Extreme-point Symmetric Mode Decomposition Research Articles

A novel integrated method for improving the forecasting accuracy of crude oil: ESMD-CFastICA-BiLSTM-Attention

The volatility of crude oil price can significantly impact the stability of the crude oil market and even the global economy. Effectively predicting global crude oil price and volatility provides a scientific basis for decision-making for market regulators and investors worldwide, promoting the sound development of the global economy. In this study, we integrate signal processing with deep learning methods to present an optimal forecasting strategy for global crude oil price and volatility. We select the daily price of the WTI crude oil market from April 4, 1983, to December 12, 2023, for calculating volatility. Subsequently, employing extreme-point symmetric empirical mode decomposition (ESMD), K-means clustering, and fast independent component analysis method, we decompose and reconstruct the forecasting data, obtaining independent components with non-Gaussian characteristics. These components serve as inputs to estimate the accuracy of various models, including BiLSTM, Attention, LSTM, SVR, RF, and their combinations, in predicting crude oil price and volatility from both a point prediction and interval prediction perspective. Empirical results demonstrate that data decomposition, reconstruction, and the BiLSTM-Attention model outperform other models in predicting crude oil price and volatility.

New secondary decomposition ensemble support vector regression for monthly drought index forecasting

Drought prediction on a monthly timescale is conducive to the timely identification of drought characteristics and provides a reference for drought mitigation. Current research is generally based on drought indices on timescales of three months or more for drought prediction, whereas the presence of highly nonlinear and drastic changes in the characteristics of drought indices leads to suboptimal drought prediction for drought index sequences on monthly timescales. In this study, a secondary decomposition model based on extreme-point symmetric mode decomposition (ESMD), variational mode decomposition (VMD), and support vector regression (SVR) was investigated to predict a monthly-scale drought index. To evaluate the predictive ability of the model, it was applied to 100 meteorological stations in the Pearl River Basin of China and compared and analyzed using four comparative models. The results showed that the model proposed in this study has better performance index values, and the prediction accuracies of all stations are improved compared with the four comparative models, with the most significant improvement in the Nash–Sutcliffe efficiency (NSE) index value, followed by the root mean square error (RMSE) and mean absolute error (MAE) index values, and the smallest improvement in the Wilmot consistency index (WIA) index value. The monthly-scale drought quadratic decomposition (ESMD-VMD) combined prediction model established in this study provides a novel method for drought prediction.

Systemic Financial Risk Forecasting with Decomposition–Clustering-Ensemble Learning Approach: Evidence from China

Establishing a scientifically effective systemic financial risk early warning model is of great significance for prudently mitigating systemic financial risks and enhancing the efficiency of financial supervision. Based on the measurement of systemic financial risk and the network sentiment index of 47 financial institutions, this study adopted the “decomposition–reconstruction–integration” approach, utilizing techniques such as extreme-point symmetric empirical mode decomposition (ESMD), empirical mode decomposition (EMD), variational mode decomposition (VMD), hierarchical clustering, fast independent component analysis (FastICA), attention mechanism, bidirectional long short-term memory neural network (BiLSTM), support vector regression (SVR), and their combination, to construct a systemic financial risk prediction model. The empirical results demonstrate that decomposing and reconstructing relevant indicators before predicting systemic financial risks can enhance prediction accuracy. Among the proposed models, the ESMD-HFastICA-BiLSTM-Attention model exhibits superior performance in systemic financial risk early warning.

