Corpus ID: 207779626

Predicting Weather Uncertainty with Deep Convnets

  title={Predicting Weather Uncertainty with Deep Convnets},
  author={Peter Gr{\"o}nquist and Tal Ben-Nun and Nikoli Dryden and P. Dueben and Luca Lavarini and Shigang Li and Torsten Hoefler},
Modern weather forecast models perform uncertainty quantification using ensemble prediction systems, which collect nonparametric statistics based on multiple perturbed simulations. To provide accurate estimation, dozens of such computationally intensive simulations must be run. We show that deep neural networks can be used on a small set of numerical weather simulations to estimate the spread of a weather forecast, significantly reducing computational cost. To train the system, we both modify… Expand
Deep Learning for Ensemble Forecasting
Deep convolutional neural networks have been demonstrated as very effective for many tasks in the field of atmospheric science including forecasting, satellite retrievals, downscaling/super resolution, atmospheric state classification, and many others, and are particularly well suited for problems that involve very large, gridded datasets where complex non-linear relationships must be learned. Expand
Investigating Communication Techniques to Support Trust Calibration for Automated Systems
The state of the art on the communication of reliability, uncertainty, awareness and intent, as well as of alternatives is provided, which provides first directions and an outlook into exploiting these approaches for the calibration of trust in the application area of automated driving. Expand
FatPaths: Routing in Supercomputers and Data Centers when Shortest Paths Fall Short
We introduce FatPaths: a simple, generic, and robust routing architecture that enables state-of-the-art low-diameter topologies such as Slim Fly to achieve unprecedented performance. FatPaths targetsExpand
Deep learning for post-processing ensemble weather forecasts
A mixed model that uses only a subset of the original weather trajectories combined with a post-processing step using deep neural networks enables the model to account for non-linear relationships that are not captured by current numerical models or post- processing methods. Expand
Ensemble Methods for Neural Network‐Based Weather Forecasts
This work aims to transform a deterministic neural network weather forecasting system into an ensemble forecasting system, and test four methods to generate the ensemble: random initial perturbations, retraining of the neural network, use of random dropout in the network, and the creation of initial perturgations with singular vector decomposition. Expand
FatPaths: routing in supercomputers and data centers when shortest paths fall short
FatPaths is introduced, a simple, generic, and robust routing architecture that enables state-of-the-art lowdiameter topologies such as Slim Fly to achieve unprecedented performance and may become a standard routing scheme for modern topologies. Expand


Precipitation Nowcasting : Leveraging Deep Recurrent Convolutional Neural Networks
Automating very short-term precipitation forecasts can prove a significant challenge in that traditional physics-based weather models are computationally expensive; by the time the forecast is made,Expand
Challenges and design choices for global weather and climate models based on machine learning
A toy model for global weather predictions will be presented and used to identify challenges and fundamental design choices for a forecast system based on neural networks. Expand
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
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. Expand
Segmenting and Tracking Extreme Climate Events using Neural Networks
Predicting extreme weather events in a warming world is one of the most pressing and challenging problems that humanity faces today. Deep learning and advances in the field of computer vision provideExpand
Predicting uncertainty in forecasts of weather and climate
The predictability of weather and climate forecasts is determined by the projection of uncertainties in both initial conditions and model formulation onto flow-dependent instabilities of the chaoticExpand
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
This work goes beyond ConvLSTM and proposes the Trajectory GRU (TrajGRU) model that can actively learn the location-variant structure for recurrent connections, and provides a benchmark that includes a real-world large-scale dataset from the Hong Kong Observatory. Expand
ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
This work presents a multichannel spatiotemporal CNN architecture for semi-supervised bounding box prediction and exploratory data analysis, and demonstrates that this approach is able to leverage temporal information and unlabeled data to improve the localization of extreme weather events. Expand
Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather
AbstractHigh-impact weather events, such as severe thunderstorms, tornadoes, and hurricanes, cause significant disruptions to infrastructure, property loss, and even fatalities. High-impact eventsExpand
Toward Data‐Driven Weather and Climate Forecasting: Approximating a Simple General Circulation Model With Deep Learning
It is shown that it is possible to emulate the dynamics of a simple general circulation model with a deep neural network and can predict the complete mode of the model. Expand
The ECMWF Ensemble Prediction System: Methodology and validation
The European Centre for Medium-Range Weather Forecasts (ECMWF) Ensemble Prediction System (EPS) is described. In addition to an unperturbed (control) forecast, each ensemble comprises 32 10-dayExpand