from the quantity of water thus calculated. In conclusion, it was established that an approximate increase of 12.89 million m³ (90% confidence interval: 7.83–17.95 million m³) of water, and 4.79 (2.91–6.68) million kWh of electric power generation will be possible through approximately 96 precipitation enhancement operations in a year at the catchment area of Seomjin River (SJ) dam which has a high frequency of occurrence of seedable clouds, a large drainage area, and a high net head. An economic benefit of approximately 1.01 (0.61–1.40) million USD can be anticipated, the benefit/cost ratio being 1.46 (0.89–2.04).

Accurate visibility prediction is imperative in the interests of human and environmental health. However, the existing numerical models for visibility prediction are characterized by low prediction accuracy and high computational cost. Thus, in this study, we predicted visibility using tree-based machine learning algorithms and numerical weather prediction data determined by the local data assimilation and prediction system (LDAPS) of the Korea Meteorological Administration. We then evaluated the accuracy of visibility prediction for Seoul, South Korea, through a comparative analysis using observed visibility from the automated synoptic observing system. The visibility predicted by machine learning algorithm was compared with the visibility predicted by LDAPS. The LDAPS data employed to construct the visibility prediction model were divided into learning, validation, and test sets. The optimal machine learning algorithm for visibility prediction was determined using the learning and validation sets. In this study, the extreme gradient boosting (XGB) algorithm showed the highest accuracy for visibility prediction. Comparative results using the test sets revealed lower prediction error and higher correlation coefficient for visibility predicted by the XGB algorithm (bias: −0.62 km, MAE: 2.04 km, RMSE: 2.94 km, and R: 0.88) than for that predicted by LDAPS (bias: −0.32 km, MAE: 4.66 km, RMSE: 6.48 km, and R: 0.40). Moreover, the mean equitable threat score (ETS) also indicated higher prediction accuracy for visibility predicted by the XGB algorithm (ETS: 0.5–0.6 for visibility ranges) than for that predicted by LDAPS (ETS: 0.1–0.2).