Ensemble Empirical Mode Decomposition Algorithm Research Articles

Carbon price prediction in China based on ensemble empirical mode decomposition and machine learning algorithms.

The carbon emission trading market is crucial for reducing emissions, conserving energy, and enhancing the climate and environment. Studying carbon price forecasting can encourage China's involvement in international carbon financial instruments trading and promote the development of China's pilot carbon markets. This study employs ensemble empirical mode decomposition (EEDM) to convert the initial carbon price, which is a non-stationary signal, into several intrinsic mode functions and residual terms. Subsequently, hybrid machine learning methods are used to estimate the carbon price. For empirical analysis, the three main carbon markets with large trading volumes, Guangdong, Hubei, and Shenzhen, are selected from the eight pilot carbon markets. To achieve short-term carbon price prediction, a hybrid model combining a genetic algorithm (GA) and back propagation (BP) neural network is used. This model effectively addresses the issue of neural networks falling into local optimization. The results indicate that the hybrid algorithm is significantly superior to other algorithms for short-term prediction. Additionally, another hybrid model, combining the least squares support vector machine (LSSVM) and particle swarm optimization (PSO) algorithms, is employed to reduce forecast error while minimizing search parameters, which is not possible with traditional neural network models.

Fault diagnosis method of switch machine based on adaptive neural fuzzy network

Aiming at the problem of a large number of switch machines, harsh working environment and high frequency of equipment failures caused by many factors, in order to accurately diagnose railway switch machine faults, a switch machine fault diagnosis method based on adaptive neural fuzzy network (ANFIS) optimized by dynamic weight particle swarm (DPSO) algorithm is proposed by analyzing the vibration signals generated during the operation of the switch machine. Firstly, the working vibration signal is decomposed into several intrinsic mode functions (IMFs) and selected by using the ensemble empirical mode decomposition (EEMD) algorithm; then, the feature values of IMFs are extracted by using the improved time domain multiscale scatter extraction (ITMDE) algorithm, and then input into the optimized ANFIS model to learn and realize fault diagnosis; finally, the method is compared and analyzed with various diagnostic model algorithms and learning algorithms. The experimental results show that the proposed method can effectively diagnose switch machine faults, which has certain reference significance for intelligent diagnosis of switch machine faults and related research in the future.

Complete Ensemble Empirical Mode Decomposition and Wavelet Algorithm Denoising Method for Bridge Monitoring Signals

Complete Ensemble Empirical Mode Decomposition and Wavelet Algorithm Denoising Method for Bridge Monitoring Signals

Convolutional preprocessing Transformer-based fault diagnosis for rectifier-filter circuits in nuclear power plants

Rectifier-filter circuit, as a vital electronic component in nuclear power plants (NPPs), serves the role of converting alternating current into smooth direct current. Affected by intense radiation environmental factors and variable operating profiles, the rectifier-filter circuit is subject to degradation and soft failures, namely, a derated circuit performance but not yet to failure. It is urgent to diagnose the soft failures of the rectifier-filter circuit, so as to ensure the safe operations of NPPs. In this article, an ensemble empirical mode decomposition (EEMD) algorithm is first employed to decompose the three-phase current signals and electrical signals of electronic components. The decomposed signals are fed into a convolutional preprocessing Transformer (CPT) to deeply extract the fault features of the rectifier-filter circuit. Specifically, the multi-directional, multi-scale, and extremely sensitive long-range time-dependent features in the EEMD feature data are extracted by the multi-head attention mechanism of the Transformer. A deep Softmax classifier is, then, devised to reduce the feature dimensionality and identify the soft fault modes of the rectifier-filter circuit. The fault simulation of the rectifier-filter circuit is conducted, and a real case experiment and multiple comparative studies are conducted to validate the effectiveness and diagnosis accuracy of the CPT-based method.

