Evaluation of Dependency Structure for Multivariate Weather Predictors Using Copulas

In the Global South, the effects of climate change have resulted in more frequent and severe weather events such as droughts, floods, and storms, leading to crop failures, food insecurity, and job loss. These effects are expected to increase in intensity in the future, further disadvantaging already marginalized communities and exacerbating existing inequalities. Hence, the need for prevention and adaptation is urgent, but accurate weather forecasting remains challenging, despite advances in machine learning and numerical modeling, due to complex interaction of atmospheric and oceanic variables. This research aims to explore the potential of vine copulas in explaining complex relationships of different weather variables in three African locations. Copulas separate marginal distributions from the dependency structure, offering a flexible way to model dependence between random variables for improved risk assessments and simulations. Vine copulas are based on a variety of bivariate copulas, including Gaussian, Student’s t , Clayton, Gumbel, and Frank copulas, and they are effective in high-dimensional problems and offer a hierarchy of trees to express conditional dependence. In addition, we propose how this framework can be applied within the subseasonal forecasting models to enhance the prediction of different weather events or variables.