Probabilistic Forecasts Research Articles

Electricity price forecasting using quantile regression averaging with nonconvex regularization

AbstractElectricity price forecasting (EPF) is an emergent research domain that focuses on forecasting the future electricity market price both deterministically and probabilistically. EPF has attracted enormous interest from both practitioners and scholars since the deregulation of the power market and wide applications of renewable energy sources, such as wind and solar energy. However, forecasting the electricity price accurately and efficiently is an extremely challenging task because of its high volatility, randomness, and fluctuation. Although quantile regression averaging (QRA) has been demonstrated to be efficacious in probabilistic EPF since the global energy forecasting competition in 2014 (GEFCom2014), it is sensitive to nuisance variables especially when the number of variables is large. The forecasting accuracy will be negatively affected by these nuisance variables. To address these challenges, this study investigates a nonconvex regularized QRA in probabilistic forecasting. Two types of nonconvex regularized QRA select the important inputs obtained from point forecasting to obtain more accurate forecasting outcomes. To demonstrate the effectiveness of the proposed EPF model, two real datasets from the European power market are considered.

Earthquake forecasting from paleoseismic records

Forecasting large earthquakes along active faults is of critical importance for seismic hazard assessment. Statistical models of recurrence intervals based on compilations of paleoseismic data provide a forecasting tool. Here we compare five models and use Bayesian model-averaging to produce time-dependent, probabilistic forecasts of large earthquakes along 93 fault segments worldwide. This approach allows better use of the measurement errors associated with paleoseismic records and accounts for the uncertainty around model choice. Our results indicate that although the majority of fault segments (65/93) in the catalogue favour a single best model, 28 benefit from a model-averaging approach. We provide earthquake rupture probabilities for the next 50 years and forecast the occurrence times of the next rupture for all the fault segments. Our findings suggest that there is no universal model for large earthquake recurrence, and an ensemble forecasting approach is desirable when dealing with paleoseismic records with few data points and large measurement errors.

WoFS and the Wisdom of the Crowd: The Impact of the Warn-on-Forecast System on Hourly Forecasts during the 2021 NOAA Hazardous Weather Testbed Spring Forecasting Experiment

Abstract During the 2021 Spring Forecasting Experiment (SFE), the usefulness of the experimental Warn-on-Forecast System (WoFS) ensemble guidance was tested with the issuance of short-term probabilistic hazard forecasts. One group of participants used the WoFS guidance, while another group did not. Individual forecasts issued by two NWS participants in each group were evaluated alongside a consensus forecast from the remaining participants. Participant forecasts of tornadoes, hail, and wind at lead times of ∼2–3 h and valid at 2200–2300, 2300–0000, and 0000–0100 UTC were evaluated subjectively during the SFE by participants the day after issuance, and objectively after the SFE concluded. These forecasts exist between the watch and the warning time frame, where WoFS is anticipated to be particularly impactful. The hourly probabilistic forecasts were skillful according to objective metrics like the fractions skill score. While the tornado forecasts were more reliable than the other hazards, there was no clear indication of any one hazard scoring highest across all metrics. WoFS availability improved the hourly probabilistic forecasts as measured by the subjective ratings and several objective metrics, including increased POD and decreased FAR at high probability thresholds. Generally, expert forecasts performed better than consensus forecasts, though expert forecasts overforecasted. Finally, this work explored the appropriate construction of practically perfect fields used during subjective verification, which participants frequently found to be too small and precise. Using a Gaussian smoother with σ = 70 km is recommended to create hourly practically perfect fields in future experiments. Significance Statement This work explores the impact of cutting-edge numerical weather prediction ensemble guidance (the Warn-on-Forecast System) on severe thunderstorm hazard outlooks at watch-to-warning time scales, typically between 1 and 6 h of lead time. Real-time forecast products in this time frame are currently provided on an as-needed basis, and the transition to continuous probabilistic forecast products across scales requires targeted research. Results showed that hourly probabilistic participant forecasts were skillful subjectively and statistically, and that the experimental guidance improved the forecasts. These results are promising for the implementation and value of the Warn-on-Forecast System to provide improved hazard timing and location guidance within severe weather watches. Suggestions are made to aid future subjective evaluations of watch-to-warning-scale probabilistic forecasts.

