Conditional Forecasts Research Articles

Context-aware sequence labeling for condition information extraction from historical bridge inspection reports

Effective upkeep of aging infrastructure systems with limited funding and resources calls for efficient bridge management systems. Although data-driven models have been extensively studied in the last decade for extracting knowledge from past experience to guide future maintenance decision making, their performance and usefulness have been limited by the level of detail and accuracy of currently available bridge condition databases. This paper leverages an untapped resource for bridge condition data and proposes a new method to extract condition information from it at a high level of detail. To that end, a natural language processing approach was developed to formalize structural condition knowledge by formulating a sequence labeling task and modeling inspection narratives as a combination of words representing defects, their severity and location, while accounting for the context of each word. The proposed framework employs a deep-learning-based approach and incorporates context-aware components including a bi-directional Long Short Term Memory (LSTM) neural network architecture and a Conditional Random Field (CRF) classifier to account for the context of words when assigning labels. A dependency-based word embedding model was also used to represent the raw text while incorporating both semantic and contextual information. The sequence labeling model was trained using bridge inspection reports collected from the Virginia Department of Transportation bridge inspection database and achieved an F1 score of 94.12% during testing. The proposed model also demonstrated improvements compared with baseline sequence labeling models, and was further used to demonstrate the capability of detecting condition changes with respect to previous inspection records. Results of this study show that the proposed method can be used to extract and create a condition information database that can further assist in developing data-driven bridge management and condition forecasting models, as well as automated bridge inspection systems.

Binary Conditional Forecasts

While conditional forecasting has become prevalent both in the academic literature and in practice (e.g., bank stress testing, scenario forecasting), its applications typically focus on continuous variables. In this article, we merge elements from the literature on the construction and implementation of conditional forecasts with the literature on forecasting binary variables. We use the Qual-VAR, whose joint VAR-probit structure allows us to form conditional forecasts of the latent variable which can then be used to form probabilistic forecasts of the binary variable. We apply the model to forecasting recessions in real-time and investigate the role of monetary and oil shocks on the likelihood of two U.S. recessions.

A satellite-based mobile warning system to reduce interactions with an endangered species.

Earth‐observing satellites are a major research tool for spatially explicit ecosystem nowcasting and forecasting. However, there are practical challenges when integrating satellite data into usable real‐time products for stakeholders. The need of forecast immediacy and accuracy means that forecast systems must account for missing data and data latency while delivering a timely, accurate, and actionable product to stakeholders. This is especially true for species that have legal protection. Acipenser oxyrinchus oxyrinchus (Atlantic sturgeon) were listed under the United States Endangered Species Act in 2012, which triggered immediate management action to foster population recovery and increase conservation measures. Building upon an existing research occurrence model, we developed an Atlantic sturgeon forecast system in the Delaware Bay, USA. To overcome missing satellite data due to clouds and produce a 3‐d forecast of ocean conditions, we implemented data interpolating empirical orthogonal functions (DINEOF) on daily observed satellite data. We applied the Atlantic sturgeon research model to the DINEOF output and found that it correctly predicted Atlantic sturgeon telemetry occurrences over 90% of the time within a 3‐d forecast. A similar framework has been utilized to forecast harmful algal blooms, but to our knowledge, this is the first time a species distribution model has been applied to DINEOF gap‐filled data to produce a forecast product for fishes. To implement this product into an applied management setting, we worked with state and federal organizations to develop real‐time and forecasted risk maps in the Delaware River Estuary for both state‐level managers and commercial fishers. An automated system creates and distributes these risk maps to subscribers’ mobile devices, highlighting areas that should be avoided to reduce interactions. Additionally, an interactive web interface allows users to plot historic, current, future, and climatological risk maps as well as the underlying model output of Atlantic sturgeon occurrence. The mobile system and web tool provide both stakeholders and managers real‐time access to estimated occurrences of Atlantic sturgeon, enabling conservation planning and informing fisher behavior to reduce interactions with this endangered species while minimizing impacts to fisheries and other projects.