Identification and evolution characteristics of drought field in the Pearl River Basin based on REOF-ESMD

Abstract The traditional drought field studies are inadequate to study drought field characteristics from the perspective of trend and periodicity at the same time, especially to compare the interannual and interdecadal variations of different drought types in the drought field to reveal their similarity and difference patterns. The drought field in Pearl River Basin (PRB) was determined in this paper using the standardized precipitation evapotranspiration index (SPEI) and the empirical orthogonal function (EOF)/rotated empirical orthogonal function (REOF). Periodic characteristics and trend features of the drought field were recognized by extreme-point symmetric mode decomposition (ESMD) and other methods. The results showed that from the perspective of regional characteristics five different spatial modes may be used to categorize the interannual drought field of the PRB; there were interannual cycles associated with the southwest-type drought and the northwest-type drought. The central-south-, north-central- and eastern-type droughts had both interannual and interdecadal cycles; during the study period, the PRB's five types of drought revealed a changing tendency as opposed to a straightforward linear trend; from the interannual variation, the southwest-type drought was consistent with the northwest-type drought prior to 2000, and the north-central-type drought was consistent with the eastern-type drought before 2010.

Multi-step wind speed prediction based on LSSVM combined with ESMD and fractional-order beetle swarm optimization

Accurate and stable wind speed prediction can alleviate the uncertain impacts of wind power generation caused by nonlinear characteristics of wind speed, and then improve the reliability of wind power. In this paper, a hybrid model for wind speed prediction based on mode decomposition, parameter optimization and basic prediction model is proposed. First, the extreme-point symmetric mode decomposition (ESMD) is employed to adaptively decompose the denoised wind speed time series into sub-sequences with different frequencies. Second, a fractional-order beetle swarm optimization (FO-BSO) for parameter optimization of the Least squares support vector machine (LSSVM) is proposed. Through benchmark functions and non-parametric statistical test, the advantages of the FO-BSO in accuracy, stability and convergence speed are verified. Subsequently, the ESMD-FO-BSO-LSSVM prediction model is established, and three groups of wind speed datasets with different sampling locations and sampling frequencies are selected for simulation experiments. The results show that the coefficient of determination of 1-step prediction of the proposed model in three datasets are 0.9856, 0.9713, 0.9940, which has 2.43%, 3.38%, 3.08% average promotion than that of 7 comparative models. And the accuracy and stability of ESMD-FO-BSO-LSSVM model in multi-step wind speed prediction have also achieved better performance than 7 competitors.

An enhanced monthly runoff time series prediction using extreme learning machine optimized by salp swarm algorithm based on time varying filtering based empirical mode decomposition

Reliable runoff prediction plays a significant role in reservoir scheduling, water resources management, and efficient utilization of water resources. To effectively enhance the prediction accuracy of monthly runoff series, a hybrid prediction model (TVF-EMD-SSA-ELM) combining time varying filtering (TVF) based empirical mode decomposition (EMD), salp swarm algorithm (SSA) and extreme learning machine (ELM) is proposed. Firstly, the monthly runoff series is decomposed into several sub-series using TVF-EMD. Secondly, SSA is used to optimize the input weights and hidden layer biases of the selected ELM model. Finally, the prediction results are generated by summing and reconstructing each sub-series based on the SSA optimized ELM model. This hybrid model is applied to the monthly runoff prediction of Manwan hydropower, Hongjiadu hydropower, and Yingluoxia hydrological station, and compared with back propagation (BP), ELM, SSA-ELM, PSO-ELM, GSA-ELM, TVF-EMD-ELM, EMD-SSA-ELM, extreme-point symmetric mode decomposition (ESMD)-SSA-ELM, wavelet decomposition (WD)-SSA-ELM and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)-SSA-ELM models. The prediction performance of various models is reflected by four evaluation indicators (R, NSEC, NRMSE, MAPE). Results reveal that the prediction effect of the ELM model is better than that of BP, the optimization accuracy of SSA is better than those of particle swarm optimization (PSO) and gravitational search algorithm (GSA), and the prediction accuracy of the hybrid TVF-EMD and SSA is better than that of only TVF-EMD or SSA. TVF-EMD-SSA-ELM model has the highest prediction accuracy. When compared with the single ELM model, it’s NRMSE and MAPE at Manwan hydropower decrease by 84.4% and 72.38%, those of Hongjiadu hydropower decrease by 85.21% and 78.38%, and those of Yingluoxi hydrological station decrease by 68.42% and 39.51%, respectively. R and NSEC of the three sites are close to 1. Therefore, the proposed model provides a new method for the prediction of monthly runoff, and the results can provide a reference for the prediction of monthly runoff in the study area.