Deep Learning for Postprocessing Global Probabilistic Forecasts on Subseasonal Time Scales

Abstract Subseasonal weather forecasts are becoming increasingly important for a range of socioeconomic activities. However, the predictive ability of physical weather models is very limited on these time scales. We propose four postprocessing methods based on convolutional neural networks to improve subseasonal forecasts by correcting systematic errors of numerical weather prediction models. Our postprocessing models operate directly on spatial input fields and are therefore able to retain spatial relationships and to generate spatially homogeneous predictions. They produce global probabilistic tercile forecasts for biweekly aggregates of temperature and precipitation for weeks 3–4 and 5–6. In a case study based on a public forecasting challenge organized by the World Meteorological Organization, our postprocessing models outperform the bias-corrected forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF), and achieve improvements over climatological forecasts for all considered variables and lead times. We compare several model architectures and training modes and demonstrate that all approaches lead to skillful and well-calibrated probabilistic forecasts. The good calibration of the postprocessed forecasts emphasizes that our postprocessing models reliably quantify the forecast uncertainty based on deterministic input information in the form of ECMWF ensemble mean forecast fields only.

Visualizing the Shelf Life of Population Forecasts: A Simple Approach to Communicating Forecast Uncertainty

It is widely appreciated that population forecasts are inherently uncertain. Researchers have responded by quantifying uncertainty using probabilistic forecasting methods. Yet despite several decades of development, probabilistic forecasts have gained little traction outside the academic sector. Therefore, this article suggests an alternative and simpler approach to estimating and communicating uncertainty which might be helpful for population forecast practitioners and users. Drawing on the naïve forecasts idea of Alho, it suggests creating “synthetic historical forecast errors” by running a regular deterministic projection model many times over recent decades. Then, borrowing from perishable food terminology, the “shelf life” of forecast variables, the number of years into the future the forecast is likely to remain “safe for consumption” (within a specified error tolerance), is estimated from the “historical” errors. The shelf lives are then applied to a current set of forecasts and presented in a simple manner in graphs and tables of forecasts using color-coding. The approach is illustrated through a case study of 2021-based population forecasts for Australia. It´s concluded that the approach offers a relatively straightforward way of estimating and communicating population forecast uncertainty.

The impact of probabilistic tornado warnings on risk perceptions and responses.

Many warnings issued to members of the public are deterministic in that they do not include event likelihood information. This is true of the current polygon-based tornado warning used by the American National Weather Service, although the likelihood of a tornado varies within the boundaries of the polygon. To test whether adding likelihood information benefits end users, two experimental studies and one in-person interview study were conducted. The experimental studies compared five probabilistic formats, two with color and three with numeric probabilities alone, to the deterministic polygon. In both experiments, probabilistic formats led to better understanding of tornado likelihood and higher trust than the polygon alone, although color-coding led to several misunderstandings. When the polygon boundary was drawn at 10% chance, those using probabilistic formats made fewer correct shelter decisions at low probabilities and more correct shelter decisions at high probabilities compared to those using the deterministic warning, although overall decision quality, operationalized as expected value, did not differ. However, when the polygon boundary was drawn around 30%, participants with probabilistic forecasts had higher expected value. The interview study revealed that, although tornado-experienced individuals would not shelter at 10% chance, they would take intermediate actions, such as information-seeking and sharing. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Prediction of Tsunami Alert Levels Using Deep Learning

AbstractTsunami simulations require powerful computational resources to be performed efficiently. Although the modern graphics processing units (GPUs) allow the acceleration of this kind of simulations, they can still last many minutes or even hours for simulations which have to deal with very high spatial resolutions or simulation times. In this paper, we propose a method to predict the alert or inundation level of a tsunami generated by an earthquake using deep learning methods. In particular, we train multilayer perceptron (MLP) neural networks for predicting the alert level due to a tsunami at given coastal locations. Ensemble methods are used to improve the predictions of the neural networks. Tsunamis caused by ruptures of several fault segments at different time instants, application to real events, probabilistic forecasting and comparison with other machine learning algorithms are also addressed. Results on realistic scenarios confirm that good accuracies are obtained. The inference times of the trained networks and ensembles are also very low, lasting less than one second to predict the results of thousands of simulations. The proposed method could be used in a tsunami early warning system along with the application of scaling laws.

