Prototype-enhanced prediction in graph neural networks for climate applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Keshtmand, Nawid, Fillola, Elena, Clark, Jeffrey Nicholas, Santos-Rodriguez, Raul, Rigby, Matthew
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909591856480256
author Keshtmand, Nawid
Fillola, Elena
Clark, Jeffrey Nicholas
Santos-Rodriguez, Raul
Rigby, Matthew
author_facet Keshtmand, Nawid
Fillola, Elena
Clark, Jeffrey Nicholas
Santos-Rodriguez, Raul
Rigby, Matthew
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prototype-enhanced prediction in graph neural networks for climate applications
Keshtmand, Nawid
Fillola, Elena
Clark, Jeffrey Nicholas
Santos-Rodriguez, Raul
Rigby, Matthew
Machine Learning
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.
title Prototype-enhanced prediction in graph neural networks for climate applications
topic Machine Learning
url https://arxiv.org/abs/2504.17492