Long‐Range Forecasting as a Past Value Problem: Untangling Correlations and Causality With Scaling

AbstractConventional long‐range weather prediction is an initial value problem that uses the current state of the atmosphere to produce ensemble forecasts. Purely stochastic predictions for long‐memory processes are “past value” problems that use historical data to provide conditional forecasts. Teleconnection patterns, defined from cross‐correlations, are important for identifying possible dynamical interactions, but they do not necessarily imply causation. Using the precise notion of Granger causality, we show that for long‐range stochastic temperature forecasts, the cross‐correlations are only relevant at the level of the innovations–not temperatures. This justifies the Stochastic Seasonal to Interannual Prediction System (StocSIPS) that is based on a (long memory) fractional Gaussian noise model. Extended here to the multivariate case (m‐StocSIPS) produces realistic space‐time temperature simulations. Although it has no Granger causality, emergent properties include realistic teleconnection networks and El Niño events and indices.

Experience of application of calcium-containing cored wire with various fillers at steel ladle treatment

Treatment of mass production steels by cored calcium-containing wires is widely spread all over the world. Injection of several tens of gram of calcium per 1 t of the treated steel enables significantly improve its cast ability, increase the yield of CC billet, decrease rejection of rolled products by surface and internal defects, improve corrosion properties of steel and have similar effects. At the same time application of the technological method requires accurate forecasting of the purpose process conditions, strict following the technology parameters, application of quality injection equipment, as well as application of best calcium-containing cored wires. Taking into consideration, that the role of the filler in the cored wires is not discussed widely, the purpose of the work was summarizing of the experience of application of various calcium-containing materials. Mechanisms of calcium influence on steel quality considered. It was shown that it is possible to control not only chemical composition but also phase composition of nonmetallic inclusions by variation of calcium concentration in steel melt. Among others, liquid inclusions based on calcium aluminates which have high speed of surfacing, will be formed, thus ensuring deep steel refining for nonmetallic inclusions within a short time. Having high sulphur affinity, at the stage of continuous casting calcium forms sulfide and oxide-sulfide nonmetallic inclusions of micron and submicron size, uniformly distributed in the steel volume, which improves the structure of center zone of the continuously casted billet and that of the rolled product. It was shown that calcium-containing filler of a cored wire plays an important role in ensuring high and stable result. It was established based on the probes from tundish that the average recovery of fillers of electrolytic calcium is higher comparing with other fillers. Analysis of frequency distribution of the calcium recovery value showed that to ensure a guaranteed minimal content of calcium of 12 ppm at a CCM, it is required to inject aluminothermic calcium in the amount of 4.5 times bigger comparing with electrolytic calcium and ferrocalcium – 6 times bigger. Analysis of cast ability of steel treated by cored wires showed that to ensure a stable cast ability it is enough to add 55 grams of electrolytic calcium per 1 t of steel, at that addition of 83 grams of aluminothermic calcium does not ensure a stable casting from heat to heat. A dependence of rolled products rejection indices on calcium content in steel was noted, which indicated of a possibility of further increase of economic efficiency of technologies of steel mass production due to development of steel treatment by calcium.

Real-time environmental forecasts of the Chesapeake Bay: Model setup, improvements, and online visualization

Daily real-time nowcasts (current conditions) and 2-day forecasts of environmental conditions in the Chesapeake Bay have been continuously available for 4 years. The forecasts use a 3-D hydrodynamic-biogeochemical model with 1–2 km resolution and 3-D output every 6 h that includes salinity, water temperature, pH, aragonite saturation state, alkalinity, dissolved oxygen, and hypoxic volume. Visualizations of the forecasts are available through a local institutional website (www.vims.edu/hypoxia) and the MARACOOS Oceans Map portal (https://oceansmap.maracoos.org/chesapeake-bay/). Modifications to real-time graphics on the local website are routinely made based on stakeholder input and are formatted for use on a mobile device. Continuous model input files were developed from daily real-time forecast input files, for hindcast simulations and efficient evaluation and improvement of the real-time model. This manuscript describes the setup of the environmental forecasting system, how the model accuracy has been improved, and the revision of online graphics based on stakeholder feedback.

Assessing the Skills of a Seasonal Forecast of Chlorophyll in the Global Pelagic Oceans

While forecasts of atmospheric variables, and to a lesser degree ocean circulation, are relatively common, the forecast of biogeochemical conditions is still in its infancy. Using a dynamical ocean biogeochemical forecast forced by seasonal forecasts of atmospheric and physical ocean variables, we produce seasonal predictions of chlorophyll concentration at the global scale. Results show significant Anomaly Correlation Coefficients (ACCs) for the majority of regions (11 out of the 12 regions for the 1-month lead forecast). Root mean square errors are smaller (<0.05 µg chlorophyll (chl) L−1) in the Equatorial regions compared to the higher latitudes (range from 0.05 up to 0.13 µg chl L−1). The forecast for all regions except three (North Atlantic, South Pacific and North Indian) are within the Semi-Interquartile Range of the satellite chlorophyll concentration (Suomi-National Polar-orbiting Partnership (NPP), 27.9%). This suggests the potential for skillful global biogeochemical forecasts on seasonal timescales of chlorophyll, primary production and harmful algal blooms that could support fisheries management and other applications.

Real-Time Prognostics of Engineered Systems under Time Varying External Conditions Based on the COX PHM and VARX Hybrid Approach.

In spite of the development of the Prognostics and Health Management (PHM) during past decades, the reliability prognostics of engineered systems under time-varying external conditions still remains a challenge in such a field. When considering the challenge mentioned above, a hybrid method for predicting the reliability index and the Remaining Useful Life (RUL) of engineered systems under time-varying external conditions is proposed in this paper. The proposed method is competent in reflecting the influence of time-varying external conditions on the degradation behaviour of engineered systems. Based on a subset of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset as case studies, the Cox Proportional Hazards Model (Cox PHM) with time-varying covariates is utilised to generate the reliability indices of individual turbofan units. Afterwards, a Vector Autoregressive model with Exogenous variables (VARX) combined with pairwise Conditional Granger Causality (CGC) tests for sensor selections is defined to model the time-varying influence of sensor signals on the reliability indices of different units that have been previously generated by the Cox PHM with time-varying covariates. During the reliability prediction, the Fourier Grey Model (FGM) is employed with the time series models for long-term forecasting of the external conditions. The results show that the method that is proposed in this paper is competent for the RUL prediction as compared with baseline approaches.

Research on the Intelligent Early Warning System for Metal Mine Mining Safety

In order to reduce mine safety accidents and realize safe production, the mine safety early warning system was developed by studying the causes of accidents, using Python as the development language, using Web network technology and database technology. The paper uses the deployment of high-precision sensors and the development of a distributed management information system to realize the real-time collection and online monitoring of the monitoring index data of the metal mine; based on the accurately obtained key indicators such as the deformation displacement, the reservoir water level, and the depth of the infiltration line, it is safe for the metal mine Multi-level early warning and forecasting of risk conditions are implemented. The actual operation of the system shows that the integrated management system can provide decision-making basis for regional safety management.

Time-varying autoregressive distributed lag model with changing volatility for stress test

We present a novel time-varying autoregressive distributed lag (TV-ADL) model that allows for changes in both transmission mechanisms and innovation volatilities. The forecasting performance of the TV-ADL model has been substantially improved by removing the unrealistic traditional assumptions of constant volatility and constant inter-variable relationship. Our model is further adapted to stress tests mandated by the US Federal Reserve to generate conditional forecasts of the pre-provision net revenue of financial holding companies with large assets. The improvement of forecasting performance is demonstrated by the significant reduction of out-of-sample forecast errors at different horizons.