Bayesian Optimization - LSTM Modeling and Time Frequency Correlation Mapping Based Probabilistic Forecasting of Ultra-short-term Photovoltaic Power Outputs

Bayesian Optimization - LSTM Modeling and Time Frequency Correlation Mapping Based Probabilistic Forecasting of Ultra-short-term Photovoltaic Power Outputs

Adaptive Probabilistic Forecasting of Electricity (Net-)Load

Adaptive Probabilistic Forecasting of Electricity (Net-)Load

Causal Effect Estimation With Global Probabilistic Forecasting: A Case Study of the Impact of Covid-19 Lockdowns on Energy Demand

Causal Effect Estimation With Global Probabilistic Forecasting: A Case Study of the Impact of Covid-19 Lockdowns on Energy Demand

Seasonal forecasting of local-scale soil moisture droughts with Global BROOK90: a case study of the European drought of 2018

Abstract. Prolonged deficit of soil moisture can result in significant ecosystem and economical losses. General slowdown of vegetation growth and development, withering of foliage cover, reduction of carbon, nutrients and water cycling, increase of fire and insect outbreaks are just a few examples of soil moisture drought impacts. Thus, an early and timely warning via monitoring and forecast could help to prepare for a drought and manage its consequences. In this study, a new version of Global BROOK90, an automated framework to simulate water balance at any location, is presented. The new framework integrates seasonal meteorological forecasts (SEAS5 forecasting system) from European Centre for Medium-Range Weather Forecasts (ECMWF). Here we studied how well the framework can predict the soil moisture drought on a local scale. Twelve small European catchments (from 7 to 115 km2) characterized by various geographical conditions were chosen to reconstruct the 2018–2019 period, when a large-scale prolonged drought was observed in Europe. Setting the ERA5-forced soil moisture simulations as a reference, we analysed how the lead time of the SEAS5 hindcasts influences the quality of the soil moisture predictions under drought and non-drought conditions. It was found that the hindcasted soil moisture fits well with the reference model runs only within the first (in some cases until the second and third) month of lead time. Afterwards, significant deviations up to 50 % of soil water volume were found. Furthermore, within the drought period the SEAS5 hindcast forcings resulted in overestimation of the soil moisture for most of the catchment, indicating an earlier end of a drought period. Finally, it was shown that application of the probabilistic forecast using the ensembles' quantiles to account for the uncertainty of the meteorological input is reasonable only for a lead time of up to 3 months.

Разработка алгоритма комплексной методики оценки технического состояния цилиндропоршневой группы судовой двигательной установки на основе показателей масляной системы

The algorithm of a complex methodology for assessing the technical condition of the cylinder piston group of a marine propulsion system is being investigated. Wear is a continuous process characteristic of all working mechanisms. Studies aimed at identifying factors contributing to the degradation of system elements of devices provide the basis for the development of preventive measures to reduce their effects. Knowledge of the technical condition of marine engine components is important for the development of measures that increase the reliability of equipment and reduce the risks of emergency situations. Some of the main approaches to modeling and evaluating the state of the cylinder-piston system of marine diesel engines are presented. To solve the problems of assessing the technical condition of the cylinder piston group during operation, classical methods of statistical data analysis are considered, methods that artificially increase the size of the data sample are proposed, machine learning methods are analyzed and the most effective for use are determined. An integrated approach is being created to study the operation process of a cylinder-piston group of diesel marine engines based on a combination of statistical methods, machine learning methods and probabilistic forecasting. A diagram of the properties of the studied parameters is illustrated for constructing a model for analyzing a cylinder-piston group system. Machine learning algorithms used to study systems are presented. The proposed technique allows, using the results of indirect measurements (data from lubrication analyses), to determine the technical condition of the engine system, in particular the cylinder piston group.

Probabilistic forecast of electric vehicle charging demand: analysis of different aggregation levels and energy procurement

Electric vehicles (EVs) are expected to be vital in transitioning to a low-carbon energy system. However, integrating EVs into the power grid poses significant challenges for grid operators and energy suppliers, especially regarding the uncertainty and variability of EV charging demand. Accurate forecasting of EV charging demand is essential for optimal power system integration, yet previous studies have often only considered point predictions that are inadequate for risk assessment. Therefore, this paper compares different probabilistic forecasting models for the short-term prediction of EV charging demand at various aggregation levels, using a large and novel dataset of over 350,000 charging processes at more than 500 locations across Germany. The performance of both machine learning and deep learning methods is evaluated against a naïve benchmark model, and the impact of data availability on the forecasting models is investigated. Further, the paper examines the effects of forecast accuracy on energy procurement, which has so far received minor attention in the literature. The results show that machine learning methods such as Ada Boosting and Random Forest yield robust results with a normalized root mean square error of 0.42 and 0.41 and a mean absolute scaled error of 0.36 and 0.34 at the highest aggregation level. Furthermore, the results show the influence of different site compositions on the forecast quality and how many charging points are likely to yield a robust forecast. Energy and fleet managers can use the described method to reliably predict the required energy quantities for fleets of sufficient size and procure them at low risk.