Multi-spatiotemporal AOD trends and association with land use changes over the Guangdong-Hong Kong-Macao Greater Bay Area during 2001-2021.

Analyzing long-term variations of aerosol optical depth (AOD) is beneficial for determining high-pollutant-risk areas and formulating mitigation policies. In this study, multi-spatiotemporal trends and periodicity of AOD, as well as the persistence over the Guangdong-Hong Kong-Macao Greater Bay Area from 2001 to 2021, were investigated by the extreme-point symmetric mode decomposition (ESMD), Theil-Sen Median trend analysis and Hurst exponent. The results elucidate that AOD exhibits fluctuant variations during the 21-year period with the year 2012 as the turning point. There is a slight upward tendency (0.009year-1) in the pre-2012 period but a pronounced downward trend (- 0.03year-1) in the post-2012 period, suggesting an overall declining trend in the study area. The northern cities in the area present an increasing-stable-decreasing trend of monthly average AOD, whereas other cities have an increasing-fluctuating-decreasing trend over the study period. The decreasing rate in the western parts is higher than that in the eastern parts, like Zhaoqing, Jiangmen and Foshan city. A continuous decline of AOD is dominated over the study area, whereas an anti-persistence tendency is accumulated in the northeastern parts. Additionally, elevated AOD can be observed in unused land, water bodies and construction land, while grassland, cropland and woodland have lower AOD. The decreasing rate is larger when land-use types with high AOD are converted to those with low AOD; otherwise, the decreasing rate is smaller. The results have a great significance for improving the understanding of long-term variations of AOD, as well as providing a scientific basis to formulate environmental protection and mitigation practices.

Temporal and spatial evolutionary trends of regional extreme precipitation under different emission scenarios: Case study of the Jialing River Basin, China

Exploration of the temporal and spatial evolutionary trends of future extreme precipitation under different emission scenarios is of considerable importance for promoting active response to climate change. Based on the output of CMIP6 global climate models (GCMs) with four Shared Socioeconomic Pathways (SSPs), precipitation data for the Jialing River Basin (China) were obtained through CMhyd downscaling and correction. A relative threshold of 95 percentile of each year was used to extract extreme precipitation in the basin, and historical observational data were used to verify the capability of the GCMs to simulate extreme precipitation. Based on Extreme-point Symmetric Mode Decomposition, the trends and periodic characteristics of future extreme precipitation in the Jialing River Basin under four different emission scenarios (SSP2.6, SSP4.5, SSP7.0, and SSP8.5) were simulated and analyzed. The future temporal and spatial distributions of extreme precipitation frequency and intensity in different periods were described. The results revealed the following. (1) Future extreme precipitation in the Jialing River Basin is likely to increase with rates of 21.8 mm/10a, 11.4 mm/10a, 8.7 mm/10a, and 8.3 mm/10a for SSP8.5, SSP 7.0, SSP4.5, and SSP2.6, respectively. (2) The frequency of extreme precipitation decreased in the whole basin with a 1-day decrease of 3.88 % (SSP8.5), 7.11 % (SSP7.0), 5.66 % (SSP4.5), and 2.40 % (SSP2.6) from historical levels. (3) The intensity of extreme precipitation increased with a 1-day increase of 11.18 % (SSP8.5), 6.80 % (SSP7.0), 5.04 % (SSP4.5), and 4.57 % (SSP2.6) from historical levels. Over time, the change of extreme precipitation showed strong periodic characteristics with three periodic components of 2–3, 4–6, and 9–12 years. In terms of spatial distribution, the frequency (intensity) center of extreme precipitation in the next 80 years will be distributed in the south (southeast) of the basin. Compared with historical observations, the area of extreme precipitation intensity in the future accounted for a larger proportion, while the area of extreme precipitation frequency accounted for a smaller proportion. In terms of increased emission levels, the extreme precipitation frequency would decrease and the intensity would increase. The conclusions of this study could provide a reference for disaster prevention and mitigation of the effects of extreme precipitation under future climate change.