Spatial and temporal evolution of heatwaves in Taiwan in a changing climate using multi-dimensional complementary ensemble empirical mode decomposition

Recent decades have witnessed noticeable warming in highly developed cities. Taiwan, a densely populated island characterized by its monsoon-dominated climate and unique mountainous topography, has experienced an average temperature increase of 1.0–1.4 °C in the last century, significantly exceeding the global average. This research introduces the Multi-dimensional Complementary Ensemble Empirical Mode Decomposition (MCEEMD) algorithm, providing a novel approach for analyzing gridded climate data and uncovering spatiotemporal temperature patterns in Taiwan. This methodology offers valuable insights into the localized impacts of climate change. The spatiotemporal evolution of temperature from 1960 to 2020 is analyzed to estimate the warming trend associated with climate change. Essential factors related to the urban heat island (UHI) effect, which leads to temperature disparities between urban and rural areas, are also examined. Warming and the UHI effect are critical components of climate change, increasing the likelihood of extreme weather events in urban areas. The study investigates extreme weather events from 1960 to 2020, focusing on heatwaves. It projects changes in the frequency and duration of heatwaves for the mid (2046–2065) and late 21st century (2081–2100). Notably, Taipei experienced a warming trend exceeding 1.5°C in the 2010s, which was likely influenced by urbanization. Additionally, areas experiencing the sharpest increase in heatwave events (more than 1.5 events) by 2000 were predominantly in highly developed cities across northern and southern Taiwan. Further analysis under the RCP8.5 scenario suggests that, by the end of the 21st century, heatwave events could last for at least 20 days in many regions, with the potential to extend to nearly a month during the summer.

Feature Extraction of Flow Sediment Content of Hydropower Unit Based on Voiceprint Signal

The hydropower turbine parts running in the sand-bearing flow will experience surface wear, leading to a decline in the hydropower unit’s stability, mechanical performance, and efficiency. A voiceprint signal-based method is proposed for extracting the flow sediment content feature of the hydropower unit. Firstly, the operating voiceprint information of the hydropower unit is obtained, and the signal is decomposed by the Ensemble Empirical Mode Decomposition (EEMD) algorithm, and a series of intrinsic mode functions (IMFs) are obtained. Combined with correlation analysis, more sensitive IMF components are extracted and input into a convolutional neural network (CNN) for training, and the multi-dimensional output of the fully connected layer of CNN is used as the feature vector. The k-means clustering algorithm is used to calculate the eigenvector clustering center of the hydropower unit with a clean flow state and a high sediment content state, and the characteristic index of the hydropower unit sediment content is constructed based on the Euclidean distance method. We define this characteristic index as SI, and the change in the SI value can reflect the degree of sediment content in the flow of the unit. A higher SI value indicates a lower sediment content, while a lower SI value suggests a higher sediment content. Combined with the sediment voiceprint data of the test bench, when the water flow changed from clear water to high sediment flow (1.492 × 105 mg/L), the SI value decreased from 1 to 0.06, and when the water flow with high sediment content returned to clear water, the SI value returned to 1. The experiment proves the effectiveness of the method. The extracted feature index can be used to detect the flow sediment content of the hydropower unit and give early warning in time, so as to improve the maintenance level of the hydropower unit.

An ensemble model for short-term wind power prediction based on EEMD-GRU-MC

As a kind of clean and renewable energy, wind power is of great significance for alleviating energy crisis and environmental pollution. However, the strong randomness and large volatility of wind power bring great challenges to the dispatching and safe operation of the power grid. Hence, accurate and reliable short-term prediction of wind power is crucial for the power grid dispatching department arranging reasonable day-ahead generation schedules. Targeting the problem of low model prediction accuracy caused by the strong intermittency and large volatility of wind power, this paper develops a novel ensemble model for short-term wind power prediction which integrates the ensemble empirical mode decomposition (EEMD) algorithm, the gated recurrent unit (GRU) model and the Markov chain (MC) technique. Firstly, the EEMD algorithm is used to decompose the historical wind power sequence into a group of relatively stationary subsequences to reduce the influence of random fluctuation components and noise. Then, the GRU model is employed to predict each subsequence, and the predicted values of each subsequence are aggregated to get the preliminary prediction results. Finally, to further enhance the prediction accuracy, the MC is used to modified the prediction results. A large number of numerical examples indicates that the proposed EEMD-GRU-MC model outperforms the six benchmark models (i.e., LSTM, GRU, EMD-LSTM, EMD-GRU, EEMD-LSTM and EEMD-GRU) in terms of multiple evaluation indicators. Taking the spring dataset of the ZMS wind farm, for example, the MAE, RMSE and MAPE of the EEMD-GRU-MC model is 1.37 MW, 1.97 MW, and from 1.76%, respectively. Moreover, the mean prediction error of the developed model in all scenarios is less than or close to 2%. After 30 iterations, the proposed model uses an average of about 35 min to accurately predict the wind power of the next day, proving its high computation efficiency. It can be concluded that the ensemble model based on EEMD-GRU-MC is a promising prospect for short-term wind power prediction.

