Probabilistic forecasting of coastal wave height during typhoon warning period using machine learning methods

[Departement_IRSTEA]Eaux [TR1_IRSTEA]ARCEAU

Bayesian bootstrapping in real-time probabilistic photovoltaic power forecasting

Providing accurate forecasts for the future power generation of renewable energy power plants is critical for the power grid operation and related tasks. Probabilistic forecasts provide additional information in comparison to conventional point forecasts and can be used to retain optimal decision-making performance under uncertain future conditions. In this article, we present a hierarchical ensemble technique that combines multiple probabilistic forecasting techniques and multiple weather models (WM). In a first step, multiple probabilistic forecasting techniques create predictions on each weather model individually. Thereafter, this set of probabilistic forecasts from each WM is aggregated to an overall refined prediction using a novel dynamic weighting technique which we call gradual coopetitive soft gating. The proposed combination technique introduces a weather situation-adaptive and lead-time dependent weighting that better exploits the advantages of single predictive models in the overall ensemble. We compare the proposed method to other state of the art probabilistic forecasting methods and weather ensemble methods on 37 data sets of wind farms with multi-model weather forecasts. The proposed technique is able to achieve statistically significant performance improvements compared to other techniques.

Winter road maintenance is one of the main tasks for the Washington State Department of Transportation. Anti-icing, that is, the preemptive application of chemicals, is often used to keep the roadways free of ice. Given the preventive nature of anti-icing, accurate predictions of road ice are needed. Currently, anti-icing decisions are usually based on deterministic weather forecasts. However, the costs of the two kinds of errors are highly asymmetric because the cost of a road closure due to ice is much greater than that of taking anti-icing measures. As a result, probabilistic forecasts are needed to optimize decision making.We propose two methods for forecasting the probability of ice formation. Starting with deterministic numerical weather predictions, we model temperature and precipitation using distributions centered around the bias-corrected forecasts. This produces a joint predictive probability distribution of temperature and precipitation, which then yields the probability of ice formation, defined here as the occurrence of precipitation when the temperature is below freezing. The first method assumes that temperatures, as well as precipitation, at different spatial locations are conditionally independent given the numerical weather predictions. The second method models the spatial dependence between forecast errors at different locations. The model parameters are estimated using a Bayesian approach via Markov chain Monte Carlo.We evaluate both methods by comparing their probabilistic forecasts with observations of ice formation for Interstate Highway 90 in Washington State for the 2003–2004 and 2004–2005 winter seasons. The use of the probabilistic forecasts reduces costs by about 50% when compared to deterministic forecasts. The spatial method improves the reliability of the forecasts, but does not result in further cost reduction when compared to the first method.

To mitigate climate change, renewable energy sources are increasingly integrated into the energy system. Due to their volatility and uncertainty, smart grid applications are required to deal with this uncertainty and maintain grid stability. To operate effectively and in an automated manner, each of these applications requires a quantification of the uncertainty in future demand and generation, which probabilistic forecasts can provide. Furthermore, these applications often require specific probabilistic forecast properties, such as coverage rate and sharpness. However, existing probabilistic forecasts cannot be easily customised to exhibit these required properties. Therefore, we present a novel approach that creates loss-customised probabilistic forecasts using automated hyperparameter optimisation based on custom loss metrics. We combine a deterministic base forecaster and a conditional Invertible Neural Network to include specified uncertainty in a deterministic forecast. This uncertainty is defined by automated hyperparameter optimisation based on flexible and adaptable loss metrics, enabling the generation of loss-customised probabilistic forecasts with different properties without computationally expensive retraining. We evaluate our approach on four real-world data sets and compare the generated loss-customised forecasts with three state-of-the-art probabilistic forecasting benchmarks. We show that our approach generates probabilistic forecasts that can be customised to achieve state-of-the-art performance in either Continuous Ranked Probability Score, Pinball Loss, or Coverage Rate Error, depending on the selected customised loss metric.

Objective wind speed and direction forecasts for seven projections (for time frames of +9 to +30h) were developed with the Model Output Statistics technique (MOS) for nine DOE candidate wind turbine sites in the continental United States. Forecasts were produced twice daily, at 0000 GMT and 1200 GMT, and verified against observations by statistical analyses. Though the reliability of the forecasts was degraded by the small size of the developmental data set, the technique appears sufficiently reliable to merit further investigation. The forecast verification results show a slight tendency toward underforecasting strong winds. In general, the forecasts perform better in the eastern portion of the country than in the West. The forecasts generally decrease in accuracy with time, except for sites having very regular diurnal wind patterns, and were markedly better at the 9-h forecast than at later times. Wind observations at the WTG site were found to be useful predictors for projections up to 15 hours after forecast time at some sites. Both deterministic forecasts (actual speed) and probabilistic forecasts (probability of the speed being within specified intervals) were produced. The results suggest that larger developmental samples or larger speed intervals be used to develop probabilistic wind speed forecasts.