The simulation manifesto: The limits of brute‐force empiricism in geopolitical forecasting

AbstractIntelligence analysis has traditionally relied on inside‐view, case‐specific modes of thinking: why did this actor—say, the USSR—do that and what might it do next? After 9/11, however, analysts faced a vastly wider range of threats that necessitated outside‐view, statistical modes of reasoning: how likely are threats to emerge from actors of diverse types operating in situations of diverse types? Area‐study specialists (who staffed most geopolitical desks) were ill‐equipped for answering these questions. Thanks to advances in long‐range sensing, digitization, and computing, the intelligence community was flooded with data, but lacked clear ideas about how to render it relevant. Empiricism, whether grounded in deep inside‐view knowledge of particular places or broad outside‐view knowledge of statistical patterns across the globe, could not and cannot solve the problem of anticipating high‐impact, rare events, like sneak attacks and pandemics. Contingency planning for these threats requires well‐calibrated conditional forecasts of the impact of policy interventions that in turn require synthesizing inside‐ and outside‐view analytics. Such syntheses will be best achieved by refining computer simulations that permit replays of history based on the interplay among initial conditions, chance, and social‐science models of causation. We offer suggestions for accelerating the development and application of theory‐guided simulation techniques.

Indian Ocean impact on ENSO evolution 2014\u20132016 in a set of seasonal forecasting experiments

This study investigates the influence of the anomalously warm Indian Ocean state on the unprecedentedly weak Indonesian Throughflow (ITF) and the unexpected evolution of El Niño-Southern Oscillation (ENSO) during 2014–2016. It uses 25-month-long coupled twin forecast experiments with modified Indian Ocean initial conditions sampling observed decadal variations. An unperturbed experiment initialized in Feb 2014 forecasts moderately warm ENSO conditions in year 1 and year 2 and an anomalously weak ITF throughout, which acts to keep tropical Pacific ocean heat content (OHC) anomalously high. Changing only the Indian Ocean to cooler 1997 conditions substantially alters the 2-year forecast of Tropical Pacific conditions. Differences include (i) increased probability of strong El Niño in 2014 and La Niña in 2015, (ii) significantly increased ITF transports and (iii), as a consequence, stronger Pacific ocean heat divergence and thus a reduction of Pacific OHC over the two years. The Indian Ocean’s impact in year 1 is via the atmospheric bridge arising from altered Indian Ocean Dipole conditions. Effects of altered ITF and associated ocean heat divergence (oceanic tunnel) become apparent by year 2, including modified ENSO probabilities and Tropical Pacific OHC. A mirrored twin experiment starting from unperturbed 1997 conditions and several sensitivity experiments corroborate these findings. This work demonstrates the importance of the Indian Ocean’s decadal variations on ENSO and highlights the previously underappreciated role of the oceanic tunnel. Results also indicate that, given the physical links between year-to-year ENSO variations, 2-year-long forecasts can provide additional guidance for interpretation of forecasted year-1 ENSO probabilities.

Exogeneity in climate econometrics

Human activity affects the Earth's climate while itself being affected by climate change. To empirically estimate the impact of humanity onto climate and vice versa, climate econometrics has emerged as a field split into two strands: one side focusing on conditional models of the economic impact of climate change, taking climate as given. The other side empirically models climate, taking economic and human activity as given. However, economic and environmental systems are determined with feedback in both directions. Here I examine one way to reconcile the two strands of climate-econometric research by considering a full (albeit simple) empirical climate-economic system and the conditions under which the system can be studied by only looking at the conditional economic or climate side alone. Weak exogeneity is necessary for valid conditioning, strong exogeneity – required for conditional forecasting – lends itself to the concept of climate-takers and climate-setters (countries measurably affecting local climate), while super-exogeneity can be interpreted as policy invariance for the economic impact side, and as a ‘no-tipping point’ condition on the physical side. An application to a stylised climate-economic system using temperatures, SO2 emissions, and global forcing highlights how these concepts can be applied in practice. A system analysis in climate econometrics allows us to move towards fully-coupled empirical climate-economic models accounting for the necessary feedback to obtain empirical estimates of the impact of climate on humanity and vice versa.

