Empirical Decomposition Research Articles

Combining Standard Artificial Intelligence Models, Pre-Processing Techniques, and Post-Processing Methods to Improve the Accuracy of Monthly Runoff Predictions in Karst-Area Watersheds

The complex and unique topography of karst regions highlights the weaknesses of traditional hydrological models which fail to fully generalize them. The successive proposals of standard artificial intelligence (AI) models, pre-processing techniques, and post-processing methods have provided new opportunities to enhance the accuracy of runoff prediction in karst areas. In this study, first, the BP neural network model and the Elman neural network model were used for runoff prediction. Then, the performance of four coupled models—formed by combining two AI pre-processing techniques, Empirical Modal Decomposition (EMD) and Ensemble Empirical Modal Decomposition (EEMD), with the previously mentioned AI models—was investigated. Finally, the accuracy of triple-coupled models, formed by applying the post-processing method of quantile mapping (QM) to the previous coupled models, was estimated. The Nash–Sutcliffe efficiency (NSE), the mean absolute percentage error (MAPE), the root mean square error (RMSE), and the peak percentage of threshold statistics (PPTS) were selected to evaluate and analyze the forecasting results of the above models. The results demonstrated that the BP model had the best prediction effect of the standard AI models, the coupled forecasting models had better prediction accuracy than the standard AI models, and the triple-coupled QM–EMD–Elman model had the best forecasting effect with an NSE value of 0.73, MAPE value of 0.75, RMSE value of 34.60, and PPTS value of 2.36.

Exploiting Asymmetric EEG Signals with EFD in Deep Learning Domain for Robust BCI

Motor imagery (MI) is a domineering paradigm in brain–computer interface (BCI) composition, personifying the imaginary limb motion into digital commandments for neural rehabilitation and automation exertions, while many researchers fathomed myriad solutions for asymmetric MI EEG signals classification, the existence of a robust, non-complex, and subject-invariant system is far-reaching. Thereupon, we put forward an MI EEG segregation pipeline in the deep-learning domain in an effort to curtail the existing limitations. Our method amalgamates multiscale principal component analysis (MSPCA), a novel empirical Fourier decomposition (EFD) signal resolution method with Hilbert transform (HT), followed by four pre-trained convolutional neural networks for automatic feature estimation and segregation. The conceived architecture is validated upon three binary class datasets: IVa, IVb from BCI Competition III, GigaDB from the GigaScience repository, and one tertiary class dataset V from BCI competition III. The average 10-fold outcomes capitulate 98.63%, 96.33%, and 89.96%, the highest classification accuracy for the aforesaid datasets accordingly using the AlexNet CNN model in a subject-dependent context, while in subject-independent cases, the highest success score was 97.69%, outperforming the contemporary studies by a fair margin. Further experiments such as the resolution scale of EFD, comparison with other signal decomposition (SD) methods, deep feature extraction, and classification with machine learning methods also accredits the supremacy of our proposed EEG signal processing pipeline. The overall findings imply that pre-trained models are reliable in identifying EEG signals due to their capacity to maintain the time-frequency structure of EEG signals, non-complex architecture, and their potential for robust classification performance.

Simulation of high-frequency dissolved oxygen dynamics in a shallow estuary, the Corsica River, Chesapeake Bay

Understanding shallow water biogeochemical dynamics is a challenge in coastal regions, due to the presence of highly variable land-water interface fluxes, tight coupling with sediment processes, tidal dynamics, and diurnal variability in biogeochemical processes. While the deployment of continuous monitoring devices has improved our understanding of high-frequency (12 - 24 hours) variability and spatial heterogeneity in shallow regions, mechanistic modeling of these dynamics has lagged behind conceptual and empirical models. The inherent complexity of shallow water systems is represented in the Corsica River estuary, a small basin within the Chesapeake Bay ecosystem, where abundant monitoring data have been collected from long-term monitoring stations, continuous monitoring sensors, synoptic sensor surveys, and measurements of sediment-water fluxes. A state-of-the-art modeling system, the Semi-implicit Cross-scale Hydroscience Integrated System Model (SCHISM), was applied to the Corsica domain with a high-resolution grid and nutrient loads from the most recent version of the Chesapeake Bay watershed model. The Corsica SCHISM model reproduced observed high-frequency variability in dissolved oxygen, as well as seasonal variability in chlorophyll-a and sediment-water fluxes. Time-series signal analyses using Empirical Model Decomposition and spectral analysis revealed that the diurnal and M2 tide frequencies are the dominant high-frequency modes and physical transport contributes a larger share to dissolved oxygen budgets than biogeochemical processes on an hourly time scale. Heterogeneity and patchiness in dissolved oxygen resulting from phytoplankton distributions and geometry-driven eddies amplify the physical transport effect, and on longer time scales oxygen is controlled more by photosynthesis and respiration. Our simulation demonstrates that interactions among physical and biological dynamics generate complex high-frequency variability in water quality and non-linear reposes to nutrient loading and environmental forcing in shallow water systems.