Study on Short‐Term Load Combination Forecasting Model Considering Historical Data Interval Construction

In response to the insufficient accuracy of load forecasting in power system and the wide range of intervals, a combined short‐term power load forecasting model considering the interval construction of historical data is proposed. First, the data are decomposed into relatively stable subsequences using extreme‐point symmetric mode decomposition (ESMD), and the adaptive dispersion entropy (DE) of C–C algorithm is proposed to recombine similar subsequences. Then, periodicity and correlation analysis are used to determine the input set of each reconstructed component, and the hybrid strategy improved equilibrium optimizer (HSIEO) is proposed to optimize the output weights of the deep extreme learning machine (DELM) to obtain the prediction values of different components and the historical data errors, and the historical data intervals are constructed based on the errors of each component. Then, based on the upper and lower bound estimation method (LUBE), the proposed improved objective function is optimized using the HSIEO‐DELM to obtain the component prediction intervals, and the optimal prediction intervals are obtained after superposition. Finally, the experimental comparison shows that the proposed algorithm has higher accuracy and better quality of model prediction intervals.

ESMD-WSST High-Frequency De-Noising Method for Bridge Dynamic Deflection Using GB-SAR

Ground-based synthetic aperture radar (GB-SAR), as a new non-contact measurement technique, has been widely applied to obtain the dynamic deflection of various bridges without corner reflectors. However, it will cause some high-frequency noise in the obtained dynamic deflection with the low signal-to-noise ratio. To solve this problem, this paper proposes an innovative high-frequency de-noising method combining the wavelet synchro-squeezing transform (WSST) method with the extreme point symmetric mode decomposition (ESMD) method. First, the ESMD method is applied to decompose the observed dynamic deflection signal into a series of intrinsic mode functions (IMFs), and the frequency boundary of the original signal autocorrelation is filtered by the mutual information entropy (MIE) for each IMF pair. Second, the high-frequency IMF components are fused into a high-frequency sub-signal. WSST is performed to remove the influence of noise to reconstruct a new sub-signal. Finally, the de-noised bridge dynamic deflection is reconstructed by the new sub-signal, the remaining IMF components, and the residual curve R. For the simulated signal with 5 dB noise, the signal-to-noise ratio (SNR) after noise reduction is increased to 11.13 dB, and the root-mean-square error (RMSE) is reduced to 0.30 mm. For the on-site experiment for the Wanning Bridge, the noise rejection ratio (NRR) is 5.48 dB, and ratio of the variance root (RVR) is 0.05 mm. The results indicate that the proposed ESMD-WSST method can retain more valid information and has a better noise reduction ability than the ESMD, WSST, and EMD-WSST methods.

Cyclically Shifted Extreme-point Symmetric Mode Decomposition (CS-ESMD)-based Progressive Denoising Approach for Ground-based Synthetic Aperture Radar Bridge Health Monitoring Signals

Cyclically Shifted Extreme-point Symmetric Mode Decomposition (CS-ESMD)-based Progressive Denoising Approach for Ground-based Synthetic Aperture Radar Bridge Health Monitoring Signals

Point and interval forecasting system for crude oil price based on complete ensemble extreme-point symmetric mode decomposition with adaptive noise and intelligent optimization algorithm

Stable and accurate prediction of crude oil prices is critical to national security, economic development, and even international relations, against the background of the COVID-19 and Russia–Ukraine war. Therefore, a memory-based hybrid forecasting system is established for point prediction and interval prediction of crude oil prices in this research, which more thoroughly separates the noise in the raw data and achieves superior prediction performance. There are five main steps in the proposed model: decomposing the raw data into intrinsic mode functions (IMFs) through our new data preprocessing technique complete ensemble extreme-point symmetric mode decomposition with adaptive noise (CEESMDAN), ensemble of IMFs based on memory features, prediction of reconstructed components, error correction via grey wolf optimizer (GWO) for final point prediction, obtaining interval prediction by multi-objective grey wolf optimizer (MOGWO). The empirical results prove that the proposed model has excellent accuracy, robustness, and generalization in both point prediction and interval prediction, compared with various baseline models.

