Error Decomposition Research Articles

THE ANALYSIS OF THE TRADE BALANCE OF TURKEY IN RESPONSE TO OIL PRICE CHANGES

This study empirically examines the effects of oil prices on the trade balance of Turkey, which depends heavily on oil imports. Unlike the other studies on this subject, in this study, the relationship between oil prices and trade balance is investigated by regime-dependent impulse response functions and forecast error decompositions based on multivariate Threshold VAR (TVAR) model comparing with linear VAR model. The findings suggest that, the relationship between oil prices and trade balances is non-linear. In the regime of higher oil price volatility, components of trade balance respond stronger to oil price shocks than lower regime and linear VAR model. Oil price increases in the high regime deteriorates the total trade balance, non-oil and non-gas trade balance and intermediate trade balance; on the other hand, consumption trade balance of Turkey is positively affected from oil price increases. Additionally, consumption goods trade balance found to be the mostly affected by oil price shocks according to the impulse-response functions and variance decomposition analysis. Finally, the findings obtained from linear VAR and lowest regime are generally similar and has less effect on the trade balance components.

Comprehensive Evaluation and Error-Component Analysis of Four Satellite-Based Precipitation Estimates against Gauged Rainfall over Mainland China

The Integrated Multi-Satellite Retrievals for Global Precipitation Measurement (IMERG) V06 product has been widely studied, but the errors and the source of the errors within IMERG over diverse climate regions still need to be quantified. To this end, the final run gauge-calibrated IMERG V06 (V06C) and uncalibrated IMERG V06 (V06UC) products are comprehensively evaluated here against 2088 precipitation gauges acquired between March 2014 and June 2018 over China. Moreover, V06C and V06UC rainfall estimates are compared against the Precipitation Estimation from Remotely Sensed Imagery using Artificial Neural Networks (PERSIANN)-Climate Data Record (CDR) and the Climate Prediction Center morphing technique (CMORPH) gauge-satellite blended (BLD) products. Continuous statistical indices and two error decomposition schemes are used to quantify their performance. Key results are as follows. (1) Except for V06UC’s relatively high underestimation over the Tibetan Plateau (TP) and high overestimation over Xinjiang (XJ), Northeastern China (DB), and Northern China (HB) and CDR’s severe overestimation over TP, all four satellite-based precipitation products can generally capture the spatial pattern of precipitation over China. Moreover, the satellite-based precipitation estimates agree better with gauge observations over humid regions than over semi-humid, semi-arid, and arid regions. (2) All the statistical indicators show that CDR has the worst performance, whereas BLD is the best precipitation product. As for the two IMERG products, V06C has improved V06UC’s precipitation estimate. Results show that the gauge calibration algorithm (GCA) used in IMERG has active effect in terms of r, POD, and CSI. (3) Within all subregions, all four satellite-based precipitation products demonstrate their worst performance over the arid XJ region which exhibits the highest FAR and lowest POD and CSI values among all regions. (4) In terms of intensity distribution, for summer over China, the four satellite-based precipitation products generally overestimate the frequency of moderate precipitation and light precipitation events (<25 mm/day) and underestimate heavy precipitation events (>42 mm/day). (5) The relative bias ratio (RBR) analysis shows that the contribution of missed precipitation tends to be lower over wetter regions. In addition, for the same climate region, the contribution of missed precipitation is clearly lower in summer than in winter. In summer, false precipitation dominates the total error, whereas missed and false precipitation are the two leading error sources in winter. Future algorithm refinement efforts should focus on decreasing FAR in summer and winter and improving missed snow events during the winter.

QRF4P‐NRT: Probabilistic Post‐Processing of Near‐Real‐Time Satellite Precipitation Estimates Using Quantile Regression Forests

