The reviewed record of science sign in
Pith

arxiv: 2306.06079 · v3 · pith:FFGCJOS2 · submitted 2023-06-06 · physics.ao-ph · cs.LG

Deep Learning for Day Forecasts from Sparse Observations

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:FFGCJOS2record.jsonopen to challenge →

classification physics.ao-ph cs.LG
keywords metnet-3modelsneuraldataforecastshoursobservationssparse
0
0 comments X
read the original abstract

Deep neural networks offer an alternative paradigm for modeling weather conditions. The ability of neural models to make a prediction in less than a second once the data is available and to do so with very high temporal and spatial resolution, and the ability to learn directly from atmospheric observations, are just some of these models' unique advantages. Neural models trained using atmospheric observations, the highest fidelity and lowest latency data, have to date achieved good performance only up to twelve hours of lead time when compared with state-of-the-art probabilistic Numerical Weather Prediction models and only for the sole variable of precipitation. In this paper, we present MetNet-3 that extends significantly both the lead time range and the variables that an observation based neural model can predict well. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 introduces a key densification technique that implicitly captures data assimilation and produces spatially dense forecasts in spite of the network training on extremely sparse targets. MetNet-3 has a high temporal and spatial resolution of, respectively, up to 2 minutes and 1 km as well as a low operational latency. We find that MetNet-3 is able to outperform the best single- and multi-member NWPs such as HRRR and ENS over the CONUS region for up to 24 hours ahead setting a new performance milestone for observation based neural models. MetNet-3 is operational and its forecasts are served in Google Search in conjunction with other models.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

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

  1. AIFS-DOP: End-to-End Medium-Range Weather Prediction from Observations Alone with Machine Learning

    physics.ao-ph 2026-06 unverdicted novelty 8.0

    An ML model trained only on harmonized gridded observations achieves competitive medium-range weather forecast skill with the IFS for several upper-air and surface headline scores when verified against observations.

  2. GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products

    physics.ao-ph 2026-05 unverdicted novelty 7.0

    GPROF-IR is a CNN-based retrieval that uses temporal context in geostationary IR observations to produce precipitation estimates with lower error than prior IR methods and climatological consistency with PMW retrieval...

  3. RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs

    cs.CV 2026-06 unverdicted novelty 6.0

    RainODE reformulates precipitation forecasting as a latent Neural ODE with stochastic refinement to enable arbitrary-time inference while preserving sharp structures.

  4. PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting

    cs.AI 2026-05 unverdicted novelty 6.0

    PnP-Corrector decouples physics simulation from error correction to counter reciprocal error amplification in coupled spatiotemporal forecasting, cutting error by 29% in a 300-day ocean-atmosphere test.

  5. PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting

    cs.AI 2026-05 unverdicted novelty 6.0

    PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.

  6. Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting

    physics.ao-ph 2026-04 unverdicted novelty 6.0

    ESFM is a single open foundation model that unifies heterogeneous Earth data sources and forecasts missing regions while preserving inter-variable physical relationships.

  7. PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting

    cs.AI 2026-05 unverdicted novelty 4.0

    PnP-Corrector decouples pre-trained physics engines from a correction agent to mitigate reciprocal error amplification in coupled spatiotemporal forecasting, cutting error by 28% on a 300-day ocean-atmosphere task.

  8. Towards a Foundation Model for the Martian Atmosphere

    astro-ph.EP 2026-05 unverdicted novelty 3.0

    The paper reviews data sources, physical models, downstream applications, and AI techniques to outline considerations for building a foundation model for the Martian atmosphere.