Adaptive Weiner filtering with AR-GWO based optimized fuzzy wavelet neural network for enhanced speech enhancement.

Speech signal enhancement is a subject of study in which a large number of researchers are working to improve the quality and perceptibility of speech signals. In the existing Kalman Filter method, the short-time magnitude or power spectrum due to random variations of noise was a serious problem and the signal-to-noise ratio was very low. This issue severely reduced the perceived qualityand intelligibility of enhanced speech. Thus, this paper intent to develop an improved speech enhancement model and it includes"training phase and testing phase". In the training phase, the input noise corrupted signal is initially fed as input to both STFT-based noise estimation and NMF-based spectrum estimation forestimating the noise spectrum and signal spectrum, respectively. The obtained noise spectrum and the signal spectrum are fed as input to the Wiener filter and these filtered signals are subjected to Empirical Mean Decomposition (EMD).Since, tuning factor η plays a key role in Wiener filter, it has to be determined for each signal and from the denoised signal the bark frequency is evaluated. The computed bark frequency is fed as input to the learning algorithm referred as Fuzzy Wavelet Neural Network (FW-NN)for detecting the suited tuning factor η for the entire input signal in Wiener filter.An Adaptive Randomized Grey Wolf Optimization (AR-GWO) is proposed for proper tuning of the tuning factor η referred as tuned tuning factor (η tuned ). The proposed AR-GWO is the improved version of standard Grey wolf optimization (GWO). In the testing phase, the training is accomplished initially and from which the tuning factor is gathered for each of the relevant input signal. Then, the properly tuned tuning factor (η tuned ) from FW-NN is fed as input to EMD via adaptive wiener filter for decomposing the spectral signal and the output of EMD is denoised enhanced speech signal. At last, the performance of the adopted approach is evaluated to the existing approaches in terms of various metrics. In particular, the computation time of the adopted AR-GWO model is 34.07%, 43.57%, 28.86%, 38.88%, and 16.03% better than the existing GA, ABC, PSO, FF, and GWO approaches respectively.

Natural Gas Price Forecasting by a New Hybrid Model Combining Quadratic Decomposition Technology and LSTM Model

Research on the price prediction of natural gas is of great significance to market participants of all kinds. In order to predict natural gas prices more reliably, this paper introduces a quadratic decomposition technology based on the combination of variational modal decomposition (VMD) and ensemble empirical modal decomposition (EEMD), which decomposes the residual term (Res) after VMD by EEMD; then, a new hybrid model called VMD-EEMD-Res.-LSTM is constructed in combination with the long short-term memory (LSTM) prediction model. The contribution of this new hybrid model is that, unlike existing application research that combines existing decomposition technology with the LSTM model, it does not ignore the important information contained in the residual after the VMD. In order to verify the predictive performance of the proposed new model, this paper uses the data of the spot price of natural gas in the United States to conduct a multistep-ahead empirical comparative analysis. The results show that the new hybrid model constructed in this paper has significant predictive advantages.

