3260 papers • 126 benchmarks • 313 datasets
Weather Forecasting is the prediction of future weather conditions such as precipitation, temperature, pressure and wind. Source: MetNet: A Neural Weather Model for Precipitation Forecasting
(Image credit: Papersgraph)
These leaderboards are used to track progress in weather-forecasting-16
Use these libraries to find weather-forecasting-16 models and implementations
This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.
NGBoost generalizes gradient boosting to probabilistic regression by treating the parameters of the conditional distribution as targets for a multiparameter boosting algorithm, and shows how the Natural Gradient is required to correct the training dynamics of the authors' multiparameters boosting approach.
Time series analysis and forecasting experiments demonstrate that the Chickenpox Cases in Hungary dataset is adequate for comparing the predictive performance and forecasting capabilities of novel recurrent graph neural network architectures.
How data-driven deep learning models such as FourCastNet are a valuable addition to the meteorology toolkit to aid and augment NWP models is discussed.
It is shown that GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures.
This paper designs a data-driven method augmented by an effective information fusion mechanism to learn from historical data that incorporates prior knowledge from NWP by proposing a novel negative log-likelihood error (NLE) loss function.
The scaling-binning calibrator is introduced, which first fits a parametric function to reduce variance and then bins the function values to actually ensure calibration, and estimates a model's calibration error more accurately using an estimator from the meteorological community.
PhyDNet is introduced, a two-branch deep architecture, which explicitly disentangles PDE dynamics from unknown complementary information, and a new recurrent physical cell (PhyCell) is proposed, inspired from data assimilation techniques, for performing PDE-constrained prediction in latent space.
Adding a benchmark result helps the community track progress.