Pith. sign in

REVIEW 6 cited by

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.10024 v1 pith:OJCPHZ3Y submitted 2024-04-15 cs.AI cs.ETcs.LGphysics.ao-ph

classification cs.AIcs.ETcs.LGphysics.ao-ph
keywords weatherclimodeclimatecomplexdata-drivenforecastinggloballearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Climate and weather prediction traditionally relies on complex numerical simulations of atmospheric physics. Deep learning approaches, such as transformers, have recently challenged the simulation paradigm with complex network forecasts. However, they often act as data-driven black-box models that neglect the underlying physics and lack uncertainty quantification. We address these limitations with ClimODE, a spatiotemporal continuous-time process that implements a key principle of advection from statistical mechanics, namely, weather changes due to a spatial movement of quantities over time. ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow, which also enables estimating the uncertainty in predictions. Our approach outperforms existing data-driven methods in global and regional forecasting with an order of magnitude smaller parameterization, establishing a new state of the art.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology

    cs.CV 2026-01 conditional novelty 7.0 of 10

    Weather-R1 is a multimodal reasoning model for meteorology that uses logical consistency rewards during reinforcement fine-tuning to cut self-contradictory outputs and raises benchmark accuracy by 9.8 points over baselines.

  2. PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    PhysMetrics.Weather is an evaluation framework that quantifies physical realism of ML weather prediction models using conservation, spectral, and dynamical metrics.

  3. WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    WeatherSyn is the first instruction-tuned MLLM for weather forecasting report generation, outperforming closed-source models on a new dataset of 31 US cities across 8 weather aspects.

  4. Probabilistic Precipitation Nowcasting with Rectified Flow Transformers

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    FREUD applies rectified flow transformers with frame-wise encoding and a unified decoder to achieve state-of-the-art probabilistic precipitation nowcasting on the SEVIR benchmark.

  5. Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning

    cs.LG 2024-10 unverdicted novelty 5.0 of 10

    S-MNN reformulates Mechanistic Neural Networks to achieve linear computational complexity for long sequences while preserving accuracy and interpretability.

  6. Programmable Virtual Humans Toward Human Physiologically-Based Drug Discovery

    cs.CY 2025-07 unverdicted novelty 4.0 of 10

    A perspective arguing that multiscale, AI-driven 'programmable virtual humans' could enable drug discovery directly in simulated human physiology, bridging the gap between lab models and patients.

Pith tools