PM2.5 Prediction Based on the CEEMDAN Algorithm and a Machine Learning Hybrid Model

The current serious air pollution problem has become a closely investigated topic in people’s daily lives. If we want to provide a reasonable basis for haze prevention, then the prediction of PM2.5 concentrations becomes a crucial task. However, it is difficult to complete the task of PM2.5 concentration prediction using a single model; therefore, to address this problem, this paper proposes a fully adaptive noise ensemble empirical modal decomposition (CEEMDAN) algorithm combined with deep learning hybrid models. Firstly, the CEEMDAN algorithm was used to decompose the PM2.5 timeseries data into different modal components. Then long short-term memory (LSTM), a backpropagation (BP) neural network, a differential integrated moving average autoregressive model (ARIMA), and a support vector machine (SVM) were applied to each modal component. Lastly, the best prediction results of each component were superimposed and summed to obtain the final prediction results. The PM2.5 data of Hangzhou in recent years were substituted into the model for testing, which was compared with eight models, namely, LSTM, ARIMA, BP, SVM, CEEMDAN–ARIMA, CEEMDAN–LSTM, CEEMDAN–SVM, and CEEMDAN–BP. The results show that for the coupled CEEMDAN–LSTM–BP–ARIMA model, the prediction ability was better than all the other models, and the timeseries decomposition data of PM2.5 had their own characteristics. The data with different characteristics were predicted separately using appropriate models and the final combined model results obtained were the most satisfactory.

Robust unsupervised Tursiops aduncus whistle enhancement based on complete ensembled empirical optimal envelope local mean decomposition with adaptive noise.

Whistle enhancement is an essential preprocessing step in studying dolphin behavior and population distributions. We propose a robust unsupervised whistle enhancement scheme based on improved local mean decomposition using adaptive noise estimation and logarithmic spectral amplitude. First, to further mitigate the mode aliasing problem effect in whistle signal decomposition and achieve better spectral separation of modes, we present a complete ensembled empirical optimal envelope local mean decomposition with adaptive noise algorithm. According to the envelope characteristics of the whistle signals, the proposed algorithm optimally and adaptively decomposes the noisy signal into product functions (PFs) with amplitude and frequency modulation. Second, the whistle enhancement framework consists of the improved minima-controlled recursive averaging for adaptive noise estimation, optimally modified log-spectral amplitude for each noisy product function enhancement, and the Hurst index for reconstructing pure whistle signal estimations with the least damaged PFs. Finally, the proposed scheme is applied to a dataset of long calls from two Tursiops aduncus individuals. After constructing the pure whistle dataset, the experimental results show that the proposed scheme performs better than other compared whistle enhancement schemes under different signal-to-noise ratios.

Spatiotemporal Characteristics and Influencing Factors of Sunshine Duration in China from 1970 to 2019

In order to alleviate global warming and the energy crisis, it is of great significance to develop and utilize solar energy resources. Sunshine duration (SD) is considered to be the best substitute for solar radiation and a key factor in evaluating solar energy resources. Therefore, the spatial and temporal characteristics of SD and the reasons for its changes have received extensive attention and discussion. Based on the data of 415 meteorological stations from 1970 to 2019, this paper uses linear trend analysis, Mann–Kendall mutation analysis, the Hurst index, empirical orthogonal decomposition, correlation analysis and partial correlation analysis to analyze the spatiotemporal characteristics of SD and its relationship with influencing factors. The results show that the annual SD in China shows a downward trend, with a climate trend rate of −37.93 h/10a, and a significant decline from 1982 to 2019. The seasonal SD shows a downward trend, and the downward trend is most obvious in summer. The annual and seasonal SD will still show a downward trend in the future. The spatial distribution of SD not only has an overall consistent distribution but also takes the Yellow River from Ningxia to Shandong as the boundary, showing a north–south opposite distribution. Annual SD has a significant positive correlation, a significant negative correlation, a positive correlation and a negative correlation with wind speed, precipitation, temperature and relative humidity, respectively, and it is most closely related to wind speed and precipitation. In addition, the change in SD may also be related to human activities.

