隨著衛星科技的發展，近年來有越來越多關於利用衛星反射訊號與反射點所在地球表面性質的研究，包括海平面高度、地表植被含水量、冰層厚度、生物量以及海平面風場等等，皆為相關研究範疇。西元2003年，英國發射了可以接收GPS海面反射訊號的衛星進行海面風速反演研究，並在2014年再次發射TechDemoSat-1 (TDS-1)，搭載可以產出延遲都卜勒圖(Delay-Doppler Map，DDM)的接收機，以DDM作為研究地表特性的重要觀測量；隨後於西元2016年，美國發射了8顆同樣搭載Delay Doppler Map接收機的衛星，也就是Cyclone Global Navigation Satellite System (CyGNSS)計畫；而四面環海且飽受颱風侵擾的台灣，也預計在西元2023年發射自主研發的獵風者號衛星，搭載了GNSS-R資料處理系統並且產生DDM資料，預計能為台灣的氣象科學領域有著重大的貢獻，並且能夠預防颱風所帶來的嚴重災害。本論文將利用測風塔作為固定式衛星反射訊號接收器，接收海面反射訊號並同時量測不同高度的風速值，再利用深度學習的方式，進行海面風速反演。

With the advancement of satellite technology, there has been an increasing amount of research in recent years on utilizing satellite-reflected signals for remote sensing applications. These studies include research on sea level height, surface vegetation moisture content, ice thickness, biomass, sea surface wind fields, among others. In 2003, the United Kingdom launched the UK-Disaster Monitoring Constellation (UK-DMC), which could receive GPS sea surface reflected signals for studying sea surface wind speed inversion. In 2014, the TechDemoSat-1 (TDS-1) was launched, carrying a receiver capable of producing Delay-Doppler Maps (DDMs), which are important observational data for studying surface characteristics. In 2016, the United States launched the Cyclone Global Navigation Satellite System (CyGNSS) project, consisting of eight satellites equipped with Delay Doppler Map receivers. Taiwan, surrounded by the sea and frequently affected by typhoons, is planning to launch the self-developed Triton satellite in 2023. It will carry a GNSS-R data processing system and generate DDM data, which is expected to make significant contributions to the field of meteorological science in Taiwan and help mitigate the severe impacts of typhoon-related disasters. This thesis aims to install a fixed satellite reflected signal receiver at a wind tower, capturing sea surface reflected signals and simultaneously measuring wind speeds at different heights. Deep learning techniques are employed for the inversion of sea surface wind speeds.

[1]Martín-Neira, M. “A passive reflectometry and interferometry system (PARIS) application to ocean altimetry.” ESA J. 1993, 17, 331–355.
[2]Garrison, J.; Katzberg, S.; Hill, M. “Effect of sea roughness on bistatically scattered range coded signals from the Global Positioning System.” Geophys. Res. Lett. 1998, 25, 2257–2260.
[3]Gleason, S.; Hodgart, S.; Sun, Y.P.; Gommenginger, C.; Mackin, S.; Adjrad, M.; Unwin, M. “Detection and Processing of Bistatically Reflected GPS signals from low Earth orbit for the purpose of ocean remote sensing.” IEEE Transactions on Geoscience and Remote Sensing, vol. 43, no. 6, pp. 1229-1241, June 2005, doi: 10.1109/TGRS.2005.845643.
[4]Foti, G., Gommenginger, C., Jales, P., Unwin, M., Shaw, A., Robertson, C., and Roselló, J. (2015), “Spaceborne GNSS reflectometry for ocean winds: First results from the UK TechDemoSat-1 mission” Geophys. Res. Lett., 42, 5435– 5441, doi:10.1002/2015GL064204.
[5]Foti, G.; Gommenginger, C.; Unwin, M.; Jales, P.; Tye, J.; Roselló, J. “An Assessment of Non-Geophysical Effects in Spaceborne GNSS Reflectometry Data from the UK TechDemoSat-1 Mission.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 10, 3418–3429.
[6]Soisuvarn, S.; Jelenak, Z.; Said, F.; Chang, P.; Egido, A.“The GNSS Reflectometry Response to the Ocean Surface Winds and Waves.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016, 9, 4678–4699.
[7]Clarizia, M.P.; Ruf, C. “Wind Speed Retrieval Algorithm for the Cyclone Global Navigation Satellite System (CYGNSS) Mission.” IEEE Trans. Geosci. Remote Sens. 2016, 54, 4419–4432.
[8]Unwin, M.; Jales, P.; Blunt, P.; Duncan, S.; Brummitt, M.; Ruf, C. “The SGR-ReSI and its application for GNSS reflectometry on the NASA EV-2 CYGNSS mission.” in Proceedings of the 2013 IEEE Aerospace Conference, Big Sky, MT, USA, 2–9 March 2013; pp. 1–6.
[9]Komjathy, A.; Armatys, M.; Masters, D.; Axelrad, P.; Zavorotny, V.; Katzberg, S. “Retrieval of Ocean Surface Wind Speed and Wind Direction Using Reflected GPS Signals.” J. Atmos. Ocean Technol. 2004, 21, 515–526.
[10]Cardellach, E.; Fabra, F.; Nogués-Correig, O.; Oliveras, S.; Ribó, S.; Rius, A. “GNSS-R ground-based and airborne campaigns for ocean, land, ice, and snow techniques: Application to the GOLD-RTR data sets.” Radio Sci. 2011, 46, 1–16.