A review of state‐of‐the‐art short‐term wind power probabilistic forecasting models is the focus here. The improvement of the accuracy and efficiency of probabilistic forecasting models has been in the centre of attention of researchers in recent years, since the need to further comprehend and efficiently use the uncertainty of forecasts is increasing. Since the optimal operation and control of energy systems and electricity markets is one of the important aspects of performing wind power forecasts, this review focuses in short‐term probabilistic forecasting models, which could prove to be useful in the daily planning and operation of power systems. The short‐term concept of forecasts is analysed in detail, along with the case studies and examples proposed by the reviewed literature. The key advantages and disadvantages of the reviewed probabilistic forecasting methodologies are identified. Furthermore, different classifications of the reviewed works according to the data that are used to provide an accurate forecasting model are also provided. Future directions in the field of short‐term wind power probabilistic forecasting are also proposed.

Given increasing computing power, an important question is whether additional computational resources would be better spent reducing the horizontal grid spacing of a convection-allowing model (CAM) or adding members to form CAM ensembles. The present study investigates this question as it applies to CAM-derived next-day probabilistic severe weather forecasts created by using forecast updraft helicity as a severe weather proxy for 63 days of the 2010 and 2011 NOAA Hazardous Weather Testbed Spring Forecasting Experiments. Forecasts derived from three sets of Weather Research and Forecasting Model configurations are tested: a 1-km deterministic model, a 4-km deterministic model, and an 11-member, 4-km ensemble. Forecast quality is evaluated using relative operating characteristic (ROC) curves, attributes diagrams, and performance diagrams, and forecasts from five representative cases are analyzed to investigate their relative quality and value in a variety of situations. While no statistically significant differences exist between the 4- and 1-km deterministic forecasts in terms of area under ROC curves, the 4-km ensemble forecasts offer weakly significant improvements over the 4-km deterministic forecasts over the entire 63-day dataset. Further, the 4-km ensemble forecasts generally provide greater forecast quality relative to either of the deterministic forecasts on an individual day. Collectively, these results suggest that, for purposes of improving next-day CAM-derived probabilistic severe weather forecasts, additional computing resources may be better spent on adding members to form CAM ensembles than on reducing the horizontal grid spacing of a deterministic model below 4 km.

The core properties of the wave climate and its changes in the Caspian Sea are established in terms of the annual mean significant wave height and its regional changes in 2002–2013 based on the outcome of the satellite altimetry mission JASON-1. Remotely estimated wave heights are validated against properties of the empirical distribution of instrumentally measured wave heights in the southern Caspian Sea and monthly averages of visually observed wave heights at three locations. A correction for systematic differences leads to very good correspondence between monthly averaged in situ and satellite data with a typical root mean square difference of 0.06 m. The average significant wave height in the Caspian Sea is 0.5–0.7 m in the northern basin of the sea, around 1.2 m in large parts of the central and southern basins and reaches up to 1.8 m in the northern segment of the central basin. The basin-wide average wave intensity varied insignificantly in the range of 1.02–1.14 m in 2002–2013. These estimates overestimate the wave heights by about 30% because low wave conditions are ignored. Substantial and statistically significant changes in the wave height occurred in certain areas. The wave height decreased by 0.019 ± 0.007 m/yr in the eastern segment of the central basin and by 0.04 ± 0.04 m/yr in the western segment of the southern basin. These changes can be explained by an increase in the frequency of westerly winds at the expence of southerly winds. Both basin-wide and regional extreme wave heights exhibit large interannual variations but do not show any significant trend. The patterns of changes in mean and extreme wave height are different. The average wave height has increased while the extreme wave height has decreased in the eastern segment of the southern basin.

This paper deals with the assessment of hydrological predictions driven by probabilistic hybrid rainfall forecasts obtained by merging numerical weather prediction and radar‐based rainfall forecasts. Deterministic and ensemble hybrid rainfall forecasts have been utilized to provide river flow predictions on a catchment study located in the UK. A novel assessment methodology has been developed and implemented for the purpose of comparing deterministic and ensemble river flow predictions. The assessment methodology provides a measure of the degree of underestimation/overestimation characterizing the forecasts in comparison with a series of normalized reference thresholds. The analysis of the results obtained by implementing this evaluation methodology shows that the overall performance of the deterministic forecasts is very similar to that of the ensemble forecasts, with a slightly larger degree of underestimation affecting the ensemble forecasts in comparison with the deterministic forecasts. Copyright © 2012 John Wiley & Sons, Ltd.