A MULTI-STEP DE-NOISING METHOD FOR INTERFEROGRAM IN PS-INSAR

Abstract. In order to reduce the influences of the noises in Synthetic Aperture Radar (SAR) image on accurate extraction of permanent scattered (PS) points in PS-InSAR technology, a multi-step de-noising approach considering the characteristics of the noises is proposed in this study. The method can deal with the noises from one-dimensional signals perspective. First, the two-dimensional interferogram is transformed into one-dimensional phase signals by extracting the phase values of each row in S-shaped. Next, the phase signals are decomposed by the extreme-point symmetric mode decomposition (ESMD) method. Then, for the purpose of reserving more useful phase information, the Lee filtering method is applied to the high-frequency noisy part identified based on the Spearman's correlation coefficients in ESMD decomposition. Finally, the de-noised interferogram is recovered from the phase signals by ways in S-shaped in reverse. The experimental results show that the proposed method is effective in dealing with the noises and can achieve a higher accuracy of interferogram for PS-InSAR.

Analysis of Long-Term Aerosol Optical Properties Combining AERONET Sunphotometer and Satellite-Based Observations in Hong Kong

This study analyzes seasonal characteristics and long-term variations in aerosol optical parameters in Hong Kong from 2006 to 2021 using AERONET data and satellite-based observations based on the extreme-point symmetric mode decomposition (ESMD) model. The dominant aerosol types in Hong Kong are mixed aerosols and urban/industrial aerosols with fine-mode sizes, and slightly absorbing or non-absorbing properties. Aerosol optical depth (AOD), Angstrom exponent (AE) and single scattering albedo (SSA) varied seasonally with a lower AOD but higher AE and SSA in summer, and elevated AOD but lower AE and SSA in spring and winter. The long-term variations show the year 2012 to be a turning point, with an upward trend in AOD and AE before 2012 and then downwards after 2012. However, for SSA, a rising trend was exhibited in both pre- and post-2012 periods, but with a larger gradient in the first period. The ESMD analysis shows shorter-term, non-linear fluctuations in aerosol optical parameters, with alternating increasing and declining trends. The examination of the relationships between AOD and meteorological factors based on the extreme gradient boosting (XGBoost) method shows that the effects of weather conditions on AOD are complex and non-monotonic. A lower relative humidity, higher wind speed in southwest directions and lower temperature are beneficial to the abatement of aerosol loads in Hong Kong. In conclusion, the findings of this study enhance the understanding of aerosol properties and the interactions between aerosol loading and meteorological factors.

Analysis of the Anomalous Environmental Response to the 2022 Tonga Volcanic Eruption Based on GNSS

