Stephan Rasp

ClimateAi

General circulation models (GCMs) are the foundation of weather and climate prediction1,2. GCMs are physics-based simulators that combine a numerical solver for large-scale dynamics with tuned representations for small-scale processes such as cloud formation. Recently, machine-learning models trained on reanalysis data have achieved comparable or b...

WeatherBench 2 is an update to the global, medium‐range (1–14 days) weather forecasting benchmark proposed by (Rasp et al., 2020, https://doi.org/10.1029/2020ms002203), designed with the aim to accelerate progress in data‐driven weather modeling. WeatherBench 2 consists of an open‐source evaluation framework, publicly available training, ground tru...

Projecting climate change is a generalization problem: We extrapolate the recent past using physical models across past, present, and future climates. Current climate models require representations of processes that occur at scales smaller than model grid size, which have been the main source of model projection uncertainty. Recent machine learning...

WeatherBench 2 is an update to the global, medium-range (1-14 day) weather forecasting benchmark proposed by Rasp et al. (2020), designed with the aim to accelerate progress in data-driven weather modeling. WeatherBench 2 consists of an open-source evaluation framework, publicly available training, ground truth and baseline data as well as a contin...

Climate projection uncertainty can be partitioned into model uncertainty, scenario uncertainty and internal variability. Here, we investigate the different sources of uncertainty in the projected frequencies of daily maximum temperature and precipitation extremes, which are defined as events that exceed the 99.97th percentile. This is done globally...

Climate projection uncertainty can be partitioned into model uncertainty, scenario uncertainty and internal variability. Here, we investigate the different sources of uncertainty in the projected frequencies of daily maximum temperature and precipitation extremes, which are defined as events that exceed the 99.97th percentile. This is done globally...

Machine learning represents a potential method to cope with the gray zone problem of representing motions in dynamical systems on scales comparable to the model resolution. Here we explore the possibility of using a neural network to directly learn the error caused by unresolved scales. We use a modified shallow water model which includes highly no...

WeatherBench is a benchmark dataset for medium-range weather forecasting of geopotential, temperature and precipitation, consisting of preprocessed data, predefined evaluation metrics and a number of baseline models. WeatherBench Probability extends this to probabilistic forecasting by adding a set of established probabilistic verification metrics...

Data-driven algorithms, in particular neural networks, can emulate the effects of unresolved processes in coarse-resolution climate models when trained on high-resolution simulation data; however, they often make large generalization errors when evaluated in conditions they were not trained on. Here, we propose to physically rescale the inputs and...

Machine learning represents a potential method to cope with the gray zone problem of representing motions in dynamical systems on scales comparable to the model resolution. Here we explore the possibility of using a neural network to directly learn the error caused by unresolved scales. We use a modified shallow water model which includes highly no...

Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically inconsistent results when violating fundamental constraints. Here, we introduce a systematic way of enforcing nonlinear analytic constraints in neural networks via constraints in the architecture or the loss function. Applied to convective pro...

Abstract Numerical weather prediction has traditionally been based on the models that discretize the dynamical and physical equations of the atmosphere. Recently, however, the rise of deep learning has created increased interest in purely data‐driven medium‐range weather forecasting with first studies exploring the feasibility of such an approach....

In previous work, it was shown that the preservation of physical properties in the data assimilation framework can significantly reduce forecast errors. Proposed data assimilation methods, such as the quadratic programming ensemble (QPEns) that can impose such constraints on the calculation of the analysis, are computationally more expensive, sever...

Abstract The use of machine learning based on neural networks for cloud microphysical parameterizations is investigated. As an example, we use the warm‐rain formation by collision‐coalescence, that is, the parameterization of autoconversion, accretion, and self‐collection of droplets in a two‐moment framework. Benchmark solutions of the kinetic col...

Abstract Data‐driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains. A natural question to ask is whether data‐driven methods could also be used to predict global weather patterns days in advance. First studies show promise but the lack of a common data set and evaluation metrics make intercomp...

In previous work, it was shown that preservation of physical properties in the data assimilation framework can significantly reduce forecasting errors. Proposed data assimilation methods, such as the quadratic programming ensemble (QPEns) that can impose such constraints on the calculation of the analysis, are computationally more expensive, severe...

Numerical weather prediction has traditionally been based on physical models of the atmosphere. Recently, however, the rise of deep learning has created increased interest in purely data-driven medium-range weather forecasting with first studies exploring the feasibility of such an approach. Here, we train a significantly larger model than in previ...

Humans excel at detecting interesting patterns in images, for example those taken from satellites. This kind of anecdotal evidence can lead to the discovery of new phenomena. However, it is often difficult to gather enough data of subjective features for significant analysis. This paper presents an example of how two tools that have recently become...

Over the last couple of years, machine learning parameterizations have emerged as a potential way to improve the representation of subgrid processes in Earth system models (ESMs). So far, all studies were based on the same three-step approach: first a training dataset was created from a high-resolution simulation, then a machine learning algorithm...