AbstractAccurate and reliable near‐real‐time satellite precipitation estimation is of great importance for operational large‐scale flood forecasting and drought monitoring. The state‐of‐the‐art precipitation post‐processing model is based on a deterministic approach to construct relationships between satellites estimates and ground observations. We propose a probabilistic postprocessor, the Probabilistic Post‐Processing of Near‐Real‐Time Satellite Precipitation Estimates using Quantile Regression Forests (QRF4P‐NRT), based on quantile modeling, yielding both deterministic and probabilistic predictions. The experimental design incorporates different solutions of near‐real‐time predictors to further improve the model performance. Using the Integrated Multi‐satellitE Retrievals Early Run for Global Precipitation Measurement Mission (IMERG‐E) product as an example, we illustrate that the proposed method significantly improves the overall quality of the raw IMERG‐E and is also superior to the bias‐corrected product (IMERG Final Run, IMERG‐F) at daily scale in a complex mountain basin. Evaluations of the corrected IMERG‐E, raw IMERG‐E, and IMERG‐F using ground observation show that the corrected IMERG‐E improves correlation coefficients (0.7), mean error (−0.14 mm/day) and root mean square error (3.3 mm/day) relative to the raw IMERG‐E (0.31, −0.72 and 5.5 mm/day) and IMERG‐F (0.34, −0.09 and 6.0 mm/day). The error decomposition further confirms that the QRF4P‐NRT improves on the various deficiencies of the raw IMERG‐E product. The ensemble assessment also demonstrates that the quantile outputs provide reliable prediction spread and sharp prediction intervals. The promising results indicate the great potential of the proposed method for probabilistic post‐processing for near‐real‐time satellite precipitation estimates, and for further applications such as hydrological ensemble forecasting.

Harmonic analysis of the arctangent function regarding the angular error introduced by superimposed Fourier series for application in sine/cosine angle encoders

We present a rigorous analytical method for harmonic analysis of the angular error of rotary and linear encoders with sine/cosine output signals in quadrature that are distorted by superimposed Fourier series. To calculate the angle from measured sine and cosine encoder channels in quadrature, the arctangent function is commonly used. The hence non-linear relation between raw signals and calculated angle—often thought of as a black box—complicates the estimation of the angular error and its harmonic decomposition. By means of a Taylor series expansion of the harmonic amplitudes, our method allows for quantification of the impact of harmonic signal distortions on the angular error in terms of harmonic order, magnitude and phase, including an upper bound on the remaining error term—without numerical evaluation of the arctangent function. The same approximation is achieved with an intuitive geometric approximation in the complex plane, validating the results. Interaction effects between harmonics in the signals are considered by higher-order Taylor expansion. The approximations show an excellent agreement with the exact calculation in numerical examples even in case of large distortion amplitudes, leading to practicable estimates for the angular error decomposition.

What drives updates of inflation expectations? A Bayesian VAR analysis for the G‐7 countries

AbstractInflation expectations play a crucial role for monetary policy transmission, having become even more important since the emergence of unconventional monetary policy. Based on survey data provided by Consensus Economics, we assess determinants of professional inflation expectations for the G7 economies, emphasising the role of international spillovers arising from the United States in inflation expectations. We also consider several other determinants of inflation expectation updates such as changes in the path of monetary policy, oil price shocks and changes in uncertainty measures. Based on a Bayesian VAR, we find significant evidence of international spillovers stemming from expectations about US monetary policy based on impulse‐response functions and forecast error decompositions. We provide similar evidence on spillovers from the dispersion across inflation forecasts, too.

Performance of HAILCAST and the Lightning Potential Index in simulating hailstorms in Croatia in a mesoscale model – Sensitivity to the PBL and microphysics parameterization schemes

Hailstorms, although extremely damaging severe weather hazards, remain a very challenging phenomenon to predict. To better understand dynamic processes and model performance, which can be helpful in forecasting hailstorms, three selected hailstorms in Croatia are simulated with the WRF model at convection-permitting (1 km) grid spacing using the HAILCAST module. In addition, the performance of the Lightning Potential Index (LPI) algorithm in representing the observed lightning activity during the selected hailstorms is analyzed. A multiphysics ensemble of 12 sensitivity simulations with the combinations of four different microphysics and three different planetary boundary layer parameterization (PBL) schemes is adopted to assess the forecasting ability of HAILCAST and LPI and their sensitivity to the choice of microphysics and PBL parameterization schemes. First, the model's ability to reproduce surface measurements of 2-m temperature, 2-m relative humidity, 2-m equivalent potential temperature and 10-m wind are examined using root mean square error (RMSE) decomposition. Then, the LPI is assessed against lightning observations via the object-based Structure-Amplitude-Location (SAL) method. Finally, an upscaled neighborhood verification method is proposed to assess HAILCAST against hail observations from the Croatian hailpad network. The results show that the observed hail and lightning activity is represented well by the model. There is a greater sensitivity to the choice of microphysics scheme than the PBL scheme, with National Severe Storms Laboratory double-moment scheme (NSSL2) microphysics scheme differing the most among the entire sensitivity ensemble. Nonetheless, both HAILCAST and LPI show promising performance in simulating observed hail and lightning activity, although HAILCAST tends to overestimate the area affected by hail. Nonetheless, the discrepancies between model configurations highlight the importance of simulating convection correctly to obtain a meaningful forecast of hail and lightning.