Principal component analysis (PCA) based sparrow search algorithm (SSA) for optimal learning vector quantized (LVQ) neural network for mechanical fault diagnosis of high voltage circuit breakers

An essential piece of equipment for the protection and management of the electricity grid is a high voltage(HV) circuit breaker. The reliability and stability of the electricity grid are directly affected by the condition of operation of a high voltage circuit breaker. This study proposes a PCA-SSA-LVQ-based high-voltage circuit breaker diagnosis method to identify mechanical faults of high-voltage circuit breakers more quickly and effectively. Laboratory simulation of vibration signals for different fault states of high voltage circuit breakers. Finite intrinsic mode functions(IMF) are obtained by empirical modal decomposition(EMD) of the simulated vibration signal. The envelope spectrum of the IMF is extracted using the Hilbert envelope transform, and the concept of information entropy is used to determine the entropy value of the envelope as the characteristic quantity of the signal. Using principal component analysis, one can decrease the eigenvectors’ dimension. The high voltage circuit breaker LVQ neural network fault diagnosis model is made, and the initial weight of the LVQ neural network is optimized using the SSA optimization algorithm. The accuracy was improved in the end. The optimized and non-optimized LVQ neural networks were compared. The results show that the PCA-SSA-LVQ neural network has a higher diagnostic rate and faster training convergence. The main contribution of this paper is to reduce the redundancy of feature vectors using the PCA algorithm, optimize LVQ neural network by the SSA algorithm, and creatively use these three algorithms together. The training speed and the accuracy of state recognition are improved.

Attention deficit hyperactivity disorder detection in children using multivariate empirical EEG decomposition approaches: A comprehensive analytical study

Early detection and timely therapeutic intervention are of prime importance to prevent the severity of attention deficit hyperactivity disorder (ADHD) in children. Conventional diagnostic methods are time-taking as they are based on subjective evaluations. The present work proposes utilities of three multivariate empirical-basis decomposition approaches (EDAs) - multivariate empirical mode decomposition (MEMD), multivariate empirical wavelet transform (MEWT), and multivariate variational mode decomposition (MVMD), for ADHD diagnosis using electroencephalography (EEG) signals. A set of 15-features were derived from each EDA-decomposed oscillatory EEG mode. Significant features were identified then by genetic algorithm (GA) and neighborhood component analysis (NCA). Finally, two models -support vector machine with Gaussian radial basis function (SVM-RBF) and artificial neural network (ANN), were employed to classify children into ADHD and control categories using the GA and NCA selected attributes. A publicly available ADHD dataset from the IEEE data portal was considered for this work. Our results have unveiled MEMD-GA-ANN as the optimal classification scheme yielding an accuracy of 96.16%, F1-score of 96.32%, and Matthews correlation coefficient (MCC) of 0.92. Moreover, this study is the first comprehensive experimental analysis to incorporate multivariate EDAs in the process of classifying ADHD children. We believe that the presented mechanisms can be effective for detecting several other neurodevelopmental disorders in children by using EEG signals. Also, it may act as an informative platform for future researchers in this field.

Hyperparameter optimization of support vector machine using adaptive differential evolution for electricity load forecasting

Peak load forecasting plays an integral part in the planning and operating of energy plants for the utility companies and policymakers to devise reliable and stable power infrastructure. However, the electricity load profile is considered a complex signal due to the non-linear and stochastic behavior of the consumer. Therefore, a rigid forecasting model with assertive stochastic and non-linear behavior capturing abilities is required to estimate the demand capacity accurately. To handle these uncertainties, this paper proposed a hybrid model that integrates the multivariate empirical modal decomposition (MEMD) and adaptive differential evolution (ADE) algorithm with a support vector machine (SVM). MEMD allows the decomposition of multivariate data to deteriorate over time to effectively extract the unique information from exogenous variables over different time frequencies to ensure high computational efficiency. The ADE algorithm obtains and tunes the SVM model’s appropriate parameters to effectively avoid trapping into local optimum and returns accurate forecasting results. Consequently, the proposed MEMD-ADE-SVM forecasting model simultaneously achieves good accuracy (93.145%), stability, and convergence rate, respectively. A historical load dataset from the independent system operator (ISO) New England (ISO-NE) energy sector is analyzed to verify the MEMD-ADE-SVM hybrid model. The results show that the developed MEMD-ADE-SVM model outperforms the benchmark frameworks such as; SVR-based model by hybridizing variational mode decomposition, the chaotic mapping mechanism, and the grey wolf optimizer (VMD-SVR-CGWO), SVM based on data preprocessing and whale optimization algorithm (DCP-SVM-WO), intelligent optimized SVR model based on variational mode decomposition and Fast Fourier transform (VMD-FFT-IOSVR), SVR model based on multivariate empirical mode decomposition and particle swarm optimization (EMD-SVR-PSO), and MEMD-ADE-LSTM for day-ahead and week-ahead electricity peak load forecasting in terms of accuracy, stability, and convergence rate.