Image-Decomposition-Enhanced Deep Learning for Detection of Rotor Cores in Cardiac Fibrillation.

Rotors, regions of spiral wave reentry in cardiac tissues, are considered as the drivers of atrial fibrillation (AF), the most common arrhythmia. Whereas physics-based approaches have been widely deployed to detect the rotors, in-depth knowledge in cardiac physiology and electrogram interpretation skills are typically needed. The recent leap forward in smart sensing, data acquisition, and Artificial Intelligence (AI) has offered an unprecedented opportunity to transform diagnosis and treatment in cardiac ailment, including AF. This study aims to develop an image-decomposition-enhanced deep learning framework for automatic identification of rotor cores on both simulation and optical mapping data. We adopt the Ensemble Empirical Mode Decomposition algorithm (EEMD) to decompose the original image, and the most representative component is then fed into a You-Only-Look-Once (YOLO) object-detection architecture for rotor detection. Simulation data from a bi-domain simulation model and optical mapping acquired from isolated rabbit hearts are used for training and validation. This integrated EEMD-YOLO model achieves high accuracy on both simulation and optical mapping data (precision: 97.2%, 96.8%, recall: 93.8%, 92.2%, and F1 score: 95.5%, 94.4%, respectively). The proposed EEMD-YOLO yields comparable accuracy in rotor detection with the gold standard in literature.

Fault diagnosis method for planetary gearbox based on intrinsic feature extraction and attention mechanism

In a high-noise environment and with a limited number of faulty samples, it becomes challenging to extract a sufficient amount of useful fault information, which makes gear fault diagnosis more difficult. To address these issues, this paper proposes a fault diagnosis method for planetary gearboxes based on intrinsic feature extraction and attention mechanism. The method utilizes the complementary ensemble empirical mode decomposition algorithm to perform modal decomposition on the fault vibration signal, obtaining a series of modal components. By comparing and selecting the modal components that contain a significant amount of fault features, they are then transformed into two-dimensional images with time–frequency properties using wavelet transform. Additionally, a neural network model based on attention mechanism and large-scale convolution is proposed. The preprocessed images are inputted into the network for feature extraction. During this process, the large-scale convolution with residual structure maximizes the retention of effective feature information, while the attention network further filters the features. Finally, the selected features are used for fault classification. The model is validated using the gear datasets from Southeast University and the University of Connecticut. A comparison is made with the Pro-MobileNetV3, channel attention and multiscale convolutional neural network, multiscale dynamic adaptive residual network, and CBAM-ResNeXt50 models. It is found that the accuracy reaches 100% before adding Gaussian noise and 99.68% after adding noise, which is significantly higher than that of other models.

A hybrid approach based machine learning models in electricity markets

In recent years, integrating renewable and non-renewable energy sources has transformed electric grids, presenting new challenges in predicting energy data due to varying levels of variability. Accurate prediction of both types of energy data is crucial for smart grid technology development and effective renewable energy integration into existing grids. We have introduced an innovative hybrid approach for forecasting both renewable and non-renewable data. This method employs a sophisticated ensemble empirical mode decomposition (EEMD) algorithm, carefully selecting intrinsic mode functions (IMFs) to dissect the original data into distinct IMFs and residuals. The IMFs are predicted utilizing support vector regression (SVR), while the residual series is forecasted using bidirectional long short-term memory with an attention mechanism (BiLSTM-AM). In pursuit of enhanced predictive accuracy, our approach employs an ensemble summation methodology to merge forecasted sub-series effectively. We conducted experiments using two distinct wind speed datasets, generating 24-h forecasts. In comparison to the second-best model, EEMD combined with BiLSTM-AM, our approach demonstrated significant improvement, reducing mean absolute error, root mean square error, and peak percentage of threshold statistics by 7.87 %, 3.91 %, and 23.51 %, respectively. The proposed model accurately captured peak and valley occurrences’ timing and amplitude, surpassing existing models.

