# Performance-Carbon Trade-Offs across Architectural Biases in Shear Flow Forecasting

arXiv: https://arxiv.org/abs/2509.24517 · HTML: https://mlsanity.com/paper/2509.24517/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [U-NO: U-shaped Neural Operators](https://mlsanity.com/paper/2204.11127/) (2022)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Physics-informed learning of governing equations from scarce data](https://mlsanity.com/paper/2005.03448/) (2020)
- [Compute Trends Across Three Eras of Machine Learning](https://mlsanity.com/paper/2202.05924/) (2022)
- [The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning](https://mlsanity.com/paper/2412.00568/) (2024)
- [The rising costs of training frontier AI models](https://mlsanity.com/paper/2405.21015/) (2024)
- [Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data](https://mlsanity.com/paper/2012.02334/) (2020)
- [Physics Informed Kolmogorov-Arnold Neural Networks for Dynamical Analysis via Efficent-KAN and WAV-KAN](https://mlsanity.com/paper/2407.18373/) (2024)
- [Physics-enhanced deep surrogates for partial differential equations](https://mlsanity.com/paper/2111.05841/) (2021)
- [Frugal Machine Learning](https://mlsanity.com/paper/2111.03731/) (2021)
- [EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search](https://mlsanity.com/paper/2210.06015/) (2022)
- [CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework](https://mlsanity.com/paper/2406.01414/) (2024)
- [AQ-PINNs: Attention-Enhanced Quantum Physics-Informed Neural Networks for Carbon-Efficient Climate Modeling](https://mlsanity.com/paper/2409.01626/) (2024)
- [Beyond Accuracy: EcoL2 Metric for Sustainable Neural PDE Solvers](https://mlsanity.com/paper/2505.12556/) (2025)

## Abstract (arXiv)

Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics), leading to large-scale models that require massive computational resources and result in considerable carbon footprint across the model lifecycle. In this work, we explore how architectural biases, specifically a model's receptive field and periodicity assumption, are associated with the trade-offs between predictive performance and carbon footprint for spatio-temporal forecasting of incompressible shear flow. We study seven models differing in these properties and evaluate pointwise accuracy, physics-fidelity, and carbon cost across training and inference. We find that no single model dominates across both predictive performance and carbon cost, that a lower training cost does not straightforwardly extend to inference, and that runtime alone is an unreliable proxy for carbon cost, particularly during training. Together, these results underscore the importance of explicitly evaluating carbon costs across the full model lifecycle. We argue that model efficiency, alongside efficacy, should be a core consideration in machine learning model development and deployment.