Probabilistic seasonal precipitation forecasts using quantiles of ensemble forecasts

Seasonal precipitation forecasting is vital for weather-sensitive sectors. Global Circulation Models (GCM) routinely produce ensemble Seasonal Climate Forecasts (SCFs) but suffer from issues like low forecast resolution and skills. To address these issues in this study, we introduce a post-processing method, Quantile Ensemble Bayesian Model Averaging (QEBMA). It utilises quantiles from a GCM ensemble forecast to create a pseudo-ensemble forecast. Through their reasonable linear relationships with observations, each pseudo-member connects a hurdle distribution with a point mass at zero for dry months and a gamma distribution for wet months. These distributions are mixed to construct a forecast probability distribution with their weights, proportional to the quantiles’ historical forecast performance. QEBMA is applied to three GCMs, including GloSea5 from the United Kingdom, ECMWF from Europe and ACCESS-S1 from Australia, for monthly precipitation forecasts in 32 locations across four climate zones in Australia. Leave-one-month-out cross-validation results illustrate that QEBMA enhances forecast skills compared to raw GCMs and other post-processing techniques, including quantile mapping and Extended Copula Post-Processing (ECPP), for forecast lead time of 0 to 2 months, based on five metrics. The skill improvements achieved by QEBMA are often statistically significant, particularly when compared to raw GCM forecasts across the 32 study locations. Among these post-processing models, only QEBMA consistently outperforms the SCF benchmark climatology, offering a promising alternative for improving seasonal precipitation forecasts.

Probabilistic Forecast of Multiphase Transport Under Viscous and Buoyancy Forces in Heterogeneous Porous Media

AbstractWe develop a probabilistic approach to map parametric uncertainty to output state uncertainty in first‐order hyperbolic conservation laws. We analyze this problem for nonlinear immiscible two‐phase transport in heterogeneous porous media in the presence of a stochastic velocity field. The uncertainty in the velocity field can arise from incomplete descriptions of either porosity field, injection flux, or both. This uncertainty leads to spatiotemporal uncertainty in the saturation field. Given information about spatial/temporal statistics of spatially correlated heterogeneity, we leverage the method of distributions to derive deterministic equations that govern the evolution of pointwise cumulative distribution functions (CDFs) of saturation for a vertical reservoir, while handling the manipulation of multiple shocks arising due to buoyancy forces. Unlike the Buckley‐Leverett equation, the equation describing the fine‐grained CDF is linear in space and time. Ensemble averaging of the fine‐grained CDF results in the CDF of saturation. Thus, we give routes to circumventing the computational cost of Monte Carlo simulations (MCS), while obtaining a pointwise description of the saturation field. We conduct a set of numerical experiments for one‐dimensional transport, and compare the obtained saturation CDFs, against those obtained using MCS as our reference solution, and the statistical moment equation method. This comparison demonstrates that the CDF equations remain accurate over a wide range of statistical properties, that is, standard deviation and correlation length of the underlying random fields, whereas the corresponding low‐order statistical moment equations significantly deviate from the MCS results, except for very small values of standard deviation and correlation length.

Probabilistic forecasting of construction labor productivity metrics

This study investigates the possibility of doing probabilistic forecasting of construction labor productivity metrics for both long-term and short-term estimates. The research aims to evaluate autoregressive forecasting models, which may help decision-makers with information currently unavailable in construction projects. Unlike point forecasts, the proposed method employs probabilistic forecasting, offering additional valuable insights for decision-makers. The distributional information is obtained by updating the moments of the distribution during training. Two datasets are used to evaluate the models: one collected from an entire construction site for long-term forecasting and one from an individual worker for short-term forecasting. The models aim to predict the state of direct work, indirect work, and waste. Several models are trained using different hyperparameters. The models are tuned on the number of trees and the regularization used. The presented method gives estimates of future levels of direct work, indirect work, and waste, which will add value to future processes.