Multi-Energy Cooperative Primary Frequency Regulation Analysis of a Hybrid Plant Station for Wind Power and Hydrogen Production Based on Ensemble Empirical-Mode Decomposition Algorithm

Wind curtailment and inadequate grid-connected frequency regulation capability are the main obstacles preventing wind power from becoming more permeable. The electric hydrogen production system can tackle the wind curtailment issue by converting electrical energy into hydrogen energy under normal operating circumstances. It can be applied as a load-reducing method during frequency regulation to help the system restore the power balance. First, this study proposes the concept of a hybrid plant station that combines the production of hydrogen and wind energy. This plant station will be referred to as a hybrid station with centralized hydrogen production and distributed energy storage. By mimicking the synchronous generator’s frequency control features, the primary frequency regulation mechanism of a hybrid plant station is examined. Secondly, due to the frequency regulation requirements of the power grid’s full-time domain hybrid power station, this paper proposes a hybrid plant station control strategy based on the EEMD variable parameter control algorithm. In frequency regulation power, the electric hydrogen production device load reduction responds to the low-frequency component, and the supercapacitor responds to the high-frequency component. The impact of the dynamic characteristics of alkaline electrolyzers on the frequency regulation effect is analyzed in this article, along with a comparison of the matching of various energy storage devices and electrolyzers in power grid frequency regulation. Finally, the feasibility and soundness of the proposed control strategy are confirmed by creating a simulation model representing a hybrid plant station involved in primary frequency management under various operational scenarios.

A multi-head attention mechanism aided hybrid network for identifying batteries’ state of charge

A Convolution Neural Network and a Bidirectional Long Short-Term Memory network connected architecture with a Multi-Head Attention mechanism (CNN-BiLSTM-MHA) is studied for predicting state of charge (SOC) of lithium-ion batteries (LIBs). Firstly, an adaptive noise based complete ensemble empirical mode decomposition (AN-CEEMD) algorithm is adopted to catch the intrinsic features of measured battery signals by adding white noises. Secondly, a CNN-BiLSTM model with the MHA mechanism is developed to learn the mapping between processed input signals and battery SOC, it has three parts: 1) the CNN extracts features of the processed data, mine the relation among input signals, and promote estimation precision; 2) the BiLSTM has memory ability to catch battery dynamics, and the Swish activation function in the BiLSTM ensures unsaturated and reduces over-fitting due to its upper unbound and lower bound; 3) The multi-head attention mechanism uses several independent self-attention layers to associate input information and variables, extracts more associate information by adding weights; it reduces the overfitting risk of a single attention head, and improves the model generalization performance through joint learning of multiple heads. Finally, experiments and simulations are implemented under four operating conditions at five different temperatures, and the presented method is verified effective.

Detection of flat-bottom holes in composite materials using multi-dimensional complementary ensemble empirical mode decomposition algorithm

Due to high-temperature resistance, high strength, and excellent fatigue resistance, composite materials are widely used in automotive manufacturing, aerospace, infrastructure and other fields. Consequently, the demand for defect detection of composite materials is also increasing. As a non-destructive testing technique, the active infrared thermography, which can achieve full-field defect detection, is suitable for defect detection of composite materials. However, this method is susceptible to noises caused by the environment and heating sources. In order to solve the problem of the defect signal being submerged by these noises, a multi-dimensional complementary ensemble empirical mode decomposition (MCEEMD) algorithm is introduced in this paper. This method can decompose the signal into the low-frequency background noise, the high-frequency heating noise, and useful defect signals, and these noises can be easily removed to improve the contrast to noise ratio (CNR) of defect images. Based on this proposed method, a defect detection experiment on the carbon fiber reinforced plastic (CFRP) is performed in this paper, and experimental results show that the method can effectively remove environmental noise and heating noise, and it can detect 11 out of 12 defects on the CFRP sample with an average CNR of 9.107. Compared with the traditional differential absolute contrast method, this method can detect one additional small defect with the aspect ratio of 1.67 and one deep defect with a depth of 2 mm.

A comparison of background noise reduction algorithms for improving acoustic beamforming output

This work presents a comparison of different background noise reduction algorithms available in literature at a range of signal-to-noise ratios (SNRs) for improving the conventional beamforming (CB) source maps. The algorithms include the classical background noise removal (BNR), eigenvalue identification organization and subtraction (EIOS), subspace-based background subtraction (SBS), and ensemble empirical mode decomposition (EEMD), amongst others. To assess the performance of different algorithms, three test-cases were considered: (1) localizing a loudspeaker placed in an anechoic environment in the presence of background white-noise, (2) diagnosing machine-tool noise source(s) during machining, i.e., when the workpiece and tool piece are in contact and (3) localizing airfoil trailing-edge (TE) noise sources in the presence of background tunnel noise. The analysis showed that the suitability of an algorithm depends upon the given situation – for the loudspeaker source, all algorithms deliver comparable results while for machine-tool application, the relatively simple BNR algorithm delivered the desired improvements in CB maps. For the experimental airfoil TE noise test-case, the EIOS and EEMD algorithms demonstrated substantial enhancements as compared to other methods. This investigation, therefore, suggests that for a given application, it is desirable to customize the background noise reduction algorithm to obtain optimal results.

