MetNet: A Neural Weather Model for Precipitation Forecasting
read the original abstract
Weather forecasting is a long standing scientific challenge with direct social and economic impact. The task is suitable for deep neural networks due to vast amounts of continuously collected data and a rich spatial and temporal structure that presents long range dependencies. We introduce MetNet, a neural network that forecasts precipitation up to 8 hours into the future at the high spatial resolution of 1 km$^2$ and at the temporal resolution of 2 minutes with a latency in the order of seconds. MetNet takes as input radar and satellite data and forecast lead time and produces a probabilistic precipitation map. The architecture uses axial self-attention to aggregate the global context from a large input patch corresponding to a million square kilometers. We evaluate the performance of MetNet at various precipitation thresholds and find that MetNet outperforms Numerical Weather Prediction at forecasts of up to 7 to 8 hours on the scale of the continental United States.
This paper has not been read by Pith yet.
Forward citations
Cited by 17 Pith papers
-
GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products
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...
-
Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors
Diffusion model priors enable training-free Bayesian sampling for more accurate rain field reconstruction from path-integrated commercial microwave link measurements than Gaussian process baselines.
-
RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
RainODE reformulates precipitation forecasting as a latent Neural ODE with stochastic refinement to enable arbitrary-time inference while preserving sharp structures.
-
SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
SwAIther-Precip uses lead-time-conditioned U-Net bias correction followed by diffusion-based generative downscaling to reduce CRPS by 48% and achieve ~4 km effective resolution from 0.25° AIFS forecasts.
-
SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
SwAIther-Precip uses lead-time-conditioned U-Net bias correction followed by diffusion-based super-resolution to downscale AIFS forecasts, achieving 48% CRPS reduction and ~4 km effective resolution up to 5 days lead time.
-
Interpretable rainfall modelling reveals rapid reorganisation of Amazonian rainfall under vegetation loss
A neural-network rainfall model finds that sustained vegetation loss in the Amazon produces rapid asymmetric shifts in rainfall intensity and timing, with heavy precipitation declining up to 7% and light rain rising 4...
-
A PMP-inspired Evaluation Framework for Assessing Deep-Learning Earth System Models
The paper presents a PMP-based evaluation framework to test deep-learning Earth system models on climatology and modes of variability using observational data.
-
VideoGPT: Video Generation using VQ-VAE and Transformers
VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.
-
Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
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.
-
Forecasting threshold exceedance of atmospheric variables at a specific location
Full conditional distribution modeling outperforms direct binary classification for rare threshold exceedances by learning bulk parameters from moderate events.
-
Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression
Multi-quantile regression training of SmaAt-UNet on Dutch radar data yields an 8.6% lower test MSE for the median forecast and useful upper quantiles compared to MSE training.
-
QuantWeather: Quantile-Aware Probabilistic Forecasting for Subseasonal Precipitation
QuantWeather is an end-to-end dual-head neural network that produces calibrated quantile-based probabilistic forecasts for subseasonal precipitation, achieving higher skill and lower inference cost than ensemble metho...
-
Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors
Bayesian inverse problem with diffusion model priors for CML-based rain field reconstruction outperforms baselines by preserving rainfall statistics better than Gaussian processes.
-
MFC-RFNet: A Multi-scale Guided Rectified Flow Network for Radar Sequence Prediction
MFC-RFNet integrates multi-scale bidirectional communication, condition-guided alignment, and rectified flow to produce clearer and more skillful radar precipitation forecasts than prior baselines on four public datasets.
-
Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks
A multimodal GNN ablation for Nordic precipitation nowcasting shows sparse point observations improve station and onset scores while NWP and CRPS losses improve radar-grid performance, indicating local and field skill...
-
Temporal Context Conditioning for Seasonality-Aware Precipitation Nowcasting of High-Intensity Rainfall
TA-SmaAt-UNet extends SmaAt-UNet with temporal conditioning via cyclical time encodings, showing benefits for high-intensity precipitation nowcasting on KNMI radar data.
-
A PMP-inspired Evaluation Framework for Assessing Deep-Learning Earth System Models
A PMP-based evaluation framework for testing deep-learning Earth system models on climate-relevant diagnostics beyond short-range forecasts.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.