A Novel Lidar Signal-Denoising Algorithm Based on Sparrow Search Algorithm for Optimal Variational Modal Decomposition

Atmospheric lidar is susceptible to the influence of light attenuation, sky background light, and detector dark currents during the detection process. This results in a large amount of noise in the lidar return signal. To reduce noise and extract a useful signal, a novel denoising method combined with variational modal decomposition (VMD), the sparrow search algorithm (SSA) and singular value decomposition (SVD) is proposed. The SSA is used to optimize the number of decomposition layers K and the quadratic penalty factor α values of the VMD algorithm. Some intrinsic mode function (IMF) components obtained from the VMD-SSA decomposition are grouped and reconstructed according to the interrelationship number selection criterion. Then, the reconstructed signal is further denoised by combining the strong noise-reduction ability of SVD to obtain a clean lidar return signal. To verify the effectiveness of the VMD-SSA-SVD method, the method is compared and analysed with wavelet packet decomposition, empirical modal decomposition (EMD), ensemble empirical modal decomposition (EEMD), and adaptive noise-complete ensemble empirical modal decomposition (CEEMD), and its noise-reduction effect is considerably improved over that of the other four methods. The method can eliminate the complex noise in the lidar return signal while retaining all the details of the signal. The signal is not distorted, the waveform is smoother, and far-field noise interference can be suppressed. The denoised signal is closer to the real signal with higher accuracy, which shows the feasibility and the practicality of the proposed method.

Day-ahead inflow forecasting using causal empirical decomposition

It is essential to have accurate and reliable daily-inflow forecasting to improve short-term hydropower scheduling. This paper proposes a Causal multivariate Empirical mode Decomposition (CED) framework as a complementary pre-processing step for a day-ahead inflow forecasting problem. The idea behind CED is combining physics-based causal inference with signal processing-based decomposition to get the most relevant features among multiple time-series to the inflow values. The CED framework is validated for two areas in Norway with different meteorological and hydrological conditions. The validation results show that using CED as a pre-processing step significantly enhances (up to 70%) the forecasting accuracy for various state-of-the-art forecasting methods. • Pre-processing step is essential for daily inflow forecasting. • A combination of causal-based inference network with decomposition technique is proposed as CED framework. • Multivariate empirical mode decomposition, transfer entropy and conditional mutual information were used in CED framework. • CED framework improved daily inflow forecasting by 70% compared with no preprocessing scenario.

Electrometallurgical Load Forecasting Based on Ensemble Learning Using CEEMDAN

Accurate load forecasting is conducive to stable power supply. It is difficult to forecast electrometallurgical load. It tends to fluctuate rapidly and randomly, especially for the ultra-short-term ones. In this work, we decompose the load into components and abstracting them with heterogeneous learners for the different characteristics. Complete ensemble empirical model decomposition adaptive noise (CEEMDAN) is introduced to data pre-treatment and signal decomposition, and different frequency sub-series are obtained. Then, we explore the complexity of sub-series by sample entropy (SE). For the low-frequency components, a low-complexity Random Forest (RF) model is designed for drawing the outline of the load fluctuating. For the high-frequency ones, a long short-term memory (LSTM) network is adopted to get the details of the fluctuating. Combined forecasting is implemented by reconstructing the predictions of the above two learners. The novel model is compared with several common models for electrometallurgical load forecasting by using industrial data of an electro-fused magnesium enterprise. Experimental results show that the proposal significantly outperforms the others.

