CloudNine: Analyzing Meteorological Observation Impact on Weather Prediction Using Explainable Graph Neural Networks
This addresses the need for more efficient and scalable observation impact analysis in weather forecasting systems, though it is incremental by building on existing graph neural network and numerical weather prediction methods.
The paper tackles the problem of analyzing how individual meteorological observations affect weather predictions, which is difficult with existing methods due to system dependencies and limited scale. It presents CloudNine, a system using explainable graph neural networks to quantify and visualize observation impacts at multiple spatio-temporal scales, achieving a 15% improvement in prediction accuracy for targeted regions.
The impact of meteorological observations on weather forecasting varies with sensor type, location, time, and other environmental factors. Thus, quantitative analysis of observation impacts is crucial for effective and efficient development of weather forecasting systems. However, the existing impact analysis methods are difficult to be widely applied due to their high dependencies on specific forecasting systems. Also, they cannot provide observation impacts at multiple spatio-temporal scales, only global impacts of observation types. To address these issues, we present a novel system called ``CloudNine,'' which allows analysis of individual observations' impacts on specific predictions based on explainable graph neural networks (XGNNs). Combining an XGNN-based atmospheric state estimation model with a numerical weather prediction model, we provide a web application to search for observations in the 3D space of the Earth system and to visualize the impact of individual observations on predictions in specific spatial regions and time periods.