Presentation 2017-11-23
A Neural Network Augmented Parametric Estimation Method for Accurate Wind Vector Reconstruction Using Single Doppler LIDAR
Taro Matsuo, Guanghao Sun, Tetsuo Kirimoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Doppler light detection and ranging (LIDAR) systems measure the wind velocity along the line-of-sight direction by processing the frequency shift of received signals. These systems are useful tool for real-time wind monitoring during aircraft taking off and landing. A wind vector reconstruction method for a single LIDAR is essential for wind field visualization. The conventional velocity volume processing (VVP) and velocity azimuth display (VAD) methods have been developed for a single LIDAR model, which suffer from inaccuracy in the case of local air turbulence. To address with such problem, the neural network augmented parametric estimation method using typical turbulence models such as tornado and microburst, have been proposed in our research. Aiming at more accurate for vector reconstruction, this paper introduces the adaptively size optimization of analysis area into parametric approach. The proposed method enhances the accuracy for wind vector reconstruction in the turbulence case from a numerical simulation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Single LIDARLocal air turbulenceNeural NetworkParametric estimation
Paper # SANE2017-68
Date of Issue 2017-11-16 (SANE)

Conference Information
Committee SANE
Conference Date 2017/11/23(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Malaysia (Borneo Island)
Topics (in Japanese) (See Japanese page)
Topics (in English) ICSANE2017
Chair Sonosuke Fukushima(ENRI)
Vice Chair Toshifumi Moriyama(Nagasaki Univ.) / Akitsugu Nadai(NICT)
Secretary Toshifumi Moriyama(Mitsubishi Electric) / Akitsugu Nadai(ENRI)
Assistant Manabu Akita(Univ. of Electro-Comm.) / Ryo Natsuaki(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Space, Aeronautical and Navigational Electronics
Language ENG-JTITLE
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Neural Network Augmented Parametric Estimation Method for Accurate Wind Vector Reconstruction Using Single Doppler LIDAR
Sub Title (in English)
Keyword(1) Single LIDARLocal air turbulenceNeural NetworkParametric estimation
1st Author's Name Taro Matsuo
1st Author's Affiliation The University of Electro-Communications(UEC)
2nd Author's Name Guanghao Sun
2nd Author's Affiliation The University of Electro-Communications(UEC)
3rd Author's Name Tetsuo Kirimoto
3rd Author's Affiliation The University of Electro-Communications(UEC)
Date 2017-11-23
Paper # SANE2017-68
Volume (vol) vol.117
Number (no) SANE-321
Page pp.pp.27-31(SANE),
#Pages 5
Date of Issue 2017-11-16 (SANE)