A wind power forecasting method based on optimized decomposition prediction and error correction

To reduce the effect of nonlinearity and volatility in the wind power time sequence, a two-stage short-term wind power forecasting method based on optimized decomposition prediction and error correction is proposed. In the first stage, in order to improve the decomposition effect of variational mode decomposition (VMD), the decomposition loss is defined as the evaluation criterion to guide the parameter setting of VMD, and flower pollination algorithm (FPA) is utilized to automatically optimize the parameters of VMD. Then the complex wind power sequence is decomposed into simple intrinsic mode functions (IMFs). Besides, bi-directional long short-term memory (BiLSTM) neural network is built for each IMF to explore the deep time-series features of wind power in both past and future directions. In the second stage, to reduce the correlation among meteorological factors, principal component analysis (PCA) is employed to convert the multi-dimensional meteorological factors into low-dimensional principal components. Then, with the input of IMFs and principal component, an error correction model based on BiLSTM neural network is established to reduce the inherent error of the model. The experimental results show that the proposed method has higher prediction accuracy than the traditional methods in single-step and multi-step ahead forecasting.

Monitoring multistage multivariate therapeutic processes using risk‐adjusted model‐based group multivariate EWMA control chart

AbstractThere exist multitude of therapeutic processes and the results are commonly observed during various dependent steps. For studying such processes that are referred to as multistage therapeutic processes, two concepts are of particular importance; risk adjustment and cascade property. To monitor such processes, a variety of control charts including model‐based control charts are used. In order to design model‐based control charts, analysts must first recognize a suitable model to identify the multistage processes by considering process risks and cascade property. Based on the identified model, the control charts can be proposed. In this study, a risk‐adjusted time‐variant linear state space model is introduced. Afterward, the model order and its parameters are estimated based on Hankel singular value decomposition (HSVD) and prediction error minimization (PEM) methods. Then, the group multivariate exponentially weighted moving average (GMEWMA) control chart is used to monitor a multistage multivariate therapeutic process. To evaluate the performance of the model‐based control chart, a simulation study as well as a two‐stage thyroid cancer surgery was used. Results show that the proposed control chart performs well for predicting and monitoring of multistage multivariate therapeutic processes in real world.

Bearing Fault Feature Extraction Method Based on GA-VMD and Center Frequency

To promote the effect of variational mode decomposition (VMD) and further enhance the recognition performances of bearing fault signals, genetic algorithm (GA) is applied to optimize the combination of VMD parameters in this paper, and GA-VMD algorithm is put forward to improve the decomposition accuracy of VMD. In addition, combined with the center frequency, a feature extraction method based on GA-VMD and center frequency is proposed to ameliorate the difficulty of bearing fault feature extraction. Firstly, the bearing signal is decomposed into a series of intrinsic mode components (IMFs) by GA-VMD. Then, the Center Frequency of IMFs is extracted, and the recognition rate is calculated by k-nearest neighbor (KNN) algorithm. Simulation signal experiments state clearly that, compared with manual parameter setting-VMD algorithm and parameter optimization VMD algorithm based on particle swarm optimization (PSO), the decomposition result of GA-VMD has a smaller root mean square error and higher decomposition accuracy, which verifies the effectiveness of GA-VMD. The experimental results demonstrate that, by comparison with the feature extraction method based on envelope entropy, the feature extraction method based on center frequency has better inter class separability and higher mean recognition rate (the highest recognition rate of single feature is 94.5%, and in the case of multiple features, the recognition rate reaches 100% when four features are extracted) and can realize the accurate identification of different bearing fault signals.

Pose error prediction and real-time compensation of a 5-DOF hybrid robot

This paper proposes a new calibration method for a 5-DOF hybrid robot, concentrating particularly on addressing the contradiction between measurement efficiency and calibration accuracy and the real-time compensation with high precision. The approach involves two successive steps: (1) an error prediction model based on a back propagation neural network (BPNN) and the Denavit-Hartenberg (D-H) method is established by the strategy of pose error decomposition; (2) an embedded joint error compensator based on a BPNN is designed to achieve real-time compensation with high precision. Experimental verification shows that the maximum position/orientation errors can be reduced by 87.05%/85.62% over the entire workspace of the robot after calibration.

