Explore the vast range of titles available.

Data assimilation (DA) is integrated with machine learning in order to perform entirely data‐driven online state estimation. To achieve this, recurrent neural networks (RNNs) are implemented as pretrained surrogate models to replace key components of the DA cycle in numerical weather prediction (NWP), including the conventional numerical forecast model, the forecast error covariance matrix, and the tangent linear and adjoint models. It is shown how these RNNs can be initialized using DA methods to directly update the hidden/reservoir state with observations of the target system. The results indicate that these techniques can be applied to estimate the state of a system for the repeated initialization of short‐term forecasts, even in the absence of a traditional numerical forecast model. Further, it is demonstrated how these integrated RNN‐DA methods can scale to higher dimensions by applying domain localization and parallelization, providing a path for practical applications in NWP. Plain Language Summary Weather forecast models derived from fundamental equations of physics continue to increase in detail and complexity. While this evolution leads to consistently improving daily weather forecasts, it also leads to associated increases in computational costs. In order to make a forecast at any given moment, these models must be initialized with our best guess of the current state of the atmosphere, which typically includes information from a limited set of observations as well as forecasts from the recent past. Modern methods for initializing these computer forecasts typically require running many copies of the model, either simultaneously or in sequence, to compare with observations over the recent past and ensure that our best guess estimate of the current state of the atmosphere agrees closely with those observations before making a new forecast. This repeated execution of the computer forecast model is often a time‐consuming and costly bottleneck in the initialization process. Here, it is shown that techniques from the fields of artificial intelligence and machine learning (AI/ML) can be used to produce simple surrogate models that provide sufficiently accurate approximations to replace the original costly model in the initialization phase. The resulting process is self‐contained, and does not require any further utilization of the original computer model when making daily forecasts. Key Points Recurrent neural networks (RNNs) can replace conventional forecast models, producing accurate ensemble forecast statistics and linearized dynamics Data assimilation (DA) is compatible with RNNs by applying state estimation in the hidden state space using a modified observation operator The integrated RNN‐DA methods can be scaled to higher dimensions by applying domain localization techniques

The Diabatic Influences on Mesoscale Structures in Extratropical Storms (DIAMET) project aims to improve forecasts of high-impact weather in extratropical cyclones through field measurements, high-resolution numerical modeling, and improved design of ensemble forecasting and data assimilation systems. This article introduces DIAMET and presents some of the first results. Four field campaigns were conducted by the project, one of which, in late 2011, coincided with an exceptionally stormy period marked by an unusually strong, zonal North Atlantic jet stream and a succession of severe windstorms in northwest Europe. As a result, December 2011 had the highest monthly North Atlantic Oscillation index (2.52) of any December in the last 60 years. Detailed observations of several of these storms were gathered using the U.K.’s BAe 146 research aircraft and extensive ground-based measurements. As an example of the results obtained during the campaign, observations are presented of Extratropical Cyclone Friedhelm on 8 December 2011, when surface winds with gusts exceeding 30 m s−1crossed central Scotland, leading to widespread disruption to transportation and electricity supply. Friedhelm deepened 44 hPa in 24 h and developed a pronounced bent-back front wrapping around the storm center. The strongest winds at 850 hPa and the surface occurred in the southern quadrant of the storm, and detailed measurements showed these to be most intense in clear air between bands of showers. High-resolution ensemble forecasts from the Met Office showed similar features, with the strongest winds aligned in linear swaths between the bands, suggesting that there is potential for improved skill in forecasts of damaging winds.

In this paper we present the derivation of two new forms of the Kalman filter equations; the first is for a pure lognormally distributed random variable, while the second set of Kalman filter equations will be for a combination of Gaussian and lognormally distributed random variables. We show that the appearance is similar to that of the Gaussian-based equations, but that the analysis state is a multivariate median and not the mean. We also show results of the mixed distribution Kalman filter with the Lorenz 1963 model with lognormal errors for the background and observations of the z component, and compare them to analysis results from a traditional Gaussian-based extended Kalman filter and show that under certain circumstances the new approach produces more accurate results.

In most data assimilation and numerical weather prediction systems, the Gaussian assumption is prevalent for the behavior of the random variables/errors that are involved. At the Cooperative Institute for Research in the Atmosphere theory has been developed for different forms of variational data assimilation schemes that enables the Gaussian assumption to be relaxed. For certain variable types, a lognormally distributed random variable can be combined in a mixed Gaussian‐lognormal distribution to better capture the interactions of the errors of different distributions. However, assuming that a distribution can change in time, then developing techniques to know when to switch between different versions of the data assimilation schemes becomes very important. By dynamically changing the formulation of the data assimilation system we are able to assimilate observations in a way that reflects the flow‐dependent variability of their distribution. In this paper, we present results with a machine learning technique (the support vector machine) to switch between data assimilation methods based on the detection of a change in the Lorenz 1963 model's z component's probability distribution. Given the machine learning technique's detection/prediction of a change in the distribution, then either a Gaussian or a mixed Gaussian‐lognormal 3DVar based cost function is used to minimize the errors in this period of time. It is shown that switching from a Gaussian 3DVar to a lognormal 3DVar at lognormally distributed parts of the attractor improves the data assimilation analysis error compared to using one distribution type for the entire attractor. Key Points Machine learning can be used to detect non‐Gaussian distributions Given the machine learning detection, we can switch between optimal data assimilation schemes Data assimilation can be improved using machine learning techniques

NASA s long-range goal is focused upon human exploration of Mars. Missions to Mars will require campaigns of multiple launches to assemble Mars Transfer Vehicles in Earth orbit. Launch campaigns are subject to delays, launch vehicles can fail to place their payloads into the required orbit, and spacecraft may fail during the assembly process or while loitering prior to the Trans-Mars Injection (TMI) burn. Additionally, missions to Mars have constrained departure windows lasting approximately sixty days that repeat approximately every two years. Ensuring high reliability of launching and assembling all required elements in time to support the TMI window will be a key enabler to mission success. This paper describes an integrated methodology for analyzing and improving the reliability of the launch and assembly campaign phase. A discrete event simulation involves several pertinent risk factors including, but not limited to: manufacturing completion; transportation; ground processing; launch countdown; ascent; rendezvous and docking, assembly, and orbital operations leading up to TMI. The model accommodates varying numbers of launches, including the potential for spare launches. Having a spare launch capability provides significant improvement to mission success.