On 15 January 2022, a violent eruption and tsunami of the Hunga Tonga-Hunga Ha’apai (HTHH) volcano in Tonga, South Pacific, caused widespread international concern. In order to detect the anomalous environmental response caused by the HTHH volcanic eruption based on GNSS ionospheric data, GNSS tropospheric data and GNSS coordinate time series, a new method combining the zenith non-hydrostatic delay difference method and the extreme-point symmetric mode decomposition (ESMD) method, was proposed to detect tropospheric anomalies. The moving interquartile range method and the ESMD method were introduced to detect ionospheric anomalous and coordinate time series anomalies, respectively. The results showed that 9–10 h before the eruption of the Tonga volcano and 11–12 h after the eruption of the Tonga volcano, obvious total electron content (TEC) anomalies occurred in the volcanic eruption center and its northeast and southeast, with the maximum abnormal value of 15 TECU. Significant tropospheric anomalies were observed on the day of the HTHH volcano eruption as well as 1–3 days and 16–17 days after the eruption, and the abnormal intensity was more than 10 times that of normal. The coordinate time series in direction E showed very significant anomalies at approximately 2:45 p.m. on 14 January, at approximately 4:30 a.m.–5:40 a.m. on 15 January, and at approximately 3:45 a.m. on 16 January, with anomalies reaching a maximum of 7–8 times daily. The abnormality in the direction north (N) is not obvious. Very prominent anomalies can be observed in the direction up (U) at approximately 4:30 a.m.–5:40 a.m., with the intensity of the anomalies exceeding the normal by more than 10 times. In this study, GNSS was successfully used to detect the anomalous environmental response during this HTHH volcano eruption.

Mid-long term forecasting of reservoir inflow using the coupling of time-varying filter-based empirical mode decomposition and gated recurrent unit

Accurate and reliable runoff forecast is beneficial to watershed planning and management and scientific operation of water resources system. However, due to the comprehensive influence of climatic conditions, geographical environment, and human activities, the runoff series is nonlinear and non-stationary, and there are still great challenges in mid-long term runoff forecasting. In order to improve the prediction accuracy, a novel model TVF-EMD-PE-PSO-GRU (TEPPG) was proposed in this study. Firstly, several intrinsic mode functions (IMFs) were obtained by decomposing the original runoff series by time-varying filter-based empirical mode decomposition (TVF-EMD). Secondly, the permutation entropy (PE) algorithm was used to calculate the complexity of each IMF, and the IMF with similar complexity was combined. Then, the gated recurrent unit (GRU) model based on particle swarm optimization (PSO) was used to predict each IMF after merging. Finally, the prediction results of each IMF were superimposed to obtain the final results. And compared with three models such as TVF-EMD-PSO-GRU, extreme-point symmetric mode decomposition coupled gated recurrent unit and particle swarm optimization (ESMD-PSO-GRU), complete ensemble empirical mode decomposition with adaptive noise coupled gated recurrent unit, and particle swarm optimization (CEEMDAN-PSO-GRU). The monthly and annual runoff forecasting of Tangnaihai hydrological station in the upper reaches of the Yellow River and Cuntan hydrological station in the upstream of the Yangtze River was taken as examples to test the performance of the model. The results show that, compared with the other three models, the TEPPG model had the highest prediction accuracy and was relatively stable in both monthly and annual runoff forecasts. Thus, the proposed method was developed to support the decision-making of water resource system.

Fingertip pulse rate variability extraction based on extreme-point symmetric mode decomposition

To solve shortcomings of being sensitive to noise and waveform when using threshold method to extract pulse rate variability (PRV) at this stage, a method using extreme-point symmetric mode decomposition to extract PRV signals from pulse waves with noise is proposed. A Butterworth filter is used to remove the baseline drift, the DC mode and power frequency noise, which can effectively avoid noise interference when identifying peak points. The pre-processed data is decomposed by extreme-point symmetric mode decomposition to select the corresponding mode of the main wave, thereby reducing the difficulty of feature point extraction. Compared with the threshold method, the extraction method proposed in this paper is more intuitive and can self-adaptively select the best decomposition layer. This method is suitable for the extraction of fingertip PRV under complex noise and some disease statuses.

A novel fault location method for hybrid lines based on traveling wave

In this paper, a novel fault traveling wave-based location method for hybrid lines is proposed. According to the refraction characteristics of fault traveling wave (TW) at junction nodes, the node ratio coefficient value Q is defined based on the amplitude of traveling wave. Then, by comparing the Q values of junction nodes and fault points, a fault section identification principle is proposed to determine the fault line section for hybrid lines. After identification of fault line section, a double-ended fault location method is revised via adding the location compensation factors to mitigate the effect of traveling wave velocity changes on fault location for multi-section hybrid lines. Additionally, considering the detection problems of arrival time for TW signals, the extreme-point symmetric mode decomposition (ESMD) method and Teager energy operator (TEO) are proposed. The ESMD method is applied to decompose the sampled fault traveling wave signals into several intrinsic modes to filter out the fundamental frequency and low frequency signals. The TEO is employed to track the characteristics of TW signals. Effectiveness of the proposed method is validated in PSCAD. Results show that the ESMD-TEO can detect TW signals effectively, and the proposed fault location method can determine the fault line section and locate fault positions correctly.

Multi-spatiotemporal patterns of aerosol optical depth and influencing factors during 2000–2020 from two spatial perspectives: The entire Yellow River Basin region and its urban agglomerations

Analyzing on the patterns and causes of atmosphere pollution in Yellow River Basin region (YRB) is critical for its construction of ecological civilization and high-quality development. Aerosol optical depth (AOD), an important optical property of aerosol that characterizes the attenuation of light by aerosols, is an indicator of regional atmospheric pollution. Based on multi-source data, we investigated spatiotemporal patterns of AOD and its influencing factors over YRB during 2000–2020 from two spatial perspectives: the entire region and its urban agglomerations. The spatial patterns and trends of AOD and its spatial response to several controls was quantitatively analyzed using Theil-Sen Slope, Mann-Kendall test and spatial principal component analysis, and its periodicity and spatial differences was finely described by extreme-point symmetric mode decomposition. The multi-year average AOD are higher in the middle and lower reaches of YRB than that in the upper reaches and significant seasonal differences of AOD spatial pattern are observed in YRB. Spatial patterns of AOD in YRB are mainly regulated by meteorology, topography and socio-economy, various factors and their combination exert different impacts on AOD. Despite the high contribution of meteorological factors in most urban agglomerations, their acting forces on AOD are not consistent. In terms of spatial trend, the areas where AOD decrease (94.54%) are much larger than the areas where AOD increase. For temporal trend, AOD exhibit a nonlinear downward trend throughout YRB, and its periodicity come from interaction of multi-time-scale components: inter-annual oscillations (imf5) and seasonal oscillations: seasonal periodic fluctuation (imf3), dust weather and man-made agricultural activities caused volatility (imf2) and fluctuation caused abrupt event (imf1), seasonal oscillations dominate the AOD changes. Those are of great significance for improving our understanding of the spationtemporal patterns and its controls of AOD on YRB and its urban agglomerations.

A novel hybrid model based on ESMD-PE and mRMR-LSTM-Adaboost for short-term wind power prediction

High-precision wind power prediction could reference the optimal dispatch and stable operation of the power system. This paper proposes an adaptive hybrid optimization algorithm that integrates decomposition and reconstruction to effectively explore the potential characteristics and related factors of wind power output and improve the accuracy of short-term wind power prediction. First, the extreme-point symmetric mode decomposition is used to analyze the periodicity, trend, and abrupt characteristics in the original wind power sequence and form multiple intrinsic mode functions with local time-domain characteristics. Then, considering the similarity of the feature sequence and the efficiency of the prediction algorithm, the permutation entropy is used to reconstruct the components with close time-domain characteristics to form subsequences that could reflect different spectral characteristics. Then, the improved maximum relevance minimum redundancy-the long short-term memory-the adaptive boosting algorithm model is used to determine the prediction model structure, parameters, and optimal feature factors of the subsequences. Finally, the prediction results of each subsequence are integrated to obtain the final wind power. Taking a wind farm in northern Shaanxi as the application object, the prediction accuracy and efficiency of the methods proposed in this paper are compared in terms of the decomposition method, prediction model, and prediction timeliness. The results show that in the 15 min to 3 h forecast periods, compared with other models, the mean absolute error and root mean square error of the proposed model are increased. At the same time, as the forecast period grows, the superiority of the proposed method is more prominent.