Different approaches for representing model error due to unresolved scales and processes are compared in convective-scale data assimilation, including the physically based stochastic perturbation (PSP) scheme for turbulence, an advanced warm bubble approach that automatically detects and triggers absent convective cells, and additive noise based on...

Data-driven algorithms, in particular neural networks, can emulate the effect of sub-grid scale processes in coarse-resolution climate models if trained on high-resolution climate simulations. However, they may violate key physical constraints and lack the ability to generalize outside of their training set. Here, we show that physical constraints...

Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains. A natural question to ask is whether data-driven methods could also be used for numerical weather prediction. First studies show promise but the lack of a common dataset and evaluation metrics make inter-comparison between studies diff...

Over the last couple of years, machine learning parameterizations have emerged as a potential way to improve the representation of sub-grid processes in Earth System Models (ESMs). So far, all studies were based on the same three-step approach: first a training dataset was created from a high-resolution simulation, then a machine learning algorithm...

Neural networks can emulate non-linear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints. In this letter, we introduce a systematic way of enforcing analytic constraints in neural networks via constraints in the architecture or the loss function. Applied to the modeling...

Kilometer-scale models allow for an explicit simulation of deep convective overturning but many subgrid processes that are crucial for convective initiation are still poorly represented. This leads to biases such as insufficient convection triggering and late peak of summertime convection. A physically based stochastic perturbation scheme (PSP) for...

The relative contributions of soil moisture heterogeneities, a stochastic boundary‐layer perturbation scheme and varied aerosol concentrations representing microphysical uncertainties on the diurnal cycle of convective precipitation and its spatial variability are examined conditional on the prevailing weather regime. To achieve this, separate pert...

Over the last couple of years, machine learning parameterizations have emerged as a potential way to improve the representation of sub-grid processes in atmospheric models. All previous studies created a training dataset from a high-resolution simulation, fitted a machine learning algorithms to that dataset, and then plugged the trained algorithm i...

Link = https://arxiv.org/pdf/1906.06622.pdf | Artificial neural-networks have the potential to emulate cloud processes with higher accuracy than the semi-empirical emulators currently used in climate models. However, neural-network models do not intrinsically conserve energy and mass, which is an obstacle to using them for long-term climate predict...

The discovery of new phenomena and mechanisms often begins with a scientist's intuitive ability to recognize patterns, for example in satellite imagery or model output. Typically, however, such intuitive evidence turns out to be difficult to encode and reproduce. Here, we show how crowd-sourcing and deep learning can be combined to scale up the int...

Ensemble weather predictions require statistical postprocessing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters of a predictive distribution are estimated from a training period. We propose a flexible alternative based on...

The representation of nonlinear subgrid processes, especially clouds, has been a major source of uncertainty in climate models for decades. Cloud-resolving models better represent many of these processes and can now be run globally but only for short-term simulations of at most a few years because of computational limitations. Here we demonstrate t...

The representation of nonlinear sub-grid processes, especially clouds, has been a major source of uncertainty in climate models for decades. Cloud-resolving models better represent many of these processes and can now be run globally but only for short-term simulations of at most a few years because of computational limitations. Here we demonstrate...

Representing unresolved moist convection in coarse-scale climate models remains one of the main bottlenecks of current climate simulations. Many of the biases present with parameterized convection are strongly reduced when convection is explicitly resolved (i.e., in cloud resolving models at high spatial resolution approximately a kilometer or so)....

Ensemble weather predictions require statistical post-processing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters of a predictive distribution are estimated from a training period. We propose a flexible alternative based on...

Modeling and representing moist convection in coarse-scale climate models remains one of the main bottlenecks of current climate simulations. Many of the biases present with parameterized convection are strongly reduced when convection is explicitly resolved (in cloud resolving models at high spatial resolution ~ a kilometer or so). We here present...

The statistical theory of convective variability developed by Craig and Cohen in 2006 has provided a promising foundation for the design of stochastic parameterizations. The simplifying assumptions of this theory, however, were made with tropical equilibrium convection in mind. This study investigates the predictions of the statistical theory in re...

Air parcel ascent in mid-latitude cyclones driven by latent heat release has been investigated using convection-permitting simulations together with an online trajectory calculation scheme. Three cyclones were simulated to represent different ascent regimes: one continental summer case which developed strong convection organized along a cold front;...

A stochastic perturbation scheme based on physical information about subgrid-scale variability of turbulence is presented. This scheme is shown to improve the representation of convective initiation for a case study.

Vertical motions in the mid-latitude atmosphere occur on short time-scales (< 1 h), as a result of convective instabilities, as well as on synoptic time scales (~1 d) associated with warm conveyor belts (WCB). In this study the COSMO model at convection-permitting resolution is used together with a recently implemented online trajectory calculation...