An Innovative Hourly Water Demand Forecasting Preprocessing Framework with Local Outlier Correction and Adaptive Decomposition Techniques

In this study, different kinds of hybrid Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithms with forecasting models including Random Forest (RF), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) neural networks, are developed to estimate the mean daily wind speed at the height of 2 m in Ağrı city (WS st12 ), Turkey. In these hybrid models, different layer networks of single and integrated LSTM and GRU models include general single LSTM, general single GRU, simple coupled LSTM-GRU, and novel coupled LSTM with GRU through Addition layer (i.e., LSTM + GRU model) structures are applied. The most effective parameters on the WS st12 , from a list of on-site potential meteorological parameters and wind speed values in its adjacent cities of Ağrı province from Jan 2015–Dec 2019 through the Pearson correlation coefficient method, are determined. In the hybrid CEEMDAN and DNNs-based models, State activation functions (SAF), numbers of hidden neurons (NHN), dropout rates (P-rate), and network structural architect (NSA) as the meta-parameters are tuned for lessening the impact of overfitting/underfitting dilemmas and improving modeling performance. According to the comparison plots, performance evaluation measures, and total learnable parameter (TLP), the novel developed hybrid CEEMDAN-RF-(LSTM + GRU) model is confirmed as the best approach with an R 2 of 0.86 while, in the optimal scenario using the RF model, R 2 was 0.47. Graphical Abstract Based on the graphical snapshot, this study focuses on estimating daily mean wind speed at a 2-meter height in Ağrı, Turkey, using hybrid data-driven models. The research integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm with advanced forecasting techniques, including Random Forest (RF), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) neural networks. The modeling framework explores various configurations, such as standalone LSTM and GRU, coupled LSTM-GRU structures, and a novel LSTM + GRU model using an Addition layer to enhance predictive accuracy.

Water Distribution Networks (WDNs) are crucial for meeting current and future urban water demands. Knowledge of future water demand at different time scales is fundamental for optimal WDN design and operations. Various predictive models of water demand have been proposed in the literature, ranging from traditional time series analysis to cutting-edge machine learning and deep learning techniques. However, the task of forecasting urban water demand remains mostly decoupled from the design of the optimal control of the related WDN. Current performance assessment of demand predictive models focuses predominantly on forecast accuracy, overlooking their practical implications on WDN operations. Meanwhile, the existing research on WDN management often assumes either perfect knowledge of future water demands or employs empirical approximations and aggregate statistics to estimate future water needs. This study bridges this gap by scrutinizing the actual operational value of water demand forecasts in designing optimal operations of WDNs.Here, we develop a forecast-informed optimal WDN control framework to evaluate the operational value of water demand forecasts for WDN operations. Our framework comprises two main modules. The first module computes water demand forecasts. We comparatively evaluate a suite of different forecasting models —including Seasonal Auto-Regressive Integrated Moving Average with eXogenous factors, Multilayer Perceptron, Convolutional Neural Network, and Long Short-Term Memory (a network augmented with an attention mechanism) —across various forecast horizons (1/6/12 hours and 1/3/7/14 days ahead). The most accurate forecasts are integrated into the second module, an economic nonlinear Model Predictive Control (MPC) algorithm designed to optimize WDN operations. Within this module, an Artificial Neural Network (ANN) – based surrogate model encapsulates the hydraulics of the physical WDN, enhancing the optimization process while reducing complexity.We demonstrate our forecast-informed optimal WDN control framework on a real WDN of a rural town with approximately 10,000 inhabitants. Water demand data collected in the Netherlands for a period of 10 years (2007-2017) at 5-minute resolution and corresponding meteorological data are used to train the water demand forecasting models. The MPC module computes the optimal control sequence for 7 pumps and 1 valve in the WDN to minimize pump energy costs while meeting water demands and ensuring safety storage in 5 tanks. Initial findings reveal that the ANN-based surrogate model can accurately incorporate the WDN characteristics (R2 > 0.85), facilitating its integration into the MPC for an efficient and simplified representation of a real-world WDN. Further, MPC fed by 24-hour ahead water demand forecasts achieves potential energy savings of approximately 18% compared to a benchmark rule-based control strategy. Our framework yields a versatile simulation-based optimization tool for evaluating the impact of demand forecasts on WDN management. Future research efforts will aim at refining and comparing deterministic and stochastic water demand forecasts within the MPC framework, under diverse operational objectives.

