Rainfall forecasts in daily use over East Africa improved by machine learning

TL;DR

This paper introduces cGAN, a high-resolution, real-time ensemble rainfall forecasting system for East Africa that improves prediction accuracy and accessibility for meteorological services with limited resources.

Contribution

The paper presents cGAN, a novel AI-based ensemble rainfall forecast system that offers high spatial resolution and real-time probabilistic correction with low computational requirements.

Findings

cGAN outperforms existing AI models in accuracy.

It provides high-resolution forecasts at low cost.

Suitable for resource-limited meteorological services.

Abstract

Ensemble forecasting has proven over the years to be a vital tool for predicting extreme or only partially predictable weather events. In particular life-threatening weather events. Many National Meteorological Services in East Africa do not have the computing resources to enable them to run their local area models in full ensemble mode over the full period of the 2 week medium range. As a result, weather users in these countries are not being given sufficient information about weather risk that is needed to make reliable decisions about taking preventative action. Consequently, society in many parts of the world is not as resilient to weather events as they could be. In this paper we test the performance of our forecast system, cGAN, which is the only high-resolution (10 km) ensemble rainfall product that does real-time, probabilistic correction of global forecasts for East Africa. Compared to existing state-of-the-art AI models, our system offers higher spatial resolution. It is cheap to train/run and requires no additional post-processing. It is run on laptops and can generate many thousands of ensemble members at little computational cost (compared with physical local area models). It is ideally suited to Meteorological Services with limited computational facilities.