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

Md Muhtasim Munif Fahim, Soyda Humyra Yesmin, Saiful Islam, Md. Palash Bin Faruque, Md. A. Salam, Md. Mahfuz Uddin, Samiul Islam, Tofayel Ahmed, Md. Binyamin, Md. Rezaul Karim

2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · 2026 · published · arXiv:2602.00240

View on arXiv → PDF → DOI →

TL;DR

239× fewer parameters than GraphCast at near-identical accuracy. Principled multi-objective NAS can find truly deployable models, and transfer learning adds ~5% accuracy gains when historical data is scarce.

Abstract

We introduce Green-NAS, a multi-objective neural architecture search (NAS) framework designed for low-resource environments using weather forecasting as a case study. Adhering to Green AI principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The search simultaneously optimizes model accuracy and efficiency to find lightweight architectures with very few parameters. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (within 1.4% of a manually tuned baseline) using only 153k parameters, 239 times fewer than globally deployed models such as GraphCast. Transfer learning improves forecasting accuracy by approximately 5.2% compared to training a new model per city when historical data is limited.

Neural Architecture SearchWeather ForecastingEdge ComputingGreen AITransfer LearningMulti-Objective OptimizationQPAIN

BibTeX

@article{fahim2026greennas,
  title   = {Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting},
  author  = {Md Muhtasim Munif Fahim and Soyda Humyra Yesmin and Saiful Islam and Md. Palash Bin Faruque and Md. A. Salam and Md. Mahfuz Uddin and Samiul Islam and Tofayel Ahmed and Md. Binyamin and Md. Rezaul Karim},
  year    = {2026},
  journal = {2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)},
  doi     = {10.1109/QPAIN69676.2026.11545925},
  eprint  = {2602.00240},
  archivePrefix = {arXiv},
  url     = {https://arxiv.org/abs/2602.00240},
}