Spatial Downscaling Based on Spectrum Analysis for Soil Freeze/Thaw Status Retrieved From Passive Microwave

Gao, Huiran; Zhang, Z. J.; Zhang, W. C.; Chen, Hao; Mingjie, XI

doi:10.1109/tgrs.2021.3051683

Cited by 4 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the meteorological factors provided by the ERA5-land dataset originally had a spatial resolution of 0.1 • , and we downscaled it to 0.01 • by bilinear interpolation. However, extreme meteorological conditions and advection are prevalent in Heihe River Basin, which may have resulted in the ERA5-land data with 0.1 • resolution failing to accurately reflect the actual meteorological conditions due to smoothing effects during the downscaling [57]. Similarly, the GLASS LAI dataset suffers from a comparable problem.…”

Section: Importance Of Input Parametersmentioning

confidence: 99%

A Comparison of Different Machine Learning Methods to Reconstruct Daily Evapotranspiration Time Series Estimated by Thermal–Infrared Remote Sensing

Zhao,

Song,

Zhao

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Remote sensing-based models usually have difficulty in generating spatio-temporally continuous terrestrial evapotranspiration (ET) due to cloud cover and model failures. To overcome this problem, machine learning methods have been widely used to reconstruct ET. Therefore, studies comparing and evaluating the accuracy and effectiveness of reconstruction among different machine learning methods at the basin scale are necessary. In this study, four popular machine learning methods, including deep forest (DF), deep neural network (DNN), random forest (RF) and extreme gradient boosting (XGB), were used to reconstruct the ET product, addressing gaps resulting from cloud cover and model failure. The ET reconstructed by the four methods was evaluated and compared for Heihe River Basin. The results showed that the four methods performed well for Heihe River Basin, but the RF method was particularly robust. It not only performed well compared with ground measurements (R = 0.73) but also demonstrated the ability to fully reconstruct gaps generated by the TSEB model across the entire basin. Validation based on ground measurements showed that the DNN and XGB models performed well (R > 0.70). However, some gaps still existed in the desert after reconstruction using the DNN and XGB models, especially for the XGB model. The DF model filled these gaps throughout the basin, but this model had lower consistency compared with ground measurements (R = 0.66) and yielded many low values. The results of this study suggest that machine learning methods have considerable potential in the reconstruction of ET at the basin scale.

show abstract

Section: Importance Of Input Parametersmentioning

confidence: 99%

A Comparison of Different Machine Learning Methods to Reconstruct Daily Evapotranspiration Time Series Estimated by Thermal–Infrared Remote Sensing

Zhao,

Song,

Zhao

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…For instance, the meteorological factors provided by ERA5-land dataset originally had a spatial resolution of 0.1°, and we downscale it to 0.01° by bilinear interpolation. However, extreme meteorological conditions and advection are prevalent in the Heihe River Basin, which may result in the ERA5-land data with 0.1° resolution failing to accurately reflect the actual meteorological conditions due to smoothing effects during the downscale [54]. Similarly, the GLASS LAI dataset suffers from comparable problem.…”

Section: Importance Of Input Parametersmentioning

confidence: 99%

Comparison of Different Machine Learning Methods to Reconstruct Daily Evapotranspiration Estimated by Thermal-Infrared Remote Sensing

Zhao,

Song,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

Remote sensing-based models usually have difficulty in generating spatio-temporally continuous terrestrial evapotranspiration (ET) due to cloud cover and model failures. To overcome this problem, machine learning methods have been widely used to reconstruct ET. However, studies comparing and evaluating the accuracy and effectiveness of reconstruction among different machine learning methods remain scarce. In this study, four popular machine learning methods (deep forest, deep neural network, random forest, extreme gradient boosting) were used to reconstruct the ET product, addressing gaps resulting from cloud cover and model failure. The ET reconstructed by four methods were evaluated and compared in Heihe River Basin. The results showed that four methods performed well in the Heihe River Basin, but the RF method was particularly robust. It not only performed well compared with ground measurement (R = 0.73), but also reconstructed ET throughout the basin. Validation based on ground measurement showed that DNN and XGB models performed well (R > 0.70). However, few gaps still existed in the desert after reconstruction, especially for the XGB model. The DF model filled these gaps throughout the basin, but the model had lower consistency compared with ground measurement (R = 0.66) and yielded many low values. The results of this study suggested that machine learning methods had considerable potential in reconstruction of ET at regional scale.

show abstract

“…An accurate F-T state is one of the primary goals of remote sensing applications on the QTP [33,34]. Microwave radiometers have proven the ability to detect near-surface (about 0-20 cm) ground F-T state [35][36][37][38][39][40] and been applied successfully on the QTP [41][42][43][44][45]. However, due to its coarse spatial resolution (~25 km), its application in fine-scale research is limited.…”

Section: Introductionmentioning

confidence: 99%

Characteristics of Freeze–Thaw Cycles in an Endorheic Basin on the Qinghai-Tibet Plateau Based on SBAS-InSAR Technology

et al. 2022

View full text Add to dashboard Cite

The freeze–thaw (F-T) cycle of the active layer (AL) causes the “frost heave and thaw settlement” deformation of the terrain surface. Accurately identifying its amplitude and time characteristics is important for climate, hydrology, and ecology research in permafrost regions. We used Sentinel-1 SAR data and small baseline subset-interferometric synthetic aperture radar (SBAS-InSAR) technology to obtain the characteristics of F-T cycles in the Zonag Lake-Yanhu Lake permafrost-affected endorheic basin on the Qinghai-Tibet Plateau from 2017 to 2019. The results show that the seasonal deformation amplitude (SDA) in the study area mainly ranges from 0 to 60 mm, with an average value of 19 mm. The date of maximum frost heave (MFH) occurred between November 27th and March 21st of the following year, averaged in date of the year (DOY) 37. The maximum thaw settlement (MTS) occurred between July 25th and September 21st, averaged in DOY 225. The thawing duration is the thawing process lasting about 193 days. The spatial distribution differences in SDA, the date of MFH, and the date of MTS are relatively significant, but there is no apparent spatial difference in thawing duration. Although the SDA in the study area is mainly affected by the thermal state of permafrost, it still has the most apparent relationship with vegetation cover, the soil water content in AL, and active layer thickness. SDA has an apparent negative and positive correlation with the date of MFH and the date of MTS. In addition, due to the influence of soil texture and seasonal rivers, the seasonal deformation characteristics of the alluvial-diluvial area are different from those of the surrounding areas. This study provides a method for analyzing the F-T cycle of the AL using multi-temporal InSAR technology.

show abstract

Spatial Downscaling Based on Spectrum Analysis for Soil Freeze/Thaw Status Retrieved From Passive Microwave

Cited by 4 publications

References 35 publications

A Comparison of Different Machine Learning Methods to Reconstruct Daily Evapotranspiration Time Series Estimated by Thermal–Infrared Remote Sensing

A Comparison of Different Machine Learning Methods to Reconstruct Daily Evapotranspiration Time Series Estimated by Thermal–Infrared Remote Sensing

Comparison of Different Machine Learning Methods to Reconstruct Daily Evapotranspiration Estimated by Thermal-Infrared Remote Sensing

Characteristics of Freeze–Thaw Cycles in an Endorheic Basin on the Qinghai-Tibet Plateau Based on SBAS-InSAR Technology

Contact Info

Product

Resources

About