Search

Quantitative precipitation forecasting in numerical weather prediction (NWP) models is contingent upon physicals parameterization schemes. However, uncertainties abound due to limited knowledge of the precipitating processes, leading to degraded forecasting skills. In light of this, our study explores the application of a Swin‐Transformer based deep learning (DL) model as a supplementary tool for enhancing the mapping trajectory between the NWP fundamental variables and the most downstream variable precipitation. Constrained by the observational satellite precipitation product from NOAA CPC Morphing Technique (CMORPH), the DL model serves as the post‐processing tool that can better resolve the precipitation patterns compared to solely based on NWP estimation. Compared to the baseline Weather Research and Forecasting simulation, the DL post‐processing effectively extracts features over meteorological variables, leading to improved precipitation skill scores of 21.7%, 60.5%, and 45.5% for light rain, moderate rain, and heavy rain, respectively, on an hourly basis. We also evaluate two case studies under different driven synoptic conditions and show promising results in estimating heavy precipitation during strong convective precipitation events. Overall, the proposed DL model can provide a vital reference for capturing precipitation‐triggering mechanisms and enhancing precipitation forecasting skills. Additionally, we discuss the sensitivities of the fundamental meteorological variables used in this study, training strategies, and performance limitations. Plain Language Summary: Numerical weather prediction models depend on certain empirical formulations known as parameterizations to estimate precipitation. However, these methods often fall short due to the intricate dynamics of rainfall, which involves numerous small‐scale interactions that these models are unable to fully capture. To counteract these limitations, our study deploys a form of machine learning known as deep learning (DL) to predict precipitation. This DL model utilizes fundamental weather variables derived from NWP models to make its estimations, serving as a remedy for the inherent weaknesses of traditional models caused by the uncertainties in their parameterization schemes. The implementation of our DL model resulted in a significant enhancement in rainfall prediction accuracy, particularly in the case of extreme precipitation events. This suggests that the application of machine learning strategies could be a promising approach to improve the reliability of rainfall forecasts, a crucial element for effective weather prediction and water resource management. Key Points: We employ a transformer based deep learning model to improve the accuracy of precipitation estimation in numerical weather prediction modelsVarious training strategies were implemented to manage the highly skewed precipitation data leading to improvements in heavy rainfall eventsEvaluation conducted with multiple metrics including skill score, quantile and spatial distribution as well as two case studies [ABSTRACT FROM AUTHOR]

Capturing TC intensity change remains a great challenge for most state‐of‐the‐art operational forecasting systems. Recent studies found TC intensity forecasts are sensitive to three‐dimensional ocean dynamics and air‐sea interface processes beneath extreme winds. By performing a series of numerical simulations based on hierarchical atmosphere‐wave‐ocean (AWO) coupling configurations, we showed how atmosphere‐ocean and atmosphere‐sea wave coupling can affect the intensity of super typhoon Mangkhut (2018). The AWO coupled model can simulate TC‐related strong winds, oceanic cold wake, and wind waves with high fidelity. With atmosphere‐ocean (AO) coupling implemented, the simulated maximum surface wind speed is reduced by 7 m s−1 compared to the atmosphere‐only run, due to TC‐induced oceanic cold wakes in the former experiment. In the fully coupled AWO simulations, the wind speed deficit can be completely compensated by the wave‐air coupling effect. Further analyses showed that, in the AWO experiment, two mechanisms contribute to the improvement of TC intensity. First, in the high wind scenario (>28 m s−1), the surface drag coefficient reaches an asymptotic level, assisting extreme wind speed to be maintained within the eyewall. Second, the wind speed distribution is modulated and becomes broader; higher wind within the TC area helps to offset the negative effect due to leveling off of the heat exchange coefficient as wind speed increases. Overall, the simulated TC in the AWO run can extract 8–9% more total heat energy from the ocean to maintain its strength, compared to that from the AO experiment. Key Points: Regional atmosphere‐wave‐ocean (AWO) coupled models have been customized to study the super typhoon Mangkhut (2018)Atmosphere‐ocean (AO) coupling reduces TC's surface maximum wind, but AWO coupling can completely compensate that deficitSurface drag coefficient leveling off and broader wind speed distribution function help to maintain the TC intensity [ABSTRACT FROM AUTHOR]