Arctic Amplification of Anthropogenic Forcing: A Vector Autoregressive Analysis

AbstractOn September 15th 2020, Arctic sea ice extent (SIE) ranked second-to-lowest in history and keeps trending downward. The understanding of how feedback loops amplify the effects of external CO2 forcing is still limited. We propose the VARCTIC, which is a Vector Autoregression (VAR) designed to capture and extrapolate Arctic feedback loops. VARs are dynamic simultaneous systems of equations, routinely estimated to predict and understand the interactions of multiple macroeconomic time series. The VARCTIC is a parsimonious compromise between full-blown climate models and purely statistical approaches that usually offer little explanation of the underlying mechanism. Our completely unconditional forecast has SIE hitting 0 in September by the 2060’s. Impulse response functions reveal that anthropogenic CO2 emission shocks have an unusually durable effect on SIE – a property shared by no other shock. We find Albedo- and Thickness-based feedbacks to be the main amplification channels through which CO2 anomalies impact SIE in the short/medium run. Furthermore, conditional forecast analyses reveal that the future path of SIE crucially depends on the evolution of CO2 emissions, with outcomes ranging from recovering SIE to it reaching 0 in the 2050’s. Finally, Albedo and Thickness feedbacks are shown to play an important role in accelerating the speed at which predicted SIE is heading towards 0.

Dynamic reduction of time and cost uncertainties in tunneling projects

The cost and time estimation play a vital role in successfully completing a tunnel construction, however in most cases the estimation falls short compared to the actual time and cost that a tunnel construction consumes due to a number of geological and geotechnical reasons. This creates uncertainties in tunnel construction in terms time and cost. In this article, the effects of geological/geotechnical uncertainties in tunnel construction time and costs are being minimized through continuous updating techniques. The forecasting of geological conditions is based on continuous space-discrete state Markov process. Whereas, predicting the construction time and costs are based on Monte-Carlo (MC) simulation. To verify the tool applicability, it has been applied to Hamru tunnel in Iran. Also, to assess the updating effect on obtained outcomes during construction, the tool has been updated two times. In the first update, the total uncertainty in construction time and costs (measured by standard deviation) has been reduced by about 45% and 52%, respectively, followed by a reduction by about 66% and 61% in the second update. Finally, we can conclude that, the presented methodology is a helpful tool for tunnel project managers to identify risks and the possibility of deviations in their construction time and costs.

The COVID-19 Shock and Challenges for Time Series Models

We document the impact of COVID-19 on frequently employed time series models, with a focus on euro area inflation. We show that for both single equation models (Phillips curves) and Vector Autoregressions (VARs) estimated parameters change notably with the pandemic. In a VAR, allowing the errors to have a distribution with fatter tails than the Gaussian one equips the model to better deal with the COVID-19 shock. A standard Gaussian VAR can still be used for producing conditional forecasts when relevant off-model information is used. We illustrate this by conditioning on official projections for a set of variables, but also by tilting to expectations from the Survey of Professional Forecasters. For Phillips curves, averaging across many conditional forecasts in a thick modelling framework offers some hedge against parameter instability.

Improving diagnostics of damage to railway catenary supports

The inspection of reinforced concrete catenary supports is a time-consuming process that necessitates a lot of time to inspect the entire fleet of supports. A large number of supports with a service life of more than 40 years require intensive monitoring and condition forecasting, which can inevitably lead to high economic costs for the work of the catenary electro-mechanics. The introduction of special technical tools to collect and process measurements could solve this problem and allow the planning of a replacement schedule for the supports based on their actual damage. The article discusses the basic factors affecting the load-bearing capacity of rein-forced concrete supports, the main damages occurring, and the procedure for carrying out inspections and assessing the current condition of the supports.

