A5018810068- Energy Load and Power Forecasting
- Meteorological Phenomena and Simulations
- Wind and Air Flow Studies
- Climate variability and models
- Climate change and permafrost
- Ferroelectric and Piezoelectric Materials
- Aerodynamics and Fluid Dynamics Research
- Tropical and Extratropical Cyclones Research
- Radio Wave Propagation Studies
- Aeolian processes and effects
- Cryospheric studies and observations
- Air Quality Monitoring and Forecasting
- Robotic Locomotion and Control
- Modular Robots and Swarm Intelligence
- Vehicle emissions and performance
- Fluid Dynamics and Turbulent Flows
- Multiferroics and related materials
- Robotic Path Planning Algorithms
- Computational Physics and Python Applications
- Precipitation Measurement and Analysis
- Plant Water Relations and Carbon Dynamics
- Air Quality and Health Impacts
- Dielectric properties of ceramics
University of Science and Technology Beijing
2022
F-BT- x NT MLCCs were designed and expected to achieve high energy-storage density because of ultrahigh P s value BiFeO 3 system. With enhancement ionic bonding dielectric relaxation, excellen U rec = 9.1 J cm −3 η > 80% achieved at 0.12.
Abstract Short‐term wind speed prediction is essential for economical power utilization. The real‐world data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model multistep prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our processes the local global input features simultaneously. We leverage RP feature...
Accurately representing background error covariances is crucial for data assimilation in numerical weather prediction models. This study compared the performance of National Meteorological Center (NMC) and RandomCV methods estimating a 3DVAR system Weather Research Forecasting (WRF) model, focusing on micro-meteorological environment specific testing area. Results suggest that NMC method may be more suitable this context, although differences between two were not significant. The highlights...
Short-term wind speed prediction is essential for economical power utilization. The real-world data typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model multi-step prediction, namely LR-FFT-RP-MLP/LSTM (Linear Fast Fourier Transformation Rank Pooling Multiple-Layer Perception/Long Short-Term Memory). Our processes the local global input features simultaneously. We leverage (RP) feature extraction...
This paper proposes a prediction approach based on MLP-Mixer with FFT (The fast Fourier transformation). The wind speed series dataset was transformed using the FFT. Extract high dimensional features initially, then deep learning time MLP mixer is introduced to explore and exploit implicit information of for forecasting. We compared different forcasting results by setting lookback premeter 4, 8, 12, 16 hours. On basis two years test dataset, performance proposed FFT-MLP-mixer effectively...
In the present study, an investigation was conducted into characteristics of variation in shallow wind across northeast Horqin grassland by using tower data from 2016 to 2020. The investigative results demonstrate that northwest is dominant at layers 3.5-101m, followed southwest and southeast order. spring, different direction accounts for same proportion. summer, winds are dominant. West prevail autumn. winter, dominance. With increase height, frequency each speed becomes dispersed....
The Plateau Numerical Weather Forecast System (GY-WRF) was evaluated for its ability to forecast spring weather in Danghe South Mountain. forecasted temperature, relative humidity, and wind were compared with GRAPES using data from four automatic stations March April 2022. results showed that GY-WRF had the smallest mean absolute error (MAE) each factor at station 4, a small MAE speed 2, but slightly larger direction. direction, similar trend GY-WRF. better predicting diurnal variation of...
Air pollution is a major environmental issue that affects human health and the environment. In recent years, deep learning has been applied to prediction of air expansion with promising results. This paper provides comprehensive review literature on application related algorithms expansion. The focuses use models such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Hybrid for forecasting. covers studies published between 2018 2023, includes articles from various...
With the development and wide application of advanced weapons, battlefield environment has gradually become more complex harsher, which greatly increases risk rescuers performing search rescue tasks. In view this situation, paper proposes a six-wheeled portable reconfigurable robot, Antibot, is used to replace perform life detection tasks in unknown environments. This robot can adapt terrain through its unique three-rocker-leg passive suspension, be folded up for users carry. The...
Short-term wind speed prediction is essential for economical power utilization. The real-world data typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model multi-step prediction, namely LR-FFT-RP-MLP/LSTM (Linear Fast Fourier Transformation Rank Pooling Multiple-Layer Perception/Long Short-Term Memory). Our processes the local global input features simultaneously. We leverage (RP) feature extraction...