[11] Yan, Q.; Huang, W.; Jin, S.; Jia, Y. “Pan-tropical soil moisture mapping based on a three-layer model from CYGNSS GNSS-R data.” Remote Sens. Environ. 2020, 247, 111944.
[12]Stilla, D.; Zribi, M.; Pierdicca, N.; Baghdadi, N.; Huc, M. “Desert Roughness Retrieval Using CYGNSS GNSS-R Data.”Remote Sens. 2020, 12, 743.
[13]Carreno-Luengo, H.; Luzi, G.; Crosetto, M. “Above-Ground Biomass Retrieval over Tropical Forests: A Novel GNSS-R Approach with CyGNSS.” Remote Sens. 2020, 12, 1368.
[14]Clarizia, M.P.; Ruf, C.; Jales, P.; Gommenginger, C. “Spaceborne GNSS-R Minimum Variance Wind Speed Estimator.” IEEE Trans. Geosci. Remote Sens. 2014, 52, 6829–6843.
[15]Frate, F.; Pacifici, F.; Schiavon, G.; Solimini, C. “Use of Neural Networks for Automatic Classification from High-Resolution Images.” IEEE Trans. Geosci. Remote Sens. 2007, 45, 800–809
[16]Eroglu, O.; Kurum, M.; Boyd, D.; Gürbüz, A.C. “High Spatio-Temporal Resolution CYGNSS Soil Moisture Estimates Using Artificial Neural Networks.” Remote Sens. 2019, 11, 2272.
[17]Reynolds, J.; Clarizia, M.P.; Santi, E. “Wind Speed Estimation from CYGNSS Using Artificial Neural Networks.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 708–716.
[18] Asgarimehr, M.; Zhelavskaya, I.; Foti, G.; Reich, S.; Wickert, J. “A GNSS-R Geophysical Model Function: Machine Learning for Wind Speed Retrievals.” IEEE Geosci. Remote Sens. Lett. 2020, 17, 1333–1337.
[19] Chu, X.; He, J.; Song, H.; Qi, Y.; Sun, Y.; Bai, W.; Li, W.; Wu, Q. “Multimodal Deep Learning for Heterogeneous GNSS-R Data Fusion and Ocean Wind Speed Retrieval. IEEE J.” Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 5971–5981.
[20] Milad Asgarimehr, Caroline Arnold, Tobias Weigel, Chris Ruf, Jens Wickert, “GNSS reflectometry global ocean wind speed using deep learning: Development and assessment of CyGNSSnet,” Remote Sensing of Environment,Volume 269,2022.
[21] Kasantikul K, Yang D, Wang Q, Lwin A. “A Novel Wind Speed Estimation Based on the Integration of an Artificial Neural Network and a Particle Filter Using BeiDou GEO Reflectometry.” Sensors (Basel). 2018 Oct 8;18(10):3350. doi 10.3390/s18103350. PMID: 30297601; PMCID: PMC6210207.
[22] Rosetta Radio Science Investigations (RSI) - Scientific Figure on ResearchGate. Availablefrom:https://www.researchgate.net/figure/The-bistatic-radar-configuration-is-distinguished-from-the-monostatic-by-the-spatial_fig3_41625151 [accessed 10 Jun 2023]
[23] Gleason,Scott.“Remote Sensing of Ocean, Ice and Land Surfaces Using Bistatically Scanner GNSS Signals From Low Earth Orbit.” University of Surrey, 2006. Web.
[24]https://acikders.ankara.edu.tr/pluginfile.php/98722/mod_resource/content/1/week-6.pdf
[25] Katzberg Stephen J. and Jr James L. Garrison.”Utilizing GPS To Determine Ionospheric Delay Over the Ocean.” Technical Report. NASA Langley Technical Report Server.
[26] Egido, Alejandro. “GNSS Reflectometry for Land Remote Sensing Applications.” 10.13140/RG.2.1.2078.7049.Signal Theory and Communications Dpt. Universitat Polit`ecnica de Catalunya.
[27] Bu, J.; Yu, K.; Zhu, Y.; Qian, N.; Chang, J. “Developing and Testing Models for Sea Surface Wind Speed Estimation with GNSS-R Delay Doppler Maps and Delay Waveforms.” Remote Sens.2020,https://doi.org/10.3390/rs12223760
[28] Masters, D.. “Surface remote sensing applications of GNSS bistatic radar, soil moisture, and aircraft altimetry.” Ph.D. Thesis, University of Colorado.
[29] Yan, Q., Huang, W., and Moloney, C., "Neural Networks Based Sea Ice Detection and Concentration Retrieval From GNSS-R Delay-Doppler Maps," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 10, no. 8, pp. 3789-3798, Aug. 2017, doi: 10.1109/JSTARS.2017.2689009.
[30]Zavorotny, V. U. and Voronovich, A. G., "Scattering of GPS signals from the ocean with wind remote sensing application," IEEE Transactions on Geoscience and Remote Sensing, vol. 38, no. 2, pp. 951-964, March 2000, doi: 10.1109/36.841977.
[31]Camps, A. and Park, H., "Sensitivity of Delay Doppler Map in Spaceborne GNSS-R to Geophysical Variables of the Ocean,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 8624-8631, 2022, doi: 10.1109/JSTARS.2022.3211876.
[32] https://www.tasa.org.tw/inprogress.php?c=20012001&ln=zh_TW