Ground validation and error decomposition for six state-of-the-art satellite precipitation products over mainland China

Evaluating the quality of satellite precipitation products (SPPs) is crucially important for SPPs' applications and improvements. This study aims to comprehensively evaluate the accuracy of six widely used SPPs (GSMaP, IMERG, TMPA, CMORPH, PERSIANN, and CHIRPS) from 2000 to 2017 over mainland China using 2372 rain gauges. The performance of SPPs at different spatio-temporal scales and altitudes are explored. The probability density function (PDF) at different precipitation intensities is also considered. In addition, special attention has been paid to analyze the error components of SPPs from different sources. Results demonstrate that: (1) GSMaP outperforms other SPPs with good statistical metrics, followed by IMERG. PERSIANN and CHIRPS have more space for improvement. All SPPs perform well in summer while worse in winter. Meanwhile, the accuracy of all SPPs varies region by region, which is better in southeast coastal basins than in northwest inland basins. (2) The overall performance in low-altitude regions is superior to high-altitude regions. The KGE (or RMSE) shows a significant negative (or positive) correlation with altitude, whereas POD, FAR, and CSI exhibit a slight dependence on altitude. (3) TMPA can well reproduce the PDF of different precipitation intensities. All SPPs' PDF is more consistent with gauges for moderate (5–10 mm/d) and heavy precipitation (10–50 mm/d), while deviates from gauges for tiny/light (0.1–5 mm/d) and violate precipitation (>50 mm/d). (4) The error components of each SPP could be larger than total errors, and the false bias is the major error source. GSMaP achieves a better performance with low hit and missed bias, whereas CHIRPS behaves poorly with large hit, missed and false bias. On the whole, the study demonstrates the error characteristics and accuracy performance of six mainstream SPPs over mainland China, which is expected to provide valuable information for hydrometeorology applications.

Financial leverage interactions: evidence from US households and government sectors

ABSTRACT Applying VAR/SVAR analysis to the national balance sheet data of the US, this paper provides evidence that the households markedly interact with those of government sectors through the channel of financial leverage, which is defined as the liabilities-to-assets ratio. In particular, the impulse-response and forecasting error decomposition analysis further show that the federal government plays an important role in absorbing the leverage shocks in households. Nevertheless, it should be emphasized that this role of the federal government as somewhat of a macroeconomic stabilizer also costs it heavily in view of its escalating leverage over time. Among other concerns, this highly leveraged financial position renders the federal balance sheet more vulnerable to macro-financial risks, thus reducing the room for manoeuvre for countercyclical policies. Finally, with a relatively low and stable leverage ratio, the state/local governments seem to be less involved in such interactions. However, their prudent balance sheet position also implies that they play a minor role in fiscal measures supporting households during economic downturns.

Оценка влияния глобальных шоков на российскую экономику в рамках факторной модели

In this study, we estimate the contribution of global demand, supply and commodity shocks to the dynamics of Russian macroeconomic variables. The main tool used in this work is a factor augmented vector autoregression (FAVAR) that allows extracting global factors from a wide range of variables. Recursive and sign restrictions are used to identify global shocks. Russian economy is represented by a large set of informational series aggregated into a small number of factors. FAVAR approach allows for extended inference on the reaction of Russian macroeconomic variables to global shocks. Impulse response function analysis shows that Russian economy is affected by all three specifi ed global shocks and forecast error decompositions indicate that those shocks account for nearly 80 per cent of key variables dynamics. We also showed that global demand and global commodity shocks were more crucial compared to the third type of shocks in explaining macroeconomic dynamics.

Attentional Factorized Q-Learning for Many-Agent Learning

The difficulty of Multi-Agent Reinforcement Learning (MARL) increases with the growing number of agents in system. The value function decomposition is an effective way to alleviate the curse of dimension. However, the existing methods usually either can only provide the low-order approximate decomposition of no more than the second-order, or need to spend a lot of effort manually designing the high-order interaction among agents according to experience. Therefore, the existing methods either tend to bear large decomposition error or are not convenient to use. In this paper, a high-order approximate value function decomposition method is proposed, which has the following prominent characteristics: the low-rank vector is exploited to represent value function, the low-order and high-order components share the same input (i.e., the embedding vector), the attention mechanism is used to select the agents participating in the high-order interaction, and all agents share the model parameters if the agents are homogeneous. To our knowledge, this is the first MARL method modeling low- and high-order interaction simultaneously among agents that can be trained end-to-end. Extensive experiments on two different multi-agent problems demonstrate the performance gain of our proposed approach in comparison with strong baselines, particularly when there are a large number of agents.

