Machine learning-based methods for sea surface rainfall detection from CYGNSS delay-doppler maps

Bu, Jinwei; Yu, Kegen; Ni, Jun; Yan, Qingyun; Han, Songtao; Wang, Jin; Wang, Changyang

doi:10.1007/s10291-022-01320-5

Cited by 11 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of structural strength test technology and science, modal parameter identification methods have been developed rapidly in recent years, and effective identification methods have emerged, mainly time domain method and frequency domain method, to perform equivalent instability and stability. Input and structural responses, non-white and nonlinear noise, and computational speed improvements [13][14]. Among them, the frequency domain method also uses FFT, but there are many improvements; the classification of time domain methods is shown in Figure 1, and each method has its practical application limitations.…”

Section: Classification Of Modal Parameter Identification Methods In ...mentioning

confidence: 99%

Identification of Structural Parameters of Offshore Platforms Based on Reality and Virtual Technology

2022

FOE

View full text Add to dashboard Cite

Offshore platforms have complex structures, high construction costs and harsh operating environments. To prevent serious and fatal accidents, regular/irregular inspections and safety assessments of outdoor platform systems are required during work. Especially for external platforms in the middle and late stages of operation and platforms that are not running, it is more important to perform effective health detection. The purpose of this paper is to study the identification of structural parameters of offshore platforms based on the reality and virtual technology. This paper summarizes the feedback-based linear structure parameter identification methods at home and abroad in recent years, and makes a comprehensive analysis of its application origin, research importance, research status at home and abroad, existing research methods and existing problems. This paper points out that the main problem in the application of output response-based modal parameter identification technology in the field of water engineering is to eliminate the noise and null conditions of measurement signals and signal keys. Denoising and removing spurious noise is a logical model command. Experiments have shown that the recognition results are very close to the real values, and the recognition accuracy will decrease in the presence of noisy signals, and the use of virtual reality technology can improve the accuracy by about 10%.

show abstract

Section: Classification Of Modal Parameter Identification Methods In ...mentioning

confidence: 99%

Identification of Structural Parameters of Offshore Platforms Based on Reality and Virtual Technology

2022

FOE

View full text Add to dashboard Cite

show abstract

“…The purpose of rainfall detection is to distinguish the data with and without rain. The CNN model proposed by Bu et al [30] is used for rainfall detection. When the rain data are obtained, they are used to retrieve the rainfall intensity.…”

Section: A Bibasic Electromagnetic Scattering Model Disturbed By Wind...mentioning

confidence: 99%

“…The F1 value balances the accuracy rate and the recall rate and is commonly used as the only measure of the overall effectiveness of a test. The calculation formulas for accuracy, recall, and F1 value can be found in [30].…”

Section: Performance Analysis Of Sea Surface Rainfall Detection Befor...mentioning

confidence: 99%

Joint Retrieval of Sea Surface Rainfall Intensity, Wind Speed, and Wave Height Based on Spaceborne GNSS-R: A Case Study of the Oceans near China

Zhu

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

In this paper, a method for joint sea surface rainfall intensity (RI), wind speed, and wave height retrieval based on spaceborne global navigation satellite system reflectometry (GNSS-R) data is proposed, which especially considers the effects between these two parameters. A method of rainfall detection (RD) according to different wind speed ranges is also proposed by mitigating the impact of swell and wind speed. The results, with data collected over the oceans near Southeast Asia, show that the RD method has a detection accuracy of up to 81.74%. The RI retrieval accuracy can reach about 2 mm/h by simultaneously correcting the effects of wind speed and swell. The accuracy of wind speed retrieval is improved by about 5% after removing rainfall interference through RD in advance. After considering the influence of wind speed and eliminating rainfall interference, the retrieval accuracy of significant wave height (SWH) is improved by about 18%. Finally, the deep convolutional neural network (DCNN) model is built to estimate the SWH of the swell. The results show that the retrieval accuracy of the swell height is better than 0.20 m after excluding rainfall interference. The proposed joint retrieval method provides an important reference for the future acquisition of multiple high-precision marine geophysical parameters by spaceborne GNSS-R technology.

show abstract

“…In addition, the satellite mission is also committed to GNSS radio occultation (GNSS-RO)related applications. It is worth mentioning that although the main objective of the above spaceborne GNSS-R tasks is to monitor ocean wind speed, these satellite tasks can also be used for sea surface height retrieval [8,9], sea ice detection [10,11], sea ice concentration (SIC) retrieval [12,13], sea ice thickness retrieval [14], tsunami detection [15], storm surge monitoring [16,17], wave height retrieval [18][19][20][21][22][23][24], rainfall detection [25,26], rainfall intensity retrieval [27,28], soil moisture retrieval [29] and biomass retrieval [30], etc.…”

Section: Introductionmentioning

confidence: 99%

GloWS-Net: A Deep Learning Framework for Retrieving Global Sea Surface Wind Speed Using Spaceborne GNSS-R Data

Zuo

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Spaceborne Global Navigation Satellite System Reflectometry (GNSS-R) is a new remote sensing technology that uses GNSS signals reflected from the Earth’s surface to estimate geophysical parameters. Because of its unique advantages such as high temporal and spatial resolutions, low observation cost, wide coverage and all-weather operation, it has been widely used in land and ocean remote sensing fields. Ocean wind monitoring is the main objective of the recently launched Cyclone GNSS (CYGNSS). In previous studies, wind speed was usually retrieved using features extracted from delay-Doppler maps (DDMs) and empirical geophysical model functions (GMFs). However, it is a challenge to employ the GMF method if using multiple sea state parameters as model input. Therefore, in this article, we propose an improved deep learning network framework to retrieve global sea surface wind speed using spaceborne GNSS-R data, named GloWS-Net. GloWS-Net considers the fusion of auxiliary information including ocean swell significant wave height (SWH), sea surface rainfall and wave direction to build an end-to-end wind speed retrieval model. In order to verify the improvement of the proposed model, ERA5 and Cross-Calibrated Multi-Platform (CCMP) wind data were used as reference for extensive testing to evaluate the wind speed retrieval performance of the GloWS-Net model and previous models (i.e., GMF, fully connected network (FCN) and convolutional neural network (CNN)). The results show that, when using ERA5 winds as ground truth, the root mean square error (RMSE) of the proposed GloWS-Net model is 23.98% better than that of the MVE method. Although the GloWS-Net model and the FCN model have similar RMSE (1.92 m/s), the mean absolute percentage error (MAPE) of the former is improved by 16.56%; when using CCMP winds as ground truth, the RMSE of the proposed GloWS-Net model is 2.16 m/s, which is 20.27% better than the MVE method. Compared with the FCN model, the MAPE is improved by 17.75%. Meanwhile, the GloWS-Net outperforms the FCN, traditional CNN, modified CNN (MCNN) and CyGNSSnet models in global wind speed retrieval especially at high wind speeds.

show abstract

Machine learning-based methods for sea surface rainfall detection from CYGNSS delay-doppler maps

Cited by 11 publications

References 36 publications

Identification of Structural Parameters of Offshore Platforms Based on Reality and Virtual Technology

Identification of Structural Parameters of Offshore Platforms Based on Reality and Virtual Technology

Joint Retrieval of Sea Surface Rainfall Intensity, Wind Speed, and Wave Height Based on Spaceborne GNSS-R: A Case Study of the Oceans near China

GloWS-Net: A Deep Learning Framework for Retrieving Global Sea Surface Wind Speed Using Spaceborne GNSS-R Data

Contact Info

Product

Resources

About