Prototype-enhanced prediction in graph neural networks for climate applications
This incremental improvement addresses the need for more accurate and efficient climate applications, such as atmospheric dispersion modeling for greenhouse gas emissions monitoring.
The paper tackles the problem of improving the quality of high-dimensional emulated outputs in data-driven emulators for physics-based simulations by using prototypes as additional inputs, resulting in better performance with up to almost 10% increase in some metrics when prototypes are chosen via data-driven methods.
Data-driven emulators are increasingly being used to learn and emulate physics-based simulations, reducing computational expense and run time. Here, we present a structured way to improve the quality of these high-dimensional emulated outputs, through the use of prototypes: an approximation of the emulator's output passed as an input, which informs the model and leads to better predictions. We demonstrate our approach to emulate atmospheric dispersion, key for greenhouse gas emissions monitoring, by comparing a baseline model to models trained using prototypes as an additional input. The prototype models achieve better performance, even with few prototypes and even if they are chosen at random, but we show that choosing the prototypes through data-driven methods (k-means) can lead to almost 10\% increased performance in some metrics.