Remote sensing algorithms for estimation of fractional vegetation cover using pure vegetation index values: A review

Gao, Lin; Wang, Xiaofei; Johnson, Brian Alan; Tian, Qingjiu; Wang, Yu; Verrelst, Jochem; Mu, Xihan; Gu, Xingfa

doi:10.1016/j.isprsjprs.2019.11.018

Cited by 261 publications

(129 citation statements)

References 130 publications

Supporting

Mentioning

121

Contrasting

Unclassified

Order By: Relevance