This study investigates the probabilistic quantitative precipitation forecast (PQPF) performance of typhoons that affected Taiwan during 2011–16. In this period, a total of 19 typhoons with a land warning issued by the Central Weather Bureau (CWB) are analyzed. The PQPF is calculated using the ensemble precipitation forecast data from the Taiwan Cooperative Precipitation Ensemble Forecast Experiment (TAPEX), and the verification data, verification thresholds, and typhoon characteristics are obtained from the CWB. The overall PQPF performance of TAPEX has an acceptable reliability and discrimination ability, and the higher probability error is distributed at the mountainous area of Taiwan. The PQPF performance is significantly influenced by typhoon characteristics (e.g., typhoon tracks, sizes, and forward speeds). The PQPFs for westward-moving, large, or slow typhoons have higher reliability and discrimination ability, and lower-probability error than those for northward-moving, small, or fast typhoons, except for similar reliability between fast and slow typhoons. Because northward-moving or small typhoons have larger forecast track error, and their PQPF performance is sensitive to the accuracy of the forecast track, a higher probability error occurs than that for westward-moving or large typhoons. Furthermore, because there is no difference in track error between fast and slow typhoons, the larger track spread for slow typhoons increases the rainfall forecast spread and reduces the probability error. The orientation of Taiwan’s topography and the topographic effect also influence and increase the distribution and value of probability error for northward-moving, small, or fast typhoons. In summary, forecast track characteristics are influenced by typhoon characteristics and further affect the PQPF performance.

It is well accepted that the parent distribution for individual ocean wave heights follows the Weibull model. However this model does not simulate significant wave height which is the average of the highest one-third of some ‘n’ (n- varies) wave heights in a wave record. It is now proposed to redefine significant wave height as average of the highest one-third of a constant number (n-constant, say,n = 100) of consecutive individual wave heights. The Weibull model is suggested for simulating redefined significant wave height distribution by the method of characteristic function. An empirical support of 100.00% is established by Χ2-test at 0.05 level of significance for 3 sets of data at 0900, 1200 and 1500 hrs at Valiathura, Kerala coast. Parametric relations have been derived for the redefined significant wave height parameters such as mean, maximum one-third average, extreme wave heights, return periods of an extreme wave height and the probability of realising an extreme wave height in a time less than the designated return period.

Global atlas of extreme significant wave heights and relative risk ratios

WIREs WaterVolume 2, Issue 5 p. 593-593 ErratumFree Access Understanding the roles of modernity, science, and risk in shaping flood management This article corrects the following: Understanding the roles of modernity, science, and risk in shaping flood management Sébastien Nobert, Kristian Krieger, Florian Pappenberger, Volume 2Issue 3Wiley Interdisciplinary Reviews: Water pages: 245-258 First Published online: March 3, 2015 First published: 08 August 2015 https://doi.org/10.1002/wat2.1095AboutSectionsPDF ToolsRequest permissionExport citationAdd to favoritesTrack citation ShareShare Give accessShare full text accessShare full-text accessPlease review our Terms and Conditions of Use and check box below to share full-text version of article.I have read and accept the Wiley Online Library Terms and Conditions of UseShareable LinkUse the link below to share a full-text version of this article with your friends and colleagues. Learn more.Copy URL In Nobert et al.1, the following error was published in Figure 1 legend. Deterministic and probabilistic forecasts from the European Flood Awareness System. The blue solid line is a flood forecast using the deterministic model of the German weather service (Deutscher Wetterdienst). The blue solid line is the high-resolution forecast of ECMWF and the box-plots show the ensemble forecast of ECMWF. The text was incorrect and should have read: Deterministic and probabilistic forecasts from the European Flood Awareness System. The blue solid line is a flood forecast using the deterministic model of the German weather service (Deutscher Wetterdienst). The red solid line is the high-resolution forecast of ECMWF and the box-plots show the ensemble forecast of ECMWF. We apologize for this error. REFERENCE 1Nobert S, Krieger K, Pappenberger F. Understanding the roles of modernity, science, and risk in shaping flood management. WIREs Water 2015, 2: 245– 58. Volume2, Issue5September/October 2015Pages 593-593 ReferencesRelatedInformation

In the reliability engineering and design of offshore structures, probabilistic approaches are frequently adopted. They require the estimation of extreme quantiles of oceanographic data based on the statistical information. Due to strong correlation between such random variables as, e.g., wave heights and wind speeds (WS), application of the multivariate, or bivariate in the simplest case, extreme value theory is sometimes necessary. The paper focuses on the extension of the average conditional exceedance rate (ACER) method for prediction of extreme value statistics to the case of bivariate time series. Using the ACER method, it is possible to provide an accurate estimate of the extreme value distribution of a univariate time series. This is obtained by introducing a cascade of conditioning approximations to the true extreme value distribution. When it has been ascertained that this cascade has converged, an estimate of the extreme value distribution has been obtained. In this paper, it will be shown how the univariate ACER method can be extended in a natural way to also cover the case of bivariate data. Application of the bivariate ACER method will be demonstrated for measured coupled WS and wave height data.