A Frequency Decomposition-Based Hybrid Forecasting Algorithm for Short-Term Reactive Power

This paper proposes a new frequency decomposition-based hybrid reactive power forecasting algorithm, EEMD-LSTM-RFR (ELR), which adopts a strategy of frequency decomposition prediction after ensemble empirical mode decomposition and then data reconstruction to improve the prediction ability of reactive power. This decomposition process can compress the high frequency of reactive power and benefits the following separate forecasting. Long short-term memory is proposed for the high-frequency feature of reactive power to deal with the forecasting difficulty caused by strong signal disturbance and randomness. In contrast, random forest regression is applied to the low-frequency part in order to speed up the forecasting. Four classical algorithms and four hybrid algorithms based on different signal decompositions are compared with the proposed algorithm, and the results show that the proposed algorithm outperforms those algorithms. The predicting index RMSE decreases to 0.687, while the fitting degree R2 gradually approaches 1 with a step-by-step superposition of high-frequency signals, indicating that the proposed decomposition-predicting reconstruction strategy is effective.

Global well-posedness for the generalized Navier-Stokes-Coriolis equations with highly oscillating initial data

We study the small initial date Cauchy problem for the generalized incompressible Navier-Stokes-Coriolis equations in critical hybrid-Besov space $\dot{\mathscr{B}}_{2,\, p}^{\frac{5}{2}-2\alpha, \frac{3}{p}-2\alpha+1}(\mathbb{R}^3)$ with $1/2<\alpha<2$ and $2\leq p\leq 4$. We prove that hybrid-Besov spaces norm of a class of highly osillating initial velocity can be arbitrarily small. and we prove the estimation of highly frequency $L^p$ smoothing effect for generalized Stokes-Coriolis semigroup with $1\leq p\leq\infty$, At the same time, we prove space-time norm estimation of hybrid-Besov spaces for Stokes-Coriolis semigroup. From this result we deduce bilinear estimation in our work space. Our method relies upon Bony’s high and low frequency decomposition technology and Banach fixed point theorem.

Identification of Food/Nonfood Visual Stimuli from Event-Related Brain Potentials

Although food consumption is one of the most basic human behaviors, the factors underlying nutritional preferences are not yet clear. The use of classification algorithms can clarify the understanding of these factors. This study was aimed at measuring electrophysiological responses to food/nonfood stimuli and applying classification techniques to discriminate the responses using a single-sweep dataset. Twenty-one right-handed male athletes with body mass index (BMI) levels between 18.5% and 25% (mean age: 21.05 ± 2.5 ) participated in this study voluntarily. The participants were asked to focus on the food and nonfood images that were randomly presented on the monitor without performing any motor task, and EEG data have been collected using a 16-channel amplifier with a sampling rate of 1024 Hz. The SensoMotoric Instruments (SMI) iView XTM RED eye tracking technology was used simultaneously with the EEG to measure the participants’ attention to the presented stimuli. Three datasets were generated using the amplitude, time-frequency decomposition, and time-frequency connectivity metrics of P300 and LPP components to separate food and nonfood stimuli. We have implemented k -nearest neighbor (kNN), support vector machine (SVM), Linear Discriminant Analysis (LDA), Logistic Regression (LR), Bayesian classifier, decision tree (DT), and Multilayer Perceptron (MLP) classifiers on these datasets. Finally, the response to food-related stimuli in the hunger state is discriminated from nonfood with an accuracy value close to 78% for each dataset. The results obtained in this study motivate us to employ classifier algorithms using the features obtained from single-trial measurements in amplitude and time-frequency space instead of applying more complex ones like connectivity metrics.

Pre-Stack Seismic Data-Driven Pre-Salt Carbonate Reef Reservoirs Characterization Methods and Application

Carbonate reservoirs have significant reserves globally, but the substantial heterogeneity brings intractable difficulties to exploration. In the work area, the thick salt rock reduces the resolution of pre-salt seismic signals and increases the difficulty of reservoir characterization. Therefore, this paper proposes to utilize wavelet frequency decomposition technology to depict the seismic blank reflection area’s signal and improve the pre-salt signal’s resolution. The high-precision pre-stack inversion based on Bayesian theory makes full use of information from various angles and simultaneously inverts multiple elastic parameters, effectively depicting reservoirs with substantial heterogeneity. Integrating the high-precision inversion results and the Kuster-Toksöz model, a porosity prediction method is proposed. The inversion results are consistent with the drilling rock samples and well-logging porosity results. Moreover, the reef’s accumulation and growth, which conform to the geological information, proves the accuracy of the above methods. This paper also discusses the seismic reflection characteristics of reefs and the influence of different lithological reservoirs on the seismic waveform response characteristics through forward modeling, which better proves the rationality of porosity inversion results. It provides a new set of ideas for future pre-salt carbonate reef reservoirs’ prediction and characterization methods.

How well do multi-satellite products capture the space-time dynamics of precipitation? Part I: five products assessed via a wavenumber-frequency decomposition

As more global satellite-derived precipitation products become available, it is imperative to evaluate them more carefully for providing guidance as to how well precipitation space-time features are captured for use in hydrologic modeling, climate studies and other applications. Here we propose a space-time Fourier spectral analysis and define a suite of metrics which evaluate the spatial organization of storm systems, the propagation speed and direction of precipitation features, and the space-time scales at which a satellite product reproduces the variability of a reference “ground-truth” product (“effective resolution”). We demonstrate how the methodology relates to our physical intuition using the case study of a storm system with rich space-time structure. We then evaluate five high-resolution multi-satellite products (CMORPH, GSMaP, IMERG-early, IMERG-final and PERSIANN-CCS) over a period of two years over the southeastern US. All five satellite products show generally consistent space-time power spectral density when compared to a reference ground gauge-radar dataset (GV-MRMS), revealing agreement in terms of average morphology and dynamics of precipitation systems. However, a deficit of spectral power at wavelengths shorter than 200 km and periods shorter than 4 h reveals that all satellite products are excessively “smooth”. The products also show low levels of spectral coherence with the gauge-radar reference at these fine scales, revealing discrepancies in capturing the location and timing of precipitation features. From the space-time spectral coherence, the IMERG-final product shows superior ability in resolving the space-time dynamics of precipitation down to 200 km and 4 h scales compared to the other products.

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.