Noise reduction and QRS detection in ECG signal using EEMD with modified sigmoid thresholding.

Novel noise reduction and QRS detection algorithms in Electrocardiogram (ECG) signal based on Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and the Modified Sigmoid Thresholding Function (MSTF) are proposed in this paper. EMD and EEMD algorithms are used to decompose the noisy ECG signal into series of Intrinsic Mode Functions (IMFs). Then, these IMFs are thresholded by the MSTF for reduction of noises and preservation of QRS complexes. After that, the thresholded IMFs are used to obtain the clean ECG signal. The characteristic points P, Q, R, S and T peaks are detected using peak detection algorithm. The proposed methods are validated through experiments on the MIT-BIH arrhythmia database and Additive White Gaussian Noise (AWGN) is added to the clean ECG signal at different input SNR (SNR in). Standard performance parameters output SNR (SNR out), mean square error (MSE), root mean square error (RMSE), SNR improvement (SNR imp) and percentage root mean square difference (PRD) are employed for evaluation of the efficacy of the proposed methods. The results showed that the proposed methods provide significant quantitative and qualitative improvements in denoising performance, compared with existing state-of-the-art methods such as wavelet denoising, conventional EMD (EMD-Conv), conventional EEMD (EEMD-Conv, Stockwell Transform (ST) and Complete EEMD with Adaptative Noise with hybrid interval thresholding and higher order statistic to select relevant modes (CEEMDAN-HIT). A detail quantitative analysis demonstrate that for abnormal ECG records 207 m and 214 m at input SNR of-2 dB the SNR imp value is 12.22 and 11.58 dB respectively, which indicates that the proposed algorithm can be used as an effective tool for denoising of ECG signals.

Development of decomposition-based model using Copula-GARCH approach to simulate instantaneous peak discharge

Estimation of instantaneous peak discharge is important in the design of hydraulic structures and reservoir management. In this study, a new approach called CEEMD-Copula-GARCH is presented for simulating instantaneous peak discharge in the Qale Shahrokh basin, upstream of Zayanderood Dam, Iran. In the developed method, the Complementary ensemble empirical mode decomposition (CEEMD) algorithm was used to analyze the observed values and generate the intrinsic mode function values and residual series. For this purpose, the intrinsic mode function values were simulated based on vine copula and its tree sequence (C-vine, D-vine, R-vine and their independent and Gaussian modes), and the residual series of the CEEMD algorithm were simulated by the GARCH model. The results of simulating instantaneous peak discharge values (m3/s) using the CEEMD-Copula-GARCH approach in the study area showed that the amount of simulation error based on the RMSE statistic compared to the CEEMD-Copula model and simulation without decomposition has improved by about 20 and 70%, respectively. The model’s efficiency was also estimated based on the Nash–Sutcliffe efficiency in the proposed approach of 0.99, and the certainty of the proposed approach was also confirmed based on the presented violin plot. According to the presented results, the proposed approach has high accuracy and efficiency in the simulation of instantaneous peak discharge (m3/s), which can be used in the flood control system design and flood management. Using the methodology proposed in this study, multivariable models can be used in simulating univariate series with high accuracy.

A Deep Neural Network for Working Memory Load Prediction from EEG Ensemble Empirical Mode Decomposition

Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD) are frequently associated with working memory (WM) dysfunction, which is also observed in various neural psychiatric disorders, including depression, schizophrenia, and ADHD. Early detection of WM dysfunction is essential to predict the onset of MCI and AD. Artificial Intelligence (AI)-based algorithms are increasingly used to identify biomarkers for detecting subtle changes in loaded WM. This paper presents an approach using electroencephalograms (EEG), time-frequency signal processing, and a Deep Neural Network (DNN) to predict WM load in normal and MCI-diagnosed subjects. EEG signals were recorded using an EEG cap during working memory tasks, including block tapping and N-back visuospatial interfaces. The data were bandpass-filtered, and independent components analysis was used to select the best electrode channels. The Ensemble Empirical Mode Decomposition (EEMD) algorithm was then applied to the EEG signals to obtain the time-frequency Intrinsic Mode Functions (IMFs). The EEMD and DNN methods perform better than traditional machine learning methods as well as Convolutional Neural Networks (CNN) for the prediction of WM load. Prediction accuracies were consistently higher for both normal and MCI subjects, averaging 97.62%. The average Kappa score for normal subjects was 94.98% and 92.49% for subjects with MCI. Subjects with MCI showed higher values for beta and alpha oscillations in the frontal region than normal subjects. The average power spectral density of the IMFs showed that the IMFs (p = 0.0469 for normal subjects and p = 0.0145 for subjects with MCI) are robust and reliable features for WM load prediction.

A Power Load Forecasting Method Based on Intelligent Data Analysis

Abnormal electricity consumption behavior not only affects the safety of power supply but also damages the infrastructure of the power system, posing a threat to the secure and stable operation of the grid. Predicting future electricity consumption plays a crucial role in resource management in the energy sector. Analyzing historical electricity consumption data is essential for improving the energy service capabilities of end-users. To forecast user energy consumption, this paper proposes a method that combines adaptive noise-assisted complete ensemble empirical mode decomposition (CEEMDAN) with long short-term memory (LSTM) networks. Firstly, considering the challenge of directly applying prediction models to non-stationary and nonlinear user electricity consumption data, the adaptive noise-assisted complete ensemble empirical mode decomposition algorithm is used to decompose the signal into trend components, periodic components, and random components. Then, based on the CEEMDAN decomposition, an LSTM prediction sub-model is constructed to forecast the overall electricity consumption by using an overlaying approach. Finally, through multiple comparative experiments, the effectiveness of the CEEMDAN-LSTM method is demonstrated, showing its ability to explore hidden temporal relationships and achieve smaller prediction errors.

Predicting future capacity of lithium-ion batteries using transfer learning method

Lithium-ion (Li-ion) batteries have numerous applications, such as electric vehicles, power tools, medical devices, drones, satellites, and utility-scale storage. Remaining useful life (RUL) prediction is a challenging task due to the highly nonlinear degradation behavior and prediction of batteries dealing with unknown future data. Online RUL prediction for Li-ion batteries plays an important role in proper battery health management. To improve the prediction accuracy of RUL, we propose a novel hybrid method based on transfer learning to predict the future capacity of Li-ion batteries. The proposed method consists of integrating an ensemble empirical mode decomposition algorithm, a support vector regression model, and a bidirectional long short-term memory with attention mechanism model to predict the state of health (SOH), where SOH is the battery cycle life and discharge capacity measured in number of cycles. In addition, we also consider keen-onset effects. The performance of RUL predictions using different starting RUL prediction points is compared with experiments. The proposed method shows that the larger the cycle number of the RUL prediction starting point, the more accurate the RUL prediction results. The relative error values for the three different charging policy target batteries using the proposed method are 6.96 %, 0.6 %, and 6.25 %, respectively. The proposed method is effective for predicting the future capacity of Li-ion batteries and can be applied to predictive maintenance.

A New Hybrid Forecasting Model Based on Dual Series Decomposition with Long-Term Short-Term Memory

In recent years, ozone (O3) has gradually become the primary pollutant plaguing urban air quality. Accurate and efficient ozone prediction is of great significance to the prevention and control of ozone pollution. The air quality monitoring network provides multisource pollutant concentration monitoring data for ozone prediction, but ozone prediction based on multisource monitoring data still faces the challenges of each station’s series of data. Aiming at the problems of low prediction accuracy and low computational efficiency in traditional atmospheric ozone concentration prediction, ozone concentration prediction using dual series decomposition was proposed by variational mode decomposition (VMD), ensemble empirical mode decomposition (EEMD), and long short-term memory (LSTM). First, the historical data series of Nanjing air quality monitoring stations is decomposed by VMD, and then the EEMD algorithm is applied to the residual of VMD to obtain several characteristic intrinsic mode function (IMF) components; each characteristic IMF component is trained by LSTM to obtain the prediction result of each component, and then the final result can be obtained by linear superposition. The proposed method achieved the best results with R2 = 99%, MSE = 5.38, MAE = 4.54, and MAPE = 3.12. Because LSTM has strong adaptive learning ability and good memory function, it has the learning advantage of long-term memory for long-term data, and the prediction results are more accurate. According to the data, the proposed method is superior to the baseline models in terms of statistical metrics. As a result, the proposed hybrid method can serve as a reliable model for ozone forecasting.