Performance evaluation, error decomposition and Tree-based Machine Learning error correction of GPM IMERG and TRMM 3B42 products in the Three Gorges Reservoir Area

Satellite precipitation products (SPPs) have excellent development prospects in hydrometeorology research for their high spatial-temporal resolution. Understanding the performance of SPPs is essential before their application in estimating multiple processes. This paper evaluated the accuracy and error composition of GPM IMERG Final-run V06 and TRMM 3B42V7 in the Three Gorges Reservoir Area (TGRA) based on the China Gauge-based Daily Precipitation Analysis dataset (CGDPA) during 2001–2019. Afterwards, the precipitation correction by merging satellite and gauge observation precipitation was conducted with three Tree-based Machine Learning models, Decision Tree (DT), Adaptive Boosting Decision Trees (Adaboost), and Random Forest (RF). The results show that: (1) Two SPPs can well reflect the spatial pattern and in-year variation of precipitation in the TGRA. However, they are limited in estimating precipitation amount for seriously underestimated the light rain or overestimated torrential rain. Under the influence of climate and variety terrains, the SPPs accuracy in the middle-elevation relief mountains of downstream is significantly higher than that in the low-elevation relief mountains of upstream. Moreover, that on the monthly and annual scales are higher than on the daily scale. Comparing two SPPs, the area proportions of IMERG-F better than 3B42V7 are 64.0%, 86.0%, and 81.6% on daily, monthly and annual scales, respectively. (2) Both the systematic error components of two SPPs raise with the increase of precipitation amount, and the error spatial pattern of 3B42V7 is more affected by precipitation. The random error component of light rain and daily precipitation is higher than other grades and scales. Despite this, the random error component decreases significantly when daily precipitation is accumulated. (3) The three primary factors affecting error correction of SPPs are precipitation amount, longitude, and DEM in TGRA. Among the three Tree-based methods, the RF showed the best error correction effect, and it can significantly improve the monthly and annual precipitation accuracy and better reproduce probability density function (PDF). Cumulative precipitation can reduce the random error component of daily precipitation and have high correction accuracy when cumulative time exceeds 5-days.

Performance of satellite-based and reanalysis precipitation products under multi-temporal scales and extreme weather in mainland China

Gridded precipitation products are efficient supplements to surface meteorological gauges and thus a comprehensive evaluation of such products is essential. This study systematically evaluated the performance of 4 gridded precipitation datasets with hourly scale in mainland China, with ground gauge precipitation as a benchmark. In particular, we assessed the performance of two satellite-based precipitation estimations (SPEs): Integrated Multi-satellite Retrievals for GPM (IMERG) and Global Satellite Mapping of Precipitation (GSMaP), and two reanalysis precipitation estimations (RPEs): Modern-Era Retrospective analysis for Research and Applications, version 2 (MERRA) and Climate Forecast System Reanalysis (CFSR). The results reveal that all the products have better performance in low-latitude areas, and have worse performance in the high-latitude mountainous regions. SPE products have similar features of temporal-spatial performance and diurnal cycle estimation, and so have RPE products. The overall summer SPE accuracy surpasses that of all RPE products, and vice versa in winter. The error decomposition of each product linked the summer bias to excessive false events of light precipitation. In winter, the SPE error is generally a result of missed and false events, while that of the RPEs originates from false precipitation. The product accuracy increases with the time scale, and the daily MERRA accuracy exceeds that of other products. However, due to the challenge in representing convective precipitation, the accuracy of the diurnal cycle and peak hour is lower than that of the SPEs, and representing weaker amplitudes compared to the gauge precipitation. This consequently results in RPEs’ poorer performance in extreme heavy precipitation compared to the SPE products. The results of this study are useful for both developers and users of gridded precipitation products.

