elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Coherent Doppler wind lidar with real-time wind processing and low signal-to-noise ratio reconstruction based on a convolutional neural network

Kliebisch, Oliver and Uittenbosch, Hugo and Thurn, Johann and Mahnke, Peter (2022) Coherent Doppler wind lidar with real-time wind processing and low signal-to-noise ratio reconstruction based on a convolutional neural network. Optics Express, 30 (4), pp. 5540-5552. Optical Society of America. doi: 10.1364/OE.445287. ISSN 1094-4087.

[img] PDF - Published version
10MB

Official URL: https://opg.optica.org/oe/fulltext.cfm?uri=oe-30-4-5540&id=469231

Abstract

Multi-classification using a convolutional neural network (CNN) is proposed as a denoising method for coherent Doppler wind lidar (CDWL) data. The method is intended to enhance the usable range of a CDWL beyond the atmospheric boundary layer (ABL). The method is implemented and tested in an all-fiber pulsed CWDL system operating at 1550 nm wavelength with 20 kHz repetition rate, 300 ns pulse length and 180 µJ of laser energy. A real-time pre-processing using a field programmable gate array (FPGA) is implemented producing averaged lidar spectrograms. Real-world measurement data is labeled using conventional frequency estimators and mixed with simulated spectrograms for training of the CNN. First results of this methods show that the CNN outperforms conventional frequency estimations substantially in terms of maximum range and delivers reasonable output in very low signal-to-noise (SNR) situations while still delivering accurate results in the high-SNR regime. Comparing the CNN output with radiosonde data shows the feasibility of the proposed method.

Item URL in elib:https://elib.dlr.de/146908/
Document Type:Article
Title:Coherent Doppler wind lidar with real-time wind processing and low signal-to-noise ratio reconstruction based on a convolutional neural network
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Kliebisch, OliverUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Uittenbosch, HugoUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Thurn, JohannUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Mahnke, PeterUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:2022
Journal or Publication Title:Optics Express
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:30
DOI:10.1364/OE.445287
Page Range:pp. 5540-5552
Publisher:Optical Society of America
ISSN:1094-4087
Status:Published
Keywords:Wind-Lidar,Lidar,Laser,FPGA,Fasern,Lichtwellenleiter,Neuronale Netzwerke,Machine Learning,CNN,Convolutional Neural Networks
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:Components and Systems
DLR - Research area:Aeronautics
DLR - Program:L CS - Components and Systems
DLR - Research theme (Project):L - Aircraft Systems
Location: Stuttgart
Institutes and Institutions:Institute of Technical Physics > Solid State Lasers and Nonlinear Optics
Deposited By: Kliebisch, Oliver
Deposited On:09 Feb 2022 13:45
Last Modified:29 Nov 2022 09:24

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.