PM2.5 concentration forecasting through a novel multi-scale ensemble learning approach considering intercity synergy

Accurate PM 2.5 concentration prediction can provide reliable air pollution warning information to the public. However, previous studies have often focused on the data of the target city itself, ignoring the interaction among cities in the same region. In this paper, we develop a multi-scale ensemble learning approach to forecast daily PM 2.5 concentrations of the target city by modeling its air and climate indicators, and PM 2.5 value of its neighboring cities. First, the proposed approach smooths the multivariate data by singular spectrum analysis and performs multi-feature selection based on distance factor and predictive power of data. Second, the inherent association among the obtained multiple features is captured by multivariate empirical modal decomposition. Third, the Hurst exponent is applied to match each time scale with the corresponding predictor for multi-step prediction. Finally, the forecasting values of all time scales are summed to obtain the PM 2.5 concentration forecasting results of the target city. Four experiments involving Beijing, Wuhan, and Shenzhen are carried out to verify the accuracy and robustness of the proposed approach. The experimental results show that our approach outperforms all benchmark models, and introducing city synergy strategy can improve the forecasting performance significantly. • The synergistic effect of surrounding cities improves the forecasting accuracy. • Double-level feature selection is established to extract the effective features. • Multivariate decomposition algorithm implements multi-source data fusion well. • A forecasting model matching strategy is developed based on the average Hurst exponent. • Average MAPE improvements of the approach against benchmark models are above 8.9%.

A two-layer SSA-XGBoost-MLR continuous multi-day peak load forecasting method based on hybrid aggregated two-phase decomposition

To further improve the prediction accuracy under the realization of rolling peak load prediction scenarios for the coming month, an aggregated hybrid two-phase decomposition with two-layer prediction model architecture (ICEEMDAN-SE-VMD-SSA-XBoost-MLR) is proposed in this paper. First, a fully integrated empirical modal decomposition with improved adaptive noise (ICEEMDAN) is used to initially decompose the historical peak load time series, which leads to several eigenmodal functions (IMFs), and by calculating the sample entropy (SE) of each IMF, the IMFs with similar SEs are aggregated and reconstructed into load components representing different time scales. Then, the variational modal decomposition (VMD) is introduced to quadratically decompose the less regular parts of the load components to fully weaken their non-smooth characteristics. Then, extreme gradient boosting (XGBoost) is used to assist in establishing the feature engineering, combining each load component to form the data set required for the prediction model, and using the sparrow search algorithm (SSA) optimized XGBoost with multiple linear regression (MLR) to construct the first layer prediction model for each component, and the prediction results of each component are superimposed to obtain the preliminary prediction results. Finally, inspired by the idea of integrated learning, an error correction link is proposed in this paper to make a secondary prediction of the preliminary prediction results by XGBoost, to better track the fluctuation of load details, realize the error correction of the preliminary prediction results and improve the prediction accuracy.

Revealing the scale‐ and location‐specific variation and control factors of soil salinity using bi‐dimensional empirical modal decomposition

AbstractThe key to saline land management and soil salinity control is to clarify the dynamics of soil salinity and the characteristics of environmental factors. However, due to the high heterogeneity of soil salinity, the influence of environmental factors on soil salinity variation at specific scales and locations is still unclear. The purpose of this study is to reveal the variability characteristics and controlling factors of soil salinity in the Wei‐Ku Oasis during different seasons. One hundred and eighty‐two topsoil samples (0–20 cm) were acquired during the irrigation and non‐irrigation seasons (IRRS and NIRRS) in the study area. This study predicted soil surface salinity at 90 m spatial resolution from randomForest (RF) models and measured data. Based on the mapping, a bi‐dimensional empirical modal decomposition (BEMD) algorithm was applied to extract the variation of the soil salinity at different scales and locations in the IRRS and NIRRS. Subsequently, correlation analysis, semi‐variance functions, and redundancy analysis were applied to dissect the correlation and main control factors between soil salinity and the environment at three different scales. The results indicated that soil salinity was greater in the NIRRS at the Weiku Oasis. Soil salinity was decomposed into five intrinsic modal functions with spatial variability scales of 6.20–50.61 km and 7.93–50.18 km during the IRRS and NIRRS, respectively. The relationships between environmental factors and soil salinity were scale‐ and location‐specific, suggesting a complex interrelationship between topography, temperature, vegetation cover, and soil salinity. The normalized difference vegetation index was found to be the main factor affecting small‐scale seasonal variation in soil salinity, whereas the large‐scale spatial distribution of soil salinity was most affected by evapotranspiration and temperature. These findings highlight the effectiveness of BEMD in revealing the scale and location control of soil salinity.

Speech enhancement via adaptive Wiener filtering and optimized deep learning framework

In today’s scientific epoch, speech is an important means of communication. Speech enhancement is necessary for increasing the quality of speech. However, the presence of noise signals can corrupt speech signals. Thereby, this work intends to propose a new speech enhancement framework that includes (a) training phase and (b) testing phase. The input signal is first given to STFT-based noise estimate and NMF-based spectra estimate during the training phase in order to compute the noise spectra and signal spectra, respectively. The obtained signal spectra and noise spectra are then Wiener-filtered, then empirical mean decomposition (EMD) is used. Because the tuning factor of Wiener filters is so important, it should be computed for each signal by coaching in a fuzzy wavelet neural network (FW-NN). Subsequently, a bark frequency is computed from the denoised signal, which is then subjected to FW-NN to identify the suitable tuning factor for all input signals in the Wiener filter. For optimal tuning of [Formula: see text], this work deploys the fitness-oriented elephant herding optimization (FO-EHO) algorithm. Additionally, an adaptive Wiener filter is used to supply EMD with the ideal tuning factor from FW-NN, producing an improved speech signal. At last, the presented approach’s supremacy is proved with varied metrics.

Uncertainties of gross primary productivity of Chinese grasslands based on multi-source estimation

Gross primary productivity (GPP) is an important parameter in the carbon cycle and climate change studies. The results of GPP fluxes estimated based on multiple models or remote sensing vary widely, but current studies of GPP in Chinese grasslands tend to ignore data uncertainty. In this study, uncertainty analysis of GPP datasets estimated based on terrestrial ecosystem models and remote sensing was conducted using cross-validation, standard error statistics, and ensemble empirical modal decomposition. We found that 1) the fit coefficients R2 of two-by-two cross-validation of GPP datasets mostly exceeded 0.8 at the global scale. 2) GPP from different sources were consistent in portraying the spatial and temporal patterns of GPP in Chinese grasslands. However, due to many differences in model structure, parameterization and driving data, some uncertainties still exist, especially in the parts of dry-cold areas where the standard deviations are relatively large. 3) Uncertainties were higher for future scenarios than for historical periods, and GPP uncertainties were much higher for future high-emissions scenarios than for low- and medium-emissions scenarios. This study highlighted the need for uncertainty analysis when GPP is applied to spatio-temporal analysis, and suggested that when comparing and assessing carbon balance conditions, multiple source data sets should be combined to avoid misleading conclusion due to uncertainty.

Spatio‐Temporal Variability of Suspended Sediment Fronts (SSFs) on the Inner Shelf of the East China Sea: The Contribution of Multiple Factors

AbstractModulated by a host of complex processes, suspended sediment fronts (SSFs) on the inner shelf of the East China Sea persist strongly and vary notably. Using hourly suspended sediment concentration data collected by the Geostationary Ocean Color Imager over the period 2011–2021, a gradient‐based edge detection algorithm was implemented to extract SSFs; the frontal probability (FP) and seasonal and interannual variability were identified and interpreted. Pronounced frontal activity is principally confined to the nearshore waters within the 60‐m isobaths and decreases with increasing offshore distance. Frontogenesis is mainly determined by the bottom topography and tide‐induced mixing. Empirical orthogonal function decompositions reveal that the seasonal cycle dominates the variability of SSFs, which responds to the cycles of winds and related changes in coastal currents and upwelling. The highest FPs are identified in winter when wind‐induced suspended sediment transport and resuspension reach their annual maxima. In summer, stratification and the intrusion of Kuroshio subsurface water are not conducive to frontogenesis. Furthermore, the discharge of the Yangtze River has a certain influence on the frontal variability in the waters around the Zhoushan Archipelago. Notably, the interannual variability of SSFs is modulated by the El Niño‐Southern Oscillation. These findings, based on a comprehensive dataset of SSFs over 10 years, can usefully inform the studies of marine pollutant transport, sedimentary dynamics, fisheries, and wider ecological processes in the study area.