The performance of tissue imaging is improved by tissue harmonic imaging (THI) to expand and enhance the range and level of clinical diagnosis for many diseases. The separation based on High-pass filtering (S_HPF) is a commonly used method for extracting harmonic components from ultrasonic echo signals. However, the cut-off frequency, order and algorithm to realize a high-pass filter have a great influence on the separation accuracy of harmonic signals. In present study, a novel separation method (S_CEEMDAN) based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm is proposed for adaptively separating harmonic components from ultrasonic echo signals. First, we calculate the ensemble size of CEEMDAN adaptively based on the added noise level, and draw a sum of intrinsic mode functions (IMFs) from the ultrasonic echo signals by CEEMDAN. Then, the spectrum of each IMF is computed and evaluated, and the IMFs containing both fundamental and harmonic components are further decomposed by using the CEEMDAN algorithm. This separation process is end until all of IMFs have been divided into either fundamental or harmonic categories. Finally, the corresponding fundamental and harmonic echo signals are yielded by accumulating separately these two categories. In experiments, simulated ultrasonic echo signals with a center frequency of 3.5MHz are separated by the proposed S_CEEMDAN method, and the results are compared with those processed by S_HPF. The edge of the harmonic image by S_CEEMDAN marginally better defined than S_HPF. The indices for the harmonic signals separated by S_CEEMDAN and S_HPF, respectively, are as follows: the center frequencies of 6.66 MHz and 6.65 MHz, 3 dB bandwidths of 1.04 MHz and 1.05 MHz, 6 dB bandwidths of 1.59 MHz and 1.55 MHz, signal-to-noise ratios (SNRs) of 14.00 and 13.63, and image contrasts of 7.01 and 7.06. In conclusion, due to good adaptive characteristics, and lower reconstruction errors, the proposed S_CEEMD method is superior to S_HPF in the performance of spectral accuracy and harmonic imaging. This method could be potentially alternative to the current method for the ultrasonic harmonic separation.

Deep learning models, including recurrent neural network (RNN) and gated recurrent unit (GRU), were used to construct the clinical prognostic prediction models for peritoneal dialysis (PD) patients based on routine clinical data. The performance of the RNN and GRU were compared with logistic regression (LR), which is commonly used in medical researches. The possible underlining clinical implications based on the result from the GRU model were also investigated. We used the clinical data from the PD center of Peking University Third Hospital as the data source. Both the baseline data at the beginning of dialysis, and the follow-up and prognostic data of the patients were used by the RNN and GRU prediction models. The hyper-parameters were tuned based on the 10-fold cross-validation. The risk prediction performance of each model was evaluated via area under the receiver operation characteristic curve (AUROC), recall rate and F1-score on the testset. A total of 656 patients with the 261 occurrences of death were included in the experiment. The total number of all diagnostic records were 13 091. The results on the testset showed that the AUROC of the LR model, RNN model, and GRU model was 0.701 4, 0.786 0, and 0.814 7, respectively. The predictive performances of the GRU and RNN models were significantly better than that of the LR model. The performances of the GRU and RNN models assessed by recall rate and F1-score were also significantly better than that of the LR model, in which the GRU model reached the best performance. In addition, the recall rates were different among different causes of death or by different prediction time windows. The recurrent neural network model, especially the GRU model, is more effective in predicting PD patients' prognosis as compared with the LR model. This new model may be helpful for clinicians to provide timely intervention, thus improving the quality of care of PD.

Electricity load demand is the fundamental building block for all utilities planning. The load demand data has nonlinear and non-stationary characteristics, which make it difficult to be predicted accurately by just computational intelligence or ensemble methods. Ensemble methods like Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is a powerful tool to forecast power load demand time series. Heterogeneous ensemble, a combination of two base models, will be distinct or more powerful in forecasting power load demand. In this paper, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method is hybridized with three computational intelligence-based predictors: support vector regression (SVR), artificial neural network (ANN) and random forest (RF). The basis of this paper was to conduct a comparative study on the accuracy of the forecasting result from using heterogeneous ensemble method to individual computational intelligence or ensemble method for four different horizons. The performances of the heterogeneous method are compared and discussed. It shows that heterogeneous method has outperformed the individual computational intelligence and ensemble methods. Possible future works are also recommended for power load demand forecasting.

A hybrid forecasting model of carbon emissions with optimized VMD and error correction

