GNSS-R Soil Moisture Retrieval Based on a XGboost Machine Learning Aided Method: Performance and Validation

Jia, Yan; Jin, Shuanggen; Savi, Patrizia; Gao, Yun; Tang, Jing; Chen, Yixiang; Li, Wenmei

doi:10.3390/rs11141655

Cited by 80 publications

(36 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advances on GNSS-R [19,21,34] have shown extraordinary capabilities to sense SMC [23][24][25][26][27][28][29][30][31][32] with high spatial and temporal coverage (Figure 12), low cost, and all-weather conditions, far to be achieved by using conventional active/passive microwave instruments onboard satellites (e.g., Figure 2b. In (b) is shown SMC from CYGNSS for the same day, for θ < 40 • and using SMAP VOD < 0.5 estimates from Figure 3 and SMAP BSR estimates from Figure 2a.…”

Section: Discussionmentioning

confidence: 99%

“…Recent advances on GNSS-R [19,21,34] have shown extraordinary capabilities to sense SMC [23][24][25][26][27][28][29][30][31][32] with high spatial and temporal coverage (Figure 12), low cost, and all-weather conditions, far to be achieved by using conventional active/passive microwave instruments onboard satellites (e.g., SMAP, SMOS). However, the research community has been facing difficulties to define a reliable benchmarking GNSS-R SMC retrieval method (e.g., [27,37,[41][42][43][44]) due to its inherent multidisciplinary character (GNSS technology, microwave remote sensing, measurement geometry and errors, spatial and temporal sampling, computation load, etc.).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Soil Moisture Content from GNSS Reflectometry Using Dielectric Permittivity from Fresnel Reflection Coefficients

2020

Self Cite

View full text Add to dashboard Cite

Global Navigation Satellite Systems-Reflectometry (GNSS-R) has shown unprecedented advantages to sense Soil Moisture Content (SMC) with high spatial and temporal coverage, low cost, and under all-weather conditions. However, implementing an appropriated physical basis to estimate SMC from GNSS-R is still a challenge, while previous solutions were only based on direct comparisons, statistical regressions, or time-series analyses between GNSS-R observables and external SMC products. In this paper, we attempt to retrieve SMC from GNSS-R by estimating the dielectric permittivity from Fresnel reflection coefficients. We employ Cyclone GNSS (CYGNSS) data and effectively account for the effects of bare soil roughness (BSR) and vegetation optical depth by employing ICESat-2 (Ice, Cloud, and land Elevation Satellites 2) and/or SMAP (Soil Moisture Active Passive) products. The tests carried out with ICESat-2 BSR data have shown the high sensitivity in SMC retrieval to high BSR values, due to the high sensitivity of ICESat-2 to land surface microrelief. Our GNSS-R SMC estimates are validated by SMAP SMC products and the results provide an R-square of 0.6, Root Mean Squared Error (RMSE) of 0.05, and a zero p-value, for the 4568 test points evaluated at the eastern region of China during April 2019. The achieved results demonstrate the optimal capability and potential of this new method for converting reflectivity measurements from GNSS-R into Land Surface SMC estimates.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Recent advances on GNSS-R [19,21,34] have shown extraordinary capabilities to sense SMC [23][24][25][26][27][28][29][30][31][32] with high spatial and temporal coverage (Figure 12), low cost, and all-weather conditions, far to be achieved by using conventional active/passive microwave instruments onboard satellites (e.g., SMAP, SMOS). However, the research community has been facing difficulties to define a reliable benchmarking GNSS-R SMC retrieval method (e.g., [27,37,[41][42][43][44]) due to its inherent multidisciplinary character (GNSS technology, microwave remote sensing, measurement geometry and errors, spatial and temporal sampling, computation load, etc.).…”

Section: Discussionmentioning

confidence: 99%

Soil Moisture Content from GNSS Reflectometry Using Dielectric Permittivity from Fresnel Reflection Coefficients

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…To avoid overfitting, the regularization term is added to help smooth the final learned weights. See Chen and Guestrin [ 55 ] and Jia et al [ 74 ] for details on algorithm derivation in XGB.…”

