MOTIVATION AND DESCRIPTION

The advantages of AI Machine Learning/Deep Learning (ML/DL) techniques have been seen in a wide range of applications within the numerical weather and climate prediction community. Together with the increase in computing power, AI techniques are valuable tools that can advance the entire workflow to forecast the weather/climate variabilities, which includes : (1) data processing/analysis such as weather/climate data monitoring/analysis and its interpretation, real-time quality control for observational data, guided quality assignment and decision making, (2) data assimilation such as data fusion from different sources, correction of observation error, learn governing differential equations, non-linear bias correction, bias predictors, learn observational operators, define optical properties of hydrometeors and aerosols, (3) model development such as emulating conventional tools to improve efficiency, emulating model components, developing improved parameterization schemes, building better error models, learning the underlying equations of motion, generating tangent linear or adjoint code from machine learning emulators, (4) model output post-processing such as real-time adjustments of forecast products, feature detection, uncertainty quantification, error corrections for seasonal predictions, development of low-complexity models, etc. The KMA-NOAA AI Workshop jointly organized with KMS in the framework of KMA-NOAA collaboration will allow experts and users in the field to contribute directly to sessions that will discuss ML/DL applications that have been already developed in the field, many exciting challenges to overcome with the support of ML/DL techniques, and will shape AI research and development in the context of NOAA and KMA interests in the future. The discussions will focus on (but not limited to) the following topics: