{"ID":2863458,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24517","arxiv_id":"2509.24517","title":"Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting","abstract":"Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics). This sole focus on efficacy has steered development of large-scale models that require massive computational resources, and results in considerable energy consumption and corresponding carbon footprint across the model lifecycle. In this work, we explore how physics inductive biases can offer useful trade-offs between model efficacy and model efficiency (compute, energy, and carbon). We study models with strong, weak, and no physics-inductive biases for spatio-temporal forecasting of incompressible shear flow, a task governed by the Navier-Stokes equations. We find that models with stronger physics priors achieve substantially lower training footprints, but this advantage does not straightforwardly extend to inference, highlighting the importance of evaluating carbon costs across the full model lifecycle rather than any single stage. We argue that model efficiency, along with model efficacy, should become a core consideration driving machine learning model development and deployment.","short_abstract":"Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics). This sole focus on efficacy has steered development of large-scale models that require massive computational resources, and results in considerable energy consumption and corresponding carb...","url_abs":"https://arxiv.org/abs/2509.24517","url_pdf":"https://arxiv.org/pdf/2509.24517v2","authors":"[\"Sophia N. Wilson\",\"Jens Hesselbjerg Christensen\",\"Raghavendra Selvan\"]","published":"2025-09-29T09:34:53Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}