Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fahim, Md Muhtasim Munif, Yesmin, Soyda Humyra, Islam, Saiful, Faruque, Md. Palash Bin, Salam, Md. A., Uddin, Md. Mahfuz, Islam, Samiul, Ahmed, Tofayel, Binyamin, Md., Karim, Md. Rezaul
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866912908945915904
author	Fahim, Md Muhtasim Munif Yesmin, Soyda Humyra Islam, Saiful Faruque, Md. Palash Bin Salam, Md. A. Uddin, Md. Mahfuz Islam, Samiul Ahmed, Tofayel Binyamin, Md. Karim, Md. Rezaul
author_facet	Fahim, Md Muhtasim Munif Yesmin, Soyda Humyra Islam, Saiful Faruque, Md. Palash Bin Salam, Md. A. Uddin, Md. Mahfuz Islam, Samiul Ahmed, Tofayel Binyamin, Md. Karim, Md. Rezaul
contents	We introduce Green-NAS, a multi-objective NAS (neural architecture search) framework designed for low-resource environments using weather forecasting as a case study. By adhering to 'Green AI' principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The Green-NAS architecture search method is optimized for both model accuracy and efficiency to find lightweight models with high accuracy and very few model parameters; this is accomplished through an optimization process that simultaneously optimizes multiple objectives. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (i.e., within 1.4% of our manually tuned baseline) using only 153k model parameters, which is 239 times fewer than other globally applied weather forecasting models, such as GraphCast. In addition, we also describe how the use of transfer learning will improve the weather forecasting accuracy by approximately 5.2%, in comparison to a naive approach of training a new model for each city, when there is limited historical weather data available for that city.
format	Preprint
id	arxiv_https___arxiv_org_abs_2602_00240
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting Fahim, Md Muhtasim Munif Yesmin, Soyda Humyra Islam, Saiful Faruque, Md. Palash Bin Salam, Md. A. Uddin, Md. Mahfuz Islam, Samiul Ahmed, Tofayel Binyamin, Md. Karim, Md. Rezaul Machine Learning We introduce Green-NAS, a multi-objective NAS (neural architecture search) framework designed for low-resource environments using weather forecasting as a case study. By adhering to 'Green AI' principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The Green-NAS architecture search method is optimized for both model accuracy and efficiency to find lightweight models with high accuracy and very few model parameters; this is accomplished through an optimization process that simultaneously optimizes multiple objectives. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (i.e., within 1.4% of our manually tuned baseline) using only 153k model parameters, which is 239 times fewer than other globally applied weather forecasting models, such as GraphCast. In addition, we also describe how the use of transfer learning will improve the weather forecasting accuracy by approximately 5.2%, in comparison to a naive approach of training a new model for each city, when there is limited historical weather data available for that city.
title	Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting
topic	Machine Learning
url	https://arxiv.org/abs/2602.00240