Forecasts of maximum and minimum air temperatures are essential to mitigate the damage of extreme weather events such as heat waves and tropical nights. The Numerical Weather Prediction (NWP) model has been widely used for forecasting air temperature, but generally it has a systematic bias due to its coarse grid resolution and lack of parametrizations. This study used random forest (RF), support vector regression (SVR), artificial neural network (ANN) and a multi‐model ensemble (MME) to correct the Local Data Assimilation and Prediction System (LDAPS; a local NWP model over Korea) model outputs of next‐day maximum and minimum air temperatures ( and ) in Seoul, South Korea. A total of 14 LDAPS model forecast data, the daily maximum and minimum air temperatures of in‐situ observations, and five auxiliary data were used as input variables. The results showed that the LDAPS model had an R² of 0.69, a bias of −0.85 °C and an RMSE of 2.08 °C for forecast, whereas the proposed models resulted in the improvement with R² from 0.75 to 0.78, bias from −0.16 to −0.07 °C and RMSE from 1.55 to 1.66 °C by hindcast validation. For forecasting , the LDAPS model had an R² of 0.77, a bias of 0.51 °C and an RMSE of 1.43 °C by hindcast, while the bias correction models showed R² values ranging from 0.86 to 0.87, biases from −0.03 to 0.03 °C, and RMSEs from 0.98 to 1.02 °C. The MME model had better generalization performance than the three single machine learning models by hindcast validation and leave‐one‐station‐out cross‐validation.

For a long time, researchers have tried to find a way to analyze tropical cyclone (TC) intensity in real-time. Since there is no standardized method for estimating TC intensity and the most widely used method is a manual algorithm using satellite-based cloud images, there is a bias that varies depending on the TC center and shape. In this study, we adopted convolutional neural networks (CNNs) which are part of a state-of-art approach that analyzes image patterns to estimate TC intensity by mimicking human cloud pattern recognition. Both two dimensional-CNN (2D-CNN) and three-dimensional-CNN (3D-CNN) were used to analyze the relationship between multi-spectral geostationary satellite images and TC intensity. Our best-optimized model produced a root mean squared error (RMSE) of 8.32 kts, resulting in better performance (~35%) than the existing model using the CNN-based approach with a single channel image. Moreover, we analyzed the characteristics of multi-spectral satellite-based TC images according to intensity using a heat map, which is one of the visualization means of CNNs. It shows that the stronger the intensity of the TC, the greater the influence of the TC center in the lower atmosphere. This is consistent with the results from the existing TC initialization method with numerical simulations based on dynamical TC models. Our study suggests the possibility that a deep learning approach can be used to interpret the behavior characteristics of TCs.

In the Northwestern Pacific, the meridionally propagating Rossby waves, known as the Pacific‐Japan (PJ) pattern, is the dominant teleconnection pattern and is considered as a source of heatwaves in East Asia. In this study, the circulation and thermodynamic characteristics of these patterns were investigated based on daily timescale to evaluate their relationship with the likelihood of heatwaves in Korea and Japan. The investigations reveal that stations in Korea and Japan record approximately 90% increase in extremely hot days (T_max > 35°C) during the positive PJ pattern events. According to thermodynamic budget, horizontal heat advection is a key factor for the observed near‐surface warming during the positive PJ. The circulation pattern during the positive PJ largely explains the enhanced warm advection and physical heating due to the increased insolation and adiabatic heating are secondary factors for near‐surface warming. This phenomenon is robustly observed regardless of the definition.

In this study, the regional climate of the Korean Peninsula is dynamically downscaled using a high‐resolution regional climate model forced by two representative concentration pathway scenarios of Hadley Centre Global Environmental Model version 2‐Atmosphere and Ocean (HadGEM2‐AO) using multiple regional climate models. Changes in extreme precipitation indices are investigated. Through the evaluation of the present climate, a multi‐model ensemble reasonably reproduces the long‐term climatology of extreme precipitation indices over South Korea despite some systematic errors. Both mean and extreme precipitation intensities for 80 years in the future (2021–2100) increase compared to those of the present. However, the increasing rates of indices related to precipitation intensities are different according to sub‐period, season, and emission scenarios. Mean and extreme precipitation intensities of the future climate increase during the summer when most extreme precipitation events occur over the Korean Peninsula. Also, abnormal extreme precipitation can increase during future summers due to increasing variances of indices related to extreme precipitation intensity. Increasing extreme summer precipitation over South Korea is proportional to the increases in convective precipitation compared to non‐convective precipitation. This indicates that future changes in summer precipitation, with regard to intensity and frequency, over South Korea, among representative concentration pathway scenarios, are more related to a change in convective instability rather than synoptic condition.