Section: Prediction System and Modelsmentioning

confidence: 99%

Real-Time Rainfall Forecasts Based on Radar Reflectivity during Typhoons: Case Study in Southeastern Taiwan

Wei

Hsu

2021

Sensors

View full text Add to dashboard Cite

This study developed a real-time rainfall forecasting system that can predict rainfall in a particular area a few hours before a typhoon’s arrival. The reflectivity of nine elevation angles obtained from the volume coverage pattern 21 Doppler radar scanning strategy and ground-weather data of a specific area were used for accurate rainfall prediction. During rainfall prediction and analysis, rainfall retrievals were first performed to select the optimal radar scanning elevation angle for rainfall prediction at the current time. Subsequently, forecasting models were established using a single reflectivity and all elevation angles (10 prediction submodels in total) to jointly predict real-time rainfall and determine the optimal predicted values. This study was conducted in southeastern Taiwan and included three onshore weather stations (Chenggong, Taitung, and Dawu) and one offshore weather station (Lanyu). Radar reflectivities were collected from Hualien weather surveillance radar. The data for a total of 14 typhoons that affected the study area in 2008–2017 were collected. The gated recurrent unit (GRU) neural network was used to establish the forecasting model, and extreme gradient boosting and multiple linear regression were used as the benchmarks. Typhoons Nepartak, Meranti, and Megi were selected for simulation. The results revealed that the input data set merged with weather-station data, and radar reflectivity at the optimal elevation angle yielded optimal results for short-term rainfall forecasting. Moreover, the GRU neural network can obtain accurate predictions 1, 3, and 6 h before typhoon occurrence.

show abstract

“…The problem is that the differences in estimator performance can lead to different results, and the I/F signal dataset used is too small, lacking sufficient persuasive power. Based on the different assumptions, several SM inversion methods have also been developed, such as spatial averaging, combine linear regression method, machine-learning method, and the global inversion accuracy of SM can reach about 0.05 cm 3 /cm 3 [21][22][23][24][25][26][27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Land GNSS-Reflected DDM Coherence on Soil Moisture Estimation from CYGNSS Data

Dong

Jin

2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

With the development of spaceborne global navigation satellite system-reflectometry (GNSS-R), it can be used for terrestrial applications as a promising remote sensing tool, such as soil moisture (SM) retrieval. The reflected L-band GNSS signal from the land surface can simultaneously generate coherent and incoherent scattering, depending on surface roughness. However, the contribution of the incoherent component was directly ignored in previous GNSS-R land soil moisture content retrieval due to the hypothesis of its relatively small proportion. In this paper, a detection method is proposed to distinguish the coherence of land GNSS-R delay-Doppler map (DDM) from the cyclone global navigation satellite system (CYGNSS) mission in terms of DDM power-spreading features, which are characterized by different classification estimators. The results show that the trailing edge slope of normalized integrated time-delay waveform presents a better performance to recognize coherent and incoherent dominated observations, indicating that 89.6% of CYGNSS land observations are dominated by the coherent component. Furthermore, the impact of the land GNSS-Reflected DDM coherence on soil moisture retrieval is evaluated from 19-month CYGNSS data. The experiment results show that the influence of incoherent component and incoherent observations is marginal for CYGNSS soil moisture retrieval, and the RMSE of GNSS-R derived soil moisture reaches 0.04 cm3/cm3.

show abstract

GNSS-R Soil Moisture Retrieval Based on a XGboost Machine Learning Aided Method: Performance and Validation

Cited by 80 publications

References 59 publications

Soil Moisture Content from GNSS Reflectometry Using Dielectric Permittivity from Fresnel Reflection Coefficients

Soil Moisture Content from GNSS Reflectometry Using Dielectric Permittivity from Fresnel Reflection Coefficients

Real-Time Rainfall Forecasts Based on Radar Reflectivity during Typhoons: Case Study in Southeastern Taiwan

Evaluation of the Land GNSS-Reflected DDM Coherence on Soil Moisture Estimation from CYGNSS Data

Contact Info

Product

Resources

About