US oil supply shocks and economies of oil-exporting African countries: A GVAR-Oil Resource Analysis

This study examined the effects of US Shale-oil supply which started in 2013. The study employed GVAR-Oil resource model from the first quarter of 1980 to the fourth quarter of 2018 for 36 trading countries with special focus on 4 oil-exporting African countries. Given that shale supply is a recent phenomenon, we estimated two models to capture these effects. The first model spanned from 1980 to 2013, while the second model was from 1980 to 2018. After implementing the preliminary tests of optimal lag length selection, cointegration test and the weak exogeneity test, we conducted the persistence profile to find Egypt and Gabon adjust to US oil supply shocks faster than Algeria while Nigeria did not. The result of the generalized impulse response functions showed negative effects of the US shale oil supply in Egypt, positive effects in Nigeria and Gabon but insignificant in Algeria. The generalized forecast variance error decomposition function conducted found output of China, Japan, US, Europe, Asia and Latin America respectively to contribute the largest variations in oil supplies during the study period. African countries, on the other hand, were found to contribute in small proportion. We recommended that robust oil savings funds by oil-exporting African countries can act as buffers against oil supply shocks.

Agree to disagree? Predictions of U.S. nonfarm payroll changes between 2008 and 2020 and the impact of the COVID19 labor shock

We analyze an unbalanced panel of monthly predictions of nonfarm payroll (NFP) changes between January 2008 and December 2020 sourced from Bloomberg. Unsurprisingly, we find that prediction quality varies across economists and we reject the hypothesis of equal predictive ability. In an error decomposition, we find evidence of significantly biased forecasts. Participation rate in the survey is affecting this bias. We find that survey participants under-predict job losses in times of market turmoil while also under-predicting the recovery thereafter, especially during the COVID19 labor shock. For prediction of NFP changes, autoregressive models are outperformed by a deep learning long short-term memory network. However, the consensus forecast yields better forecasts than model-based approaches and are further improved by combining the forecasts of the best performing economists. The COVID19 labor shock is shown to have adverse effects on the prediction performance of economists. However, not all economists are affected equally.

Insights of an AI agent via analysis of prediction errors: a case study of fluence map prediction for radiation therapy planning

Purpose. We have previously reported an artificial intelligence (AI) agent that automatically generates intensity-modulated radiation therapy (IMRT) plans via fluence map prediction, by-passing inverse planning. This AI agent achieved clinically comparable quality for prostate cases, but its performance on head-and-neck patients leaves room for improvement. This study aims to collect insights of the deep-learning-based (DL-based) fluence map prediction model by systematically analyzing its prediction errors. Methods. From the modeling perspective, the DL model’s output is the fluence maps of IMRT plans. However, from the clinical planning perspective, the plan quality evaluation should be based on the clinical dosimetric criteria such as dose-volume histograms. To account for the complex and non-intuitive relationships between fluence map prediction errors and the corresponding dose distribution changes, we propose a novel error analysis approach that systematically examines plan dosimetric changes that are induced by varying amounts of fluence prediction errors. We investigated four decomposition modes of model prediction errors. The two spatial domain decompositions are based on fluence intensity and fluence gradient. The two frequency domain decompositions are based on Fourier-space banded frequency rings and Fourier-space truncated low-frequency disks. The decomposed error was analyzed for its impact on the resulting plans’ dosimetric metrics. The analysis was conducted on 15 test cases spared from the 200 training and 16 validation cases used to train the model. Results. Most planning target volume metrics were significantly correlated with most error decompositions. The Fourier space disk radii had the largest Spearman’s coefficients. The low-frequency region within a disk of ∼20% Fourier space contained most of errors that impact overall plan quality. Conclusions. This study demonstrates the feasibility of using fluence map prediction error analysis to understand the AI agent’s performance. Such insights will help fine-tune the DL models in architecture design and loss function selection.

Predicting short wind speed with a hybrid model based on a piecewise error correction method and Elman neural network

The effective utilization of wind energy is a positive development trend in renewable energy that provides an effective impetus to alleviate global warming. However, the complex volatility and extreme suddenness of wind speeds make it difficult to accurately predict wind speeds. To overcome this challenge, a novel short-term wind speed prediction model based on double decomposition, piecewise error correction, Elman neural network and the autoregressive integrated moving average model is proposed. In this model, the fuzzy entropy is applied to judge the complexity of each subseries generated by variational mode decomposition. To address error correction, a piecewise error correction method that needs to extract only a part of the error sequence as a training set is proposed. Three experiments utilizing 6 Datasets and 14 compared models are conducted to verify the effectiveness of the proposed model. The results show that (i) the hybrid strategy based on double decomposition and piecewise error correction can improve the final prediction accuracy of different single models; (ii) the proposed hybrid model can effectively handle both linear and nonlinear problems; (iii) the root mean squared error of the proposed model for Dataset1-6 in seven-step forecasting are 0.1243, 0.1444, 0.0233, 0.1015, 0.1846 and 0.2513, respectively.