期刊：
International Journal of Environmental Research and Public Health,2018年15(5):1032- ISSN：1661-7827
通讯作者：
Zhang, Qiuwen;Zhang, Gui
作者机构：
[Zhang, Xike; Zhang, Qiuwen] Huazhong Univ Sci & Technol, Sch Hydropower & Informat Engn, Wuhan 430074, Hubei, Peoples R China.;[Zhang, Xike; Nie, Zhiping] Hunan City Univ, Sch Municipal & Mapping Engn, Yiyang 413000, Peoples R China.;[Zhang, Gui; Que, Huafei] Cent South Univ Forestry & Technol, Key Lab Digital Dongting Lake Basin Hunan Prov, Changsha 410004, Hunan, Peoples R China.;[Gui, Zifan] Shenzhen Garden Management Ctr, Shenzhen 518000, Peoples R China.
通讯机构：
[Zhang, Qiuwen] H;[Zhang, Gui] C;Huazhong Univ Sci & Technol, Sch Hydropower & Informat Engn, Wuhan 430074, Hubei, Peoples R China.;Cent South Univ Forestry & Technol, Key Lab Digital Dongting Lake Basin Hunan Prov, Changsha 410004, Hunan, Peoples R China.
关键词：
daily land surface temperature;forecasting;data-driven;hybrid model;Ensemble Empirical Mode Decomposition (EEMD);Long Short-Term Memory (LSTM);Neural Network (NN);Dongting Lake basin
摘要：
Daily land surface temperature (LST) forecasting is of great significance for application in climate-related, agricultural, eco-environmental, or industrial studies. Hybrid data-driven prediction models using Ensemble Empirical Mode Composition (EEMD) coupled with Machine Learning (ML) algorithms are useful for achieving these purposes because they can reduce the difficulty of modeling, require less history data, are easy to develop, and are less complex than physical models. In this article, a computationally simple, less data-intensive, fast and efficient novel hybrid data-driven model called the EEMD Long Short-Term Memory (LSTM) neural network, namely EEMD-LSTM, is proposed to reduce the difficulty of modeling and to improve prediction accuracy. The daily LST data series from the Mapoling and Zhijaing stations in the Dongting Lake basin, central south China, from 1 January 2014 to 31 December 2016 is used as a case study. The EEMD is firstly employed to decompose the original daily LST data series into many Intrinsic Mode Functions (IMFs) and a single residue item. Then, the Partial Autocorrelation Function (PACF) is used to obtain the number of input data sample points for LSTM models. Next, the LSTM models are constructed to predict the decompositions. All the predicted results of the decompositions are aggregated as the final daily LST. Finally, the prediction performance of the hybrid EEMD-LSTM model is assessed in terms of the Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Pearson Correlation Coefficient (CC) and Nash-Sutcliffe Coefficient of Efficiency (NSCE). To validate the hybrid data-driven model, the hybrid EEMD-LSTM model is compared with the Recurrent Neural Network (RNN), LSTM and Empirical Mode Decomposition (EMD) coupled with RNN, EMD-LSTM and EEMD-RNN models, and their comparison results demonstrate that the hybrid EEMD-LSTM model performs better than the other five models. The scatterplots of the predicted results of the six models versus the original daily LST data series show that the hybrid EEMD-LSTM model is superior to the other five models. It is concluded that the proposed hybrid EEMD-LSTM model in this study is a suitable tool for temperature forecasting.
关键词：
GB-RAR;static clutter;accuracy validation;SQP-GA;resonance frequencies;high-rise building
摘要：
Dynamic vibration characteristics monitoring of high-rise buildings is of great significance for evaluating their safety operation conditions, verifying structural design parameters and updating numerical models. A ground-based real-aperture radar (RAR) has been applied to a high-rise building in Wuhan, China. In the case of RAR measurements, in which several points in the same range bins can add unexpected multiplicity contributions due to spatial resolution varying with distance, the static clutter effect must be removed. However, only a few studies have analyzed it. In this paper, we introduced the least squares fitting circle method to eliminate the static clutter. On this basis, the accuracy of instrument deformation detection is verified by a precise stepping mobile platform in laboratory. Subsequently, we established a sequential quadratic programming-genetic algorithm (SQP-GA) to identify the dynamic vibration characteristics of buildings under natural environment excitation. The SQP-GA method not only accurately identifies the resonance frequencies, but also directly extracts the amplitudes of sine and cosine components of the building vibration signals under the resonance frequencies response compared with the traditional spectrum analysis based on fast Fourier transform.
