Machine-learning based ocean atmospheric duct forecasting:
a hybrid model-data-driven approach

doi:10.19682/j.cnki.1005-8885.2023.2011

中国邮电高校学报(英文) ›› 2023, Vol. 30 ›› Issue (4): 1-9.doi: 10.19682/j.cnki.1005-8885.2023.2011

• Artificial Intelligence • 下一篇

Machine-learning based ocean atmospheric duct forecasting: a hybrid model-data-driven approach

Feng Yuting, Gong Haobing, Hao Xiaojing, Gao Hui, Guo Xiangming

1. Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing 100876, China 2. Key Laboratory of Radio Wave Propagation Characteristics and Modeling Technology, 22nd Research Institute of China Electronics Technology Corporation, Qingdao 266107, China

收稿日期:2021-08-11 修回日期:2023-03-23 接受日期:2023-08-31 出版日期:2023-08-31 发布日期:2023-08-31
通讯作者: Gao Hui, E-mail: huigao@bupt.edu.cn E-mail:huigao@bupt.edu.cn
基金资助:
This work was supported by the National Natural Science Foundation of China (62071071, 61790553, 61871057).

Machine-learning based ocean atmospheric duct forecasting: a hybrid model-data-driven approach

Feng Yuting, Gong Haobing, Hao Xiaojing, Gao Hui, Guo Xiangming

1. Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing 100876, China 2. Key Laboratory of Radio Wave Propagation Characteristics and Modeling Technology, 22nd Research Institute of China Electronics Technology Corporation, Qingdao 266107, China

Received:2021-08-11 Revised:2023-03-23 Accepted:2023-08-31 Online:2023-08-31 Published:2023-08-31
Contact: Gao Hui, E-mail: huigao@bupt.edu.cn E-mail:huigao@bupt.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (62071071, 61790553, 61871057).

摘要/Abstract

摘要： The atmospheric duct is a vital radio wave environment. Conventional methods of forecasting the atmospheric duct mainly include statistical analysis based on sounding observation data and mesoscale numerical model-based prediction. The former can provide accurate duct information but is highly dependent on the acquisition of data sets. The latter is more practical but still lacks accuracy. This paper introduces machine learning to establish a novel meteorological parameter correction model for atmospheric duct prediction. In detail, using the weather research and forecasting (WRF) model data and spatiotemporal characteristics as input, sounding data as label and extreme gradient boosting (XGBoost) model for training, the meteorological parameter correction effect is the best, i. e. , the accuracy of forecast meteorological parameters is improved by about 65.4%. Combining the mapping relationship between meteorological parameters and corrected atmospheric refractive index ( CARI ), and the transition mechanism of CARI to duct parameters, a new duct forecasting mechanism is proposed. Due to the high efficiency of numerical model and the accuracy of sounding data, the new duct forecasting mechanism has excellent performance. By comparing the duct forecasting results, the forecasting accuracy of the new duct forecasting model is significantly higher than that of the mesoscale model.

关键词: marine atmospheric duct, neural network fitting, machine learning, forecasting mechanism

Abstract: The atmospheric duct is a vital radio wave environment. Conventional methods of forecasting the atmospheric duct mainly include statistical analysis based on sounding observation data and mesoscale numerical model-based prediction. The former can provide accurate duct information but is highly dependent on the acquisition of data sets. The latter is more practical but still lacks accuracy. This paper introduces machine learning to establish a novel meteorological parameter correction model for atmospheric duct prediction. In detail, using the weather research and forecasting (WRF) model data and spatiotemporal characteristics as input, sounding data as label and extreme gradient boosting (XGBoost) model for training, the meteorological parameter correction effect is the best, i. e. , the accuracy of forecast meteorological parameters is improved by about 65.4%. Combining the mapping relationship between meteorological parameters and corrected atmospheric refractive index ( CARI ), and the transition mechanism of CARI to duct parameters, a new duct forecasting mechanism is proposed. Due to the high efficiency of numerical model and the accuracy of sounding data, the new duct forecasting mechanism has excellent performance. By comparing the duct forecasting results, the forecasting accuracy of the new duct forecasting model is significantly higher than that of the mesoscale model.

Key words: marine atmospheric duct, neural network fitting, machine learning, forecasting mechanism

Feng Yuting, Gong Haobing, Hao Xiaojing, Gao Hui, Guo Xiangming. Machine-learning based ocean atmospheric duct forecasting: a hybrid model-data-driven approach[J]. The Journal of China Universities of Posts and Telecommunications, 2023, 30(4): 1-9.

参考文献

References

[1] PATTERSON W L. Climatology of marine atmospheric refractive effects: A compendium of the integrated refractive effects forecast system (IREPS) historical summaries. San Diego, CA, USA: Naval Ocean Systems Center, 1982.

[2] CRAIG K H, HAYTON T G. Climatic mapping of refractivity parameters from radiosonde data. Advisory Group for Aerospace Research and Development, North Atlantic Treaty Organization (ed). AGARD Conference Proceedings. London, UK: Advisory Group for Aerospace Research and Development ( AGARD ), 1995: 43.1 - 43.14.

[3] KUCAS M E. Forecasting the nighttime evolution of radio wave ducting in complex terrain using the MM5 numerical weather model. Monterey, CA, USA: Naval Postgraduate School, 2003.

[4] ATKINSON B W, LI J G, PLANT R S. Numerical modeling of the propagation environment in the atmospheric boundary layer over the Persian Gulf. Journal of Applied Meteorology and Climatology, 2001, 40(3): 586 - 603.

[5] ZHAO W P, ZHAO J, LI J C, et al. An evaporation duct height prediction model based on a long short-term memory neural network. IEEE Transactions on Antennas and Propagation, 2021, 69(11): 7795 - 7804.

[6] SKAMAROCK W C, KLEMP J B, DUDHIA J, et al. A description of the advanced research WRF version 2. NCAR/TN 468+STR. Boulder, CO, USA: National Center for Atmospheric Research, 2005.

[7] HUNTER J D. Matplotlib: A 2D graphics environment. Computing in Science & Engineering, 2007, 9(3): 90 - 95.

[8] MASTYLO M. Bilinear interpolation theorems and applications. Journal of Functional Analysis, 2013, 265(2): 185 - 207.

[9] LI J, CHENG J H, SHI J Y, et al. Brief introduction of back propagation (BP) neural network algorithm and its improvement. Advances in Computer Science and Information Engineering: Proceedings of the 2nd International Conference on Computer Science and Information Engineering (CSIE'12): Vol 2, 2012, May 19 - 20, Zhengzhou, China. AINSC 169. Berlin, Germany, Springer, 2012: 553 - 558.

[10] FRIEDMAN J H. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 2001, 29(5): 1189 - 1232.

[11] CHEN T Q, GUESTRIN C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16), 2016, Aug 13 - 17, San Francisco, CA, USA. New York, NY, USA: ACM, 2016: 785 - 794.

[12] HAO X J, LI Q L, GUO L X, et al. Spatial and temporal features of atmospheric ducts over the North Pole. Chinese Journal of Polar Research, 2018, 30(4): 349 - 359 (in Chinese).

Machine-learning based ocean atmospheric duct forecasting: a hybrid model-data-driven approach

Machine-learning based ocean atmospheric duct forecasting: a hybrid model-data-driven approach

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价