ОСНАЩЕННЯ ТЕХНІЧНИМИ ЗАСОБАМИ ПІДРОЗДІЛІВ ПСИХОЛОГІЧНОЇ РОБОТИ У СИЛАХ ОБОРОНИ: ПРО СУЧАСНИЙ СТАН І НЕВІДКЛАДНІ ЗАХОДИ

The article considers the current problems of organization and equipping with technical means of psychological work units in the defense forces. Emphasis is placed on the objective contradictions between the rapid changes in the forms and methods of information and psychological impact on personnel and its study and the actual state of technical means, their provision of troops (forces). It is determined that increasing the technical base of psychological support for the effective solution of the tasks is an urgent problem and requires in-depth research. Of paramount importance is the normative consolidation of the need to provide technical means of psychological work. The current state of provision of technical means of psychological support in the Armed Forces of Ukraine and other defense forces is analyzed. A brief description of the military mobile psychological and diagnostic complex, which undergoes departmental tests and is designed to ensure the performance of tasks as part of units and as part of individual units, groups in the field around the clock, regardless of season and time of day. The necessity of professional and psychological selection of specialists with the help of technical means is considered; assessment and forecasting of negative factors and conditions of servicemen; psychological and psychophysiological support; study of the socio-psychological climate in military units. The foreign experience of using technical means in the armed forces of the USA and the Russian Federation is analyzed. Ways to provide the latest models of the domestic system of psychological support of the defense forces to improve the psychological support of military-professional activities of personnel are proposed. It is emphasized that in order to form a unified approach to psychological support in the security and defense sector, it is necessary to create a body (structure) that would determine and coordinate activities in this direction and ensure the development of industrial production of modern technical means for psychological units.

Long-term assessment, modeling and forecast of salinity conditions of reclaimed mine dumps of Western Donbass

The neutralization of toxic mine rocks with additional of soil and loess like loam mass leads to a significant decreasing of salts migration at the contact zone. The mathematical model was working out follow general principle where mine rock is pollution source, but soil and loess like loam take place as volumetric filter for water-soluble salts. MathCAD file with commands for solving the problem forecasting the process of vertical salinization of reclaimed minelands was developed. The prospect for the numerical model using up to the most accepted range of values with experimental data shown. The irrigation of reclaimed minelands in the Western Donbass possible in the case of the dilution of the mine waters of aquifers with the Samara river water.

CURRENT STATE AND PROSPECTS OF PSYCHOLOGICAL SUPPORT IN THE ARMED FORCES OF UKRAINE

The article considers current problems of modern military psychology in the field of psychological support of militaryprofessional activity of the Armed Forces of Ukraine personnel and identifies the main content elements of psychological support in troops (forces), which include: monitoring, analysis, assessment and forecasting of negative factors and conditions; maintenance and development of psychological stability; organization of psychological selection of specialists; psychological and psychophysiological support; study of the socio-psychological climate in military units; consulting and methodological assistance to commanders on psychological support. Analyzed: normative legal acts and empirical experience of psychological support organization in the Armed Forces of Ukraine; activities of the Psychological Service, its tasks and functions; features of the professional psychological selection organization, psychological training of personnel, psychological support of hostilities, psychological assistance, psychological decompression of personnel after removal from the area of Joint operation, psychological rehabilitation and readaptation. The elements of the psychological selection system, psychological training, psychological support, psychological rehabilitation and readaptation are considered on the basis. The main emotional states and fears of servicemen at different stages of combat missions have been clarified. The organizational system of psychological assistance and rehabilitation of personnel and the task of psychological service specialists to take measures to restore the mental state of servicemen, using the methods of mental self-regulation and self-control. Ways to improve the system of psychological support in the Armed Forces of Ukraine and the security and defense sector of Ukraine are proposed.