Probabilistic electricity price forecasting based on penalized temporal fusion transformer

AbstactIn the deregulated electricity market, it is increasingly important to accurately predict the fluctuating, nonlinear, and high‐frequent electricity price for market decision‐making. However, the uncertainties associated with electricity prices, such as non‐stationarity, nonlinearity, and high volatility, pose critical difficulties for electricity price forecasting (EPF). Unlike point forecasting, which provides only a single, deterministic estimate of future prices, probabilistic forecasting gives a more comprehensive and nuanced picture of future price dynamics, which can help market participants make better‐informed decisions when facing uncertainty. Therefore, in this paper, we propose a robust deep learning method for multi‐step probabilistic forecasting. First, we use the least absolute shrinkage and selection operator (LASSO) in the expert model to generate point forecasts. Second, we introduce the smoothly clipped absolute deviation regularization term, a nonconvex penalty with proven oracle properties in model selection, into temporal fusion transformers. Finally, we employ the proposed model to integrate point forecasts to give probabilistic forecasts. To evaluate the proposed forecasting model, real‐data experiments are conducted in the Nord Pool electricity market and the Polish Power Exchange market. Empirical results show that the proposed model has demonstrated superior probabilistic forecasting performances compared with other competitors and has proven its effectiveness in real‐world applications.

Probabilistic Forecast of Ecological Drought in Rivers Based on Numerical Weather Forecast from S2S Dataset

Ecological droughts in rivers, as a new type of drought, have been greatly discussed in the past decade. Although various studies have been conducted to identify and evaluate ecological droughts in rivers from different indices, a forecast model for this type of drought is still lacking. In this paper, a numerical weather forecast, a hydrological model, and a generalized Bayesian model are employed to establish a new general framework for the probabilistic forecasting of ecological droughts in rivers, and the Daitou section in China is selected as the study area to examine the performance of the new framework. The results show that the hydrological model can accurately simulate the monthly streamflow with a Nash–Sutcliffe efficiency of 0.91 in the validation period, which means that the model can be used to reconstruct the natural streamflow from the impact of an upstream reservoir. Based on a comparison of ecological drought events from the observed and model-simulated streamflow series, the events from the observed series have a larger deficit volume and a longer duration of ecological droughts after 2014, indicating that human activities may lead to a more severe situation of ecological droughts. Furthermore, due to the uncertainty of precipitation forecasts, a probabilistic precipitation forecast is employed for probabilistic ecological drought forecasting. Compared to the deterministic forecast, the probabilistic ecological drought forecast has better performance, with a Brier score decrease of 0.35 to 0.18 and can provide more information about the risk of ecological droughts. In general, the new probabilistic framework developed in this study can serve as a basis for the development of early-warning systems and countermeasures for ecological droughts.

Probabilistic CDF-based load forecasting model in a power distribution system

The study searches for a probabilistic forecasting model for electric power demand based on the correlation between weather temperature and electric power demand using hourly time series data spanning a year. The model is based on the temperature and power demand data's cumulative probability distribution functions or CDFs. In probabilistic forecasting, a range of potential values and their associated probabilities are predicted in addition to a single value for a given range. The qualities of CDF modeling allow it to cover these uncertainties. For scenario 1, case 2, and case 3, the mean absolute percentage error (MAPE)-based forecasting accuracy for the hourly load demand is 3.93, 4.64, and 2.56, respectively. The Gaussian distribution-based CDFs' capacity to forecast outside of the present data range is an extra advantage. The world's electric power networks are growing increasingly intricate and unpredictable through the integration of several distributed energy resources (DERs) and cutting-edge technology from renewable energy resources (RERs). Other variables, such as variations in weather patterns, shifts in the status of the economy, or adjustments to energy policies, can also add to uncertainty and not be foreseen. A body of literature demonstrates a shortage of research on LTLF and general-purpose forecasting methods. The proposed approach is flexible and might establish a standard for many different forecasting tasks. The proposed method is intended to be a flexible strategy that may be used for different utilities with varying time horizons.

Hierarchical Time Series Forecasting in Emergency Medical Services

Accurate forecasts of ambulance demand are crucial inputs when planning and deploying staff and fleet. Such demand forecasts are required at national, regional, and sub-regional levels and must take account of the nature of incidents and their priorities. These forecasts are often generated independently by different teams within the organization. As a result, forecasts at different levels may be inconsistent, resulting in conflicting decisions and a lack of coherent coordination in the service. To address this issue, we exploit the hierarchical and grouped structure of the demand time series and apply forecast reconciliation methods to generate both point and probabilistic forecasts that are coherent and use all the available data at all levels of disaggregation. The methods are applied to daily incident data from an ambulance service in Great Britain, from October 2015 to July 2019, disaggregated by nature of incident, priority, managing health board, and control area. We use an ensemble of forecasting models and show that the resulting forecasts are better than any individual forecasting model. We validate the forecasting approach using time series cross-validation.