Waveform-based spaceborne GNSS-R wind speed observation: Demonstration and analysis using UK TechDemoSat-1 data

Wang, Feng; Yang, Dongkai; Zhang, Bo; Li, Weiqiang

doi:10.1016/j.asr.2018.01.013

Cited by 19 publications

(9 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANNs have been widely applied in global wind speed retrieval from scatterometer and syntheticaperture radar (SAR; Hornik, 1991;Stiles and Dunbar, 2010;Stiles et al, 2014). More recently, several studies have shown that ANNs can also improve the accuracy of GNSS-R wind speed retrieval using groundbased and spaceborne data (Kasantikul et al, 2018;Liu et al, 2019;Gao et al, 2019a;Asgarimehr et al, 2019), which have shown promising performance by using data collected by the TDS-1 (Wang et al, 2018;Asgarimehr et al, 2019) and CYGNSS missions (Liu et al, 2019;Reynolds et al, 2020). Moreover, this approach has been also attempted in some other GNSS-R applications, such as sea ice detection (Yan and Huang, 2018), soil moisture (Feng et al, 2018;Eroglu et al, 2019), hurricane tracking (Alshaye et al, 2020), and inland water detection (Ghasemigoudarzi et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network

Yang

et al. 2021

Remote Sensing of Environment

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network

Yang

et al. 2021

Remote Sensing of Environment

Self Cite

View full text Add to dashboard Cite

“…ANNs in combination with a particle filter and particle swarm optimization have been exploited for ocean wind speed estimations in coastal regions, using Beidou satellite data, and in the days surrounding Typhoon Utor [19], [20]. Other Machine Learning (ML) approaches have also been proposed for the retrieval of wind speed using GNSS-R data from both TechDemoSat-1 [21] and CYGNSS [22]. ANNs and convolutional neural networks have also been used for purposes other than the wind speed, such as Sea Ice Detection and Sea Ice Concentrations estimation using GNSS-R Delay Doppler Maps [23], [24].…”

Section: Introductionmentioning

confidence: 99%

Wind Speed Estimation From CYGNSS Using Artificial Neural Networks

Reynolds¹,

Clarizia²,

Santi

2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this article, a retrieval algorithm based on the use of an artificial neural network (ANN) is proposed for wind speed estimations from cyclone global navigation satellite system (CYGNSS). The delay/Doppler map average and the leading edge slope observables, derived from CYGNSS delay/Doppler maps, are used as inputs to the network, along with geographical, geometry, and hardware antenna information. The derivation of the optimal number of hidden layers and neurons is obtained using statistical metrics of agreement between the CYGNSS data and the wind matchups obtained from modelled winds output by the wavewatch 3 (WW3) model. A cumulative distribution function (CDF) matching step is applied to the network outputs, to impose that the CDF of the retrievals matches that of the matchups. The resulting wind speeds are unbiased with respect to WW3 modeled winds, and deliver a global root mean square (RMS) difference (RMSD) of 1.51 m/s, over a dynamic range of wind speeds up to 32 m/s. The obtained RMSD is the lowest among those seen in literature for wind speed retrievals from CYGNSS. A comparison is carried out between the winds retrieved from the ANN approach and those derived using the fully developed sea approach, which represent the CYGNSS baseline wind product. The comparison highlights that the ANN approach outperforms the baseline approach for both low and high wind speeds and removes most of the geographical biases between baseline winds and WW3 winds seen in monthly maps of wind speeds. The ANN approach could well be applied to the entire CYGNSS dataset to generate an enhanced wind speed product.

show abstract

“…The exploitation of this approach has been particularly accelerated with the availability of large and diverse datasets acquired from recent spaceborne GNSS-R observatories such as the United Kingdom's TechDemoSat-1 (TDS-1, launched in mid-2014 and retired in mid-2019) [12] and NASA's Cyclone Global Navigation Satellite System (CYGNSS, launched in late 2016) [13]. While TDS-1's GNSS-R measurements featured a relatively low revisit time due to the satellites intention for evaluating multiple payloads simultaneously, the dedicated research community surrounding TDS-1 has greatly improved the literature's understanding of spaceborne GNSS-R responses to ocean winds [14,15], ice sheets [16,17], and land geophysical parameter features [18][19][20] from space due to TDS-1's global coverage created by its polar orbiting configuration. On the other hand, CYGNSS features a high-temporal resolution over a smaller spatial extent in order to optimize its measurements for ocean studies.…”

Section: Introductionmentioning

confidence: 99%

Evaluations of Machine Learning-Based CYGNSS Soil Moisture Estimates against SMAP Observations

et al. 2020

View full text Add to dashboard Cite

This paper presents a machine learning (ML) framework to derive a quasi-global soil moisture (SM) product by direct use of the Cyclone Global Navigation Satellite System (CYGNSS)’s high spatio-temporal resolution observations over the tropics (within ±38 latitudes) at L-band. The learning model is trained by using in-situ SM data from the International Soil Moisture Network (ISMN) sites and various space-borne ancillary data. The approach produces daily SM retrievals that are gridded to 3 km and 9 km within the CYGNSS spatial coverage. The performance of the model is independently evaluated at various temporal scales (daily, 3-day, weekly, and monthly) against Soil Moisture Active Passive (SMAP) mission’s enhanced SM products at a resolution of 9 km × 9 km. The mean unbiased root-mean-square difference (ubRMSD) between concurrent (same calendar day) CYGNSS and SMAP SM retrievals for about three years (from 2017 to 2019) is 0.044 cm3 cm−3 with a correlation coefficient of 0.66 over SMAP recommended grids. The performance gradually improves with temporal averaging and degrades over regions regularly flagged by SMAP such as dense forest, high topography, and coastlines. Furthermore, CYGNSS and SMAP retrievals are evaluated against 170 ISMN in-situ observations that result in mean unbiased root-mean-square errors (ubRMSE) of 0.055 cm3 cm−3 and 0.054 cm3 cm−3, respectively, and a higher correlation coefficient with CYGNSS retrievals. It is important to note that the proposed approach is trained over limited in-situ observations and is independent of SMAP observations in its training. The retrieval performance indicates current applicability and future growth potential of GNSS-R-based, directly measured spaceborne SM products that can provide improved spatio-temporal resolution than currently available datasets.

show abstract

Waveform-based spaceborne GNSS-R wind speed observation: Demonstration and analysis using UK TechDemoSat-1 data

Cited by 19 publications

References 50 publications

Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network

Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network

Wind Speed Estimation From CYGNSS Using Artificial Neural Networks

Evaluations of Machine Learning-Based CYGNSS Soil Moisture Estimates against SMAP Observations

Contact Info

Product

Resources

About