Data-driven rainfall prediction at a regional scale: a case study with Ghana

TL;DR

This study develops and interprets machine learning models for 24-hour rainfall prediction in Ghana, demonstrating comparable or better performance than traditional models and highlighting the importance of meteorological variables.

Contribution

The paper introduces a novel interpretability methodology for CNN-based rainfall prediction models and shows that data-driven models can outperform or complement existing NWP forecasts in Ghana.

Findings

The 12h lead-time CNN model matches or exceeds ECMWF forecast performance.

Combining CNN models with classical NWP improves accuracy.

Interpretable insights into meteorological factors influencing rainfall.

Abstract

With a warming planet, tropical regions are expected to experience the brunt of climate change, with more intense and more volatile rainfall events. Currently, state-of-the-art numerical weather prediction (NWP) models are known to struggle to produce skillful rainfall forecasts in tropical regions of Africa. There is thus a pressing need for improved rainfall forecasting in these regions. Over the last decade or so, the increased availability of large-scale meteorological datasets and the development of powerful machine learning models have opened up new opportunities for data-driven weather forecasting. Focusing on Ghana in this study, we use these tools to develop two U-Net convolutional neural network (CNN) models, to predict 24h rainfall at 12h and 30h lead-time. The models were trained using data from the ERA5 reanalysis dataset, and the GPM-IMERG dataset. A special attention was paid to interpretability. We developed a novel statistical methodology that allowed us to probe the relative importance of the meteorological variables input in our model, offering useful insights into the factors that drive precipitation in the Ghana region. Empirically, we found that our 12h lead-time model has performances that match, and in some accounts are better than the 18h lead-time forecasts produced by the ECMWF (as available in the TIGGE dataset). We also found that combining our data-driven model with classical NWP further improves forecast accuracy.