Warships play an important role in the modern sea battlefield. Research on the line spectrum features of warship radio noise signals is helpful to realize the classification and recognition of different types of warships, and provides critical information for sea battlefield. In this paper, we proposed a novel linear spectrum frequency feature extraction technique for warship radio noise based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), duffing chaotic oscillator (DCO), and weighted-permutation entropy (W-PE). The proposed linear spectrum frequency feature extraction technique, named CEEMDAN-DCO-W-PE has the following advantages in comparison with other linear spectrum frequency feature extraction techniques; (i) as an adaptive data-driven algorithm, CEEMDAN has more accurate and more reliable decomposition performance than empirical mode decomposition (EMD) and ensemble EMD (EEMD), and there is no need for presetting parameters, such as decomposition level and basis function; (ii) DCO can detect the linear spectrum of narrow band periodical warship signals by way of utilizing its properties of sensitivity for weak periodical signals and the immunity for noise; and (iii) W-PE is used in underwater acoustic signal feature extraction for the first time, and compared with traditional permutation entropy (PE), W-PE increases amplitude information to some extent. Firstly, warship radio noise signals are decomposed into some intrinsic mode functions (IMFs) from high frequency to low frequency by CEEMDAN. Then, DCO is used to detect linear spectrum of low-frequency IMFs. Finally, we can determine the linear spectrum frequency of low-frequency IMFs using W-PE. The experimental results show that the proposed technique can accurately extract the line spectrum frequency of the simulation signals, and has a higher classification and recognition rate than the traditional techniques for real warship radio noise signals.

Financial time series forecasting model based on CEEMDAN and LSTM

I335 the training of Support Vector Machine (SVM) classification model, some problems such as over-fitting, under-fitting, slow training speed and prediction affected by penalty and kernel function parameters are exposed. A fault classification method of rolling bearing based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Grey Wolf Optimization (GWO) -SVM is proposed. Firstly, the acquire signals are adaptively decomposed into a plurality of Intrinsic Mode Function(IMF) component by CEEMDAN, and the energy entropy of each IMF component is extracted to form a set of high dimensional feature vector. Then, the processed feature vectors are introduced into the diagnosis network of GWO-SVM algorithm to build a fault classification model of motor rolling bearing. The classification results show that the CEEMDAN and GWO-SVM fault classification network of motor rolling bearing has higher accuracy and shorter diagnosis time than Particle Swarm Optimization (PSO) -SVM and Cross Validation (CV) -SVM.

Based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) theory, a new adaptive hybrid algorithm for sea clutter denoising is proposed. The chaotic sea clutter signals are decomposed into several intrinsic modal functions (IMF) which start from high-frequency scales to low-frequency scales by using CEEMDAN. According to the relationship between the pretreatment threshold layer and the maximum cross correlation coefficient of the original signal and each IMF corresponding the layer, the proposed algorithm can independently select the wavelet threshold denoising to pretreat. After the pretreatment of original signals, we continue to decompose the signal by CEEMDAN. And later, according to the relationship between the first local minimum corresponding the layers of two adjacent critical IMFs identified by the cross correlation coefficients of the original signal and each IMF, the proposed algorithm adaptively selects the IMFs which need to be filtered. Finally, the IMFs after filtering are reconstructed into a new signal. Rossler, Lorenz system and the measured sea clutter data were selected as examples to study, the result shows that: under the condition of low noise (SNR ≥ 5dB) and high noise (SNR ≤ 0dB), the proposed algorithm can decrease the root mean square error by at least 57% and 72% compared with wavelet threshold denoising etc, the signal to noise ration increased by 3.18-5.64db and 5.73-7.45db. Moreover, the root mean square error after sea clutter signal denoising can be reduced by one order of magnitude, reaching 0.0006147 while the model before denoising only reach 0.0084, which shows that the proposed algorithm is effective for sea clutter signal denoising.

Aiming at power quality detection and noise pollution, in combination with complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), permutation entropy (PE) and wavelet threshold denoising based on undecimated wavelet transform (UWT), a transient power quality denoising method based on CEEMDAN and UWT is proposed. CEEMDAN decomposes the disturbance signal into a series of intrinsic mode function with single-component characteristics, UWT denoising is used to deal with the noise components screened out by PE and reconstruction to obtain the original signal after denoising. The method is implemented in LabVIEW and simulated independently, the results verify the effectiveness of the method. Finally, on the basis of PXI equipment, a detection device based on LabView is built, which provides a new idea for the development of power quality detection system.

Remotely sensed soil moisture forecasting through satellite-based sensors to estimate the future state of the underlying soils plays a critical role in planning and managing water resources and sustainable agricultural practices. In this paper, Deep Learning (DL) hybrid models (i.e., CEEMDAN-CNN-GRU) are designed for daily time-step surface soil moisture (SSM) forecasts, employing the gated recurrent unit (GRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and convolutional neural network (CNN). To establish the objective model’s viability for SSM forecasting at multi-step daily horizons, the hybrid CEEMDAN-CNN-GRU model is tested at 1st, 5th, 7th, 14th, 21st, and 30th day ahead period by assimilating a comprehensive pool of 52 predictor dataset obtained from three distinct data sources. Data comprise satellite-derived Global Land Data Assimilation System (GLDAS) repository a global, high-temporal resolution, unique terrestrial modelling system, and ground-based variables from Scientific Information Landowners (SILO) and synoptic-scale climate indices. The results demonstrate the forecasting capability of the hybrid CEEMDAN-CNN-GRU model with respect to the counterpart comparative models. This is supported by a relatively lower value of the mean absolute percentage and root mean square error. In terms of the statistical score metrics and infographics employed to test the final model’s utility, the proposed CEEMDAN-CNN-GRU models are considerably superior compared to a standalone and other hybrid method tested on independent SSM data developed through feature selection approaches. Thus, the proposed approach can be successfully implemented in hydrology and agriculture management.

An accurate prediction of carbon pricing is essential in carbon emission management, and also provides an important role for governments to formulate corresponding policies. However, due to the inherent complexity and dynamics of carbon price sequence, the effectiveness of different decomposition algorithms for carbon price remains to be tested. In addition, existing studies lack a systematic framework to explore the organic integration of external factors and secondary decomposition technology, and the feature processing of complex external factors still needs to be improved. In order to overcome the shortcomings of existing research, This paper presents a Variational Modal Decomposition(VMD) algorithm and a Complete Ensemble Empirical Mode Decomposition with Adaptive Second decomposition technology of Noise(CEEMDAN) decomposition algorithm, and extract the features of external factors by Extreme Gradient Boosting (XGBoost) algorithm. The HI-VMD-PE-CEEMDAN-XGBoost-Transformer model for predicting carbon price is constructed by the combined Transformer algorithm. Specifically, first, we use Hampel identifer(HI) to detect and rectify the anomalies in the original sequence. After applying Variational Mode Decomposition(VMD) decomposition algorithm, Permutation Entropy(PE) is utilized to reassemble the decomposed component. Quadratic Decomposition is performed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN) algorithm. Then, the XGBoost algorithm is employed to extract features of external factors and screen key factors as predictive input variables. Finally, Transformer, which has stronger capability of large-scale data parallel processing, is selected as the prediction model to achieve a more scientific and effective carbon price prediction. The empirical analysis results based on EU carbon market data verify the validity and superiority of the proposed model in different forecasting scenarios.

Accurate power load forecasting plays an important role in smart grid analysis. To improve the accuracy of forecasting through the three-level “decomposition–optimization–prediction” innovation, this study proposes a prediction model that integrates complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the improved sparrow search algorithm (ISSA), a convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM). A series of simpler intrinsic mode functions (IMFs) with different frequency characteristics can be decomposed by CEEMDAN from data, then each IMF is reconstructed based on calculating the sample entropy of each IMF. The ISSA introduces three significant enhancements over the standard sparrow search algorithm (SSA), including that the initial distribution of the population is determined by the optimal point set, the position of the discoverer is updated by the golden sine strategy, and the random walk of the population is enhanced by the Lévy flight strategy. By the optimization of the ISSA to the parameters of the CNN-BiLSTM model, integrating the prediction results of the reconstructed IMFs in the sub-models can obtain the final prediction result of the data. Through the performance indexes of the designed prediction model, the application case results show that the proposed combined prediction model has a smaller prediction error and higher prediction accuracy than the eight comparison models.

Offshore platform pipeline leakage detection faces severe challenges from complex marine environments, where intense environmental noise interference and complex signal characteristics make traditional methods difficult to achieve accurate leakage valve localization. To address this technical challenge, this study proposes an offshore platform pipeline leakage valve localization method based on dynamic time warping distance-based complete ensemble empirical mode decomposition with adaptive noise (DCEEMDAN) and adaptive temporal–spatial fusion network (ATSFN). First, by introducing dynamic time warping distance similarity measurement into the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) framework and combining probability density function feature extraction, adaptive denoising of acoustic emission signals in marine environments is achieved. Second, a temporal–spatial feature extraction architecture with a parallel multiscale convolutional neural network (CNN) and a hierarchical GRU is designed, realizing deep fusion of CNN spatial features and GRU temporal features through a cross-attention mechanism. Finally, an end-to-end intelligent monitoring system is constructed, achieving high-precision localization of 10 valve positions through dual-stage verification combining laboratory experiments and offshore platform field measurements. Experimental results show that DCEEMDAN outperforms traditional EMD series algorithms, achieving a signal-to-noise ratio (SNR) of 19.69 dB with 16.6% improvement over CEEMDAN. ATSFN achieves average localization accuracies of 94.38% and 95.75% under 4 MPa and 5 MPa conditions, respectively, representing improvements of 10.9% and 10.77% over best baseline models. Under extreme noise conditions, the model maintains localization accuracy above 82.3%, demonstrating excellent noise robustness. This research provides an effective technical solution for offshore platform pipeline leakage detection.