Machine Learning Classification of Rainfall Types Based on the Differential Attenuation of Multiple Frequency Microwave Links

Pu, Kang; Liu, Xichuan; Xian, Minghao; Gao, Taichang

doi:10.1109/tgrs.2020.2977393

Cited by 18 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The values of antenna gain in the eight directions are −10 dB and −20 dB, respectively. Based on Equation (9), the sky noise temperature is obtained by: (19) where T i is the sky noise temperature in each sample direction which is calculated by Equation (8).…”

Section: Simulation Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction and Nowcasting of Rainfall Field by Oblique Earth-Space Links Network: Preliminary Results from Numerical Simulation

et al. 2020

Self Cite

View full text Add to dashboard Cite

High-precision rainfall field reconstruction and nowcasting play an important role in many aspects of social life. In recent years, the rain-induced signal attenuation of oblique earth-space links (OELs) has been presented to monitor regional rainfall. In this paper, we set up the first OEL in Nanjing, China, for the estimation of rain intensity. A year of observations from this link are also compared with the measurements from laser disdrometer OTT-Parsivel (OTT), between which the correlation is 0.86 and the determination coefficient is 0.73. Then, the simulation experiment is carried out: an OELs network is built, and the Kriging interpolation algorithm is employed to perform rainfall field reconstruction. The rainfall fields of plum rain season from 2016 to 2019 have been reconstructed by this network, which shows a good agreement with satellite remote sensing data. The resulting root-mean-square errors are lower than 3.46 mm/h and spatial correlations are higher than 0.80. Finally, we have achieved the nowcasting of rainfall field based on a machine-learning approach, especially deep learning. It can be seen from experiment results that the motion of rain cell and the position of peak rain intensity are predicted successfully, which is of great significant for taking concerted actions in case of emergency. Our experiment demonstrates that the densely distributed OELs are expected to become a futuristic rainfall monitoring system complementing existing weather radar and rain gauge observation networks.

show abstract

Section: Simulation Experimentsmentioning

confidence: 99%

“…Moreover, some studies have indicated that the links of commercial 5G networks can also be used to reconstruct a rainfall field [18]. In other applications, the HMLs have been employed to the classification of rainfall type, radar calibration and raindrop size distribution retrieval [19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Reconstruction and Nowcasting of Rainfall Field by Oblique Earth-Space Links Network: Preliminary Results from Numerical Simulation

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…where f(y/x i ), f (x), and f (y) represent the probability distribution functions of predicted output, input, and target y, respectively, whereas f(x i /y) depicts the conditional probability distribution function of input x i . Assuming the input x i follow Gaussian distribution, the probability density function is given by equation ( 11) [36]:…”

Section: A Basics Of Annmentioning

confidence: 99%

The Effects of Rain on Terrestrial Links at K, Ka and E-Bands in South Korea: Based on Supervised Learning

2021

View full text Add to dashboard Cite

At the rise of the fourth industrial revolution, artificial intelligence (AI), along with key enabling technologies such as millimeter waves (mm-waves) can be used to launch the fifth-generation (5G) and beyond communication links. However, the quality of radio links at higher frequency bands is limited by atmospheric elements. Among others, rainfall is the major propagation impairment at millimetric wave bands, which needs to be considered during the link budget planning. In this study, we investigated the rain attenuation results obtained from experimental data, existing models, and proposed supervised artificial neural network (SANN) at K, Ka, and E-bands, respectively, for terrestrial links in South Korea. The measurement campaigns were between Incheon, National Radio Research Agency (RRA) tower station, to the EMS Dongyoksang tower station operating at 75 GHz over a 100-m path length, and between Incheon, RRA tower station to Khumdang, Korea Telecom (KT) tower station, operating at 18 and 38 GHz over a 3.2km path length. The three-year rainfall and received signal level data measurements over these paths were used to determine rain attenuation distributions at different percentages of exceedance time distribution. Additionally, three existing attenuation models, ITU-R 530.17, Lin, and Revised Silva Mello (RSM) models were compared with measured rain attenuation. Our results indicate that these models did not correspond with measured results. Therefore, in this research, we proposed a supervised learning-based attenuation prediction method, which provides better performance than existing models. Furthermore, we validated our proposed model with measured received-signal level and rainfall data at the above-mentioned operating frequencies.INDEX TERMS Artificial neural network, millimeter wave, rain attenuation, South Korea, terrestrial links I. INTRODUCTION

show abstract

“…A air and A vapor were calculated based on the ITU-R P.676-10 recommendation (taking into account data from winter and the general conditions in the Nanjing area, a temperature of 0 • C and an absolute humidity of 5.0 g m −3 were adopted). Suppose that A noise = a × Gauss (Gauss represents the normal Gaussian distribution, and a stands for the noise coefficient) and a = 0.1 dB are set first (different noise levels are discussed later in Section 4) [45]. According to the observed HSDs corresponding to the different types of hydrometeors, the total attenuation value of each type of hydrometeor measured by the receiver can be obtained through Equation (13) (assuming that the level resolution of the receiver is 0.1 dB and the time resolution is 1 min).…”

Section: Microwave Link Simulationmentioning

confidence: 99%

Hydrometeor Identification Using Multiple-Frequency Microwave Links: A Numerical Simulation

Liu

Zhou

et al. 2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

A method for identifying hydrometeor types (rain, graupel, and wet snow) based on a microwave link is proposed in this paper. The measured hydrometeor size distribution (HSD) data from the winters of 2014 to 2019 in Nanjing, China, were used to carry out simulation experiments to verify the performance of the model. Single-, dual-, and tri-frequency models (combinations of 15 GHz, 18 GHz, 25 GHz, 38 GHz, 50 GHz, 60 GHz, 70 GHz, and 80 GHz) were established with the extreme learning machine (ELM) algorithm. The results showed that the performance of the tri-frequency models was overall better than that of the dual-frequency models, for which the performance was better than that of the single-frequency models. The mean (maximum) test set accuracies of the single-frequency, dual-frequency, and tri-frequency models reached 75.8%, 80.7%, and 83.2% (83.0%, 84.4%, and 85.6%), respectively. For the dual-frequency and tri-frequency models, it was found that the accuracy increased with the overall frequency or the frequency difference. In addition, the influences of different noise levels on the model performance were also analyzed. Finally, the effects of position and length of link relative to precipitation cell were analyzed and are also discussed.

show abstract

Machine Learning Classification of Rainfall Types Based on the Differential Attenuation of Multiple Frequency Microwave Links

Cited by 18 publications

References 47 publications

Reconstruction and Nowcasting of Rainfall Field by Oblique Earth-Space Links Network: Preliminary Results from Numerical Simulation

Reconstruction and Nowcasting of Rainfall Field by Oblique Earth-Space Links Network: Preliminary Results from Numerical Simulation

The Effects of Rain on Terrestrial Links at K, Ka and E-Bands in South Korea: Based on Supervised Learning

Hydrometeor Identification Using Multiple-Frequency Microwave Links: A Numerical Simulation

Contact Info

Product

Resources

About