Analysis of Neural Networks for Predicting Time Series When Assessing Industrial Safety Risks

The paper describes the choice of an artificial neural network (ANN), the most effective for use in problems of modeling the behavior of complex dynamic systems with the subsequent solution of the forecast problem. The choice is made to implement a risk-based approach in the domestic trusted innovation umbrella system «Zodiac» when monitoring the industrial safety of the enterprises of the Fuel and Energy Complex (FEC).

Impacts of Targeted AERI and Doppler Lidar Wind Retrievals on Short-Term Forecasts of the Initiation and Early Evolution of Thunderstorms

The ability of Atmospheric Emitted Radiance Interferometer (AERI) and Doppler lidar (DL) wind profile observations to impact short-term forecasts of convection is explored by assimilating retrievals into a partially cycled convection-allowing ensemble analysis and forecast system. AERI and DL retrievals were obtained over 12 days using a mobile platform that was deployed in the preconvective and near-storm environments of thunderstorms during the afternoon in the U.S. Great Plains. The observation locations were guided by real-time ensemble sensitivity analysis (ESA) fields. AERI retrievals of temperature and dewpoint and DL retrievals of the horizontal wind components were assimilated into a control experiment that only assimilated conventional observations. Using the fractions skill score within 25-km neighborhoods, it is found that the assimilation of the AERI and DL retrievals results in far more times when the forecasts are improved than degraded in the 6-h forecast period. However, statistical confidence in the improvements often is not high and little to no relationships between the ESA fields and the actual changes in spread and skill is found. But, the focus on convective initiation and early convective evolution—a challenging forecast problem—and the fact that frequent improvements were seen despite observations from only one system over a limited period, provides encouragement to continue exploring the benefits of ground-based profilers to supplement the current upper-air observing system for severe weather forecasting applications.

Statistical Forecast Model for Ice-Related Events in the Arctic

This paper presents a statistical ice event forecast model for the Arctic based on Fourier transforms and a mathematical filter. The results indicate that this model compares very well with both a multiple regression model and a human-made forecast. There seems to be a direct link between the period associated with the dominant spectral peak of the Fourier transform and the ease with which the date of events, such as fractures, bergy water, or open water, can be forecast. While useful for the normal timing of events, at this time, none of the current forecast models can predict events that occur before or beyond the usual or historical dates, which poses a forecast problem in the Arctic.

Smoothing Problems in a Bayesian Framework and Their Linear Gaussian Solutions

Smoothers are increasingly used in geophysics. Several linear Gaussian algorithms exist, and the general picture may appear somewhat confusing. This paper attempts to stand back a little, in order to clarify this picture by providing a concise overview of what the different smoothers really solve, and how. The authors begin addressing this issue from a Bayesian viewpoint. The filtering problem consists in finding the probability of a system state at a given time, conditioned to some past and present observations (if the present observations are not included, it is a forecast problem). This formulation is unique: any different formulation is a smoothing problem. The two main formulations of smoothing are tackled here: the joint estimation problem (fixed lag or fixed interval), where the probability of a series of system states conditioned to observations is to be found, and the marginal estimation problem, which deals with the probability of only one system state, conditioned to past, present, and future observations. The various strategies to solve these problems in the Bayesian framework are introduced, along with their deriving linear Gaussian, Kalman filter-based algorithms. Their ensemble formulations are also presented. This results in a classification and a possible comparison of the most common smoothers used in geophysics. It should provide a good basis to help the reader find the most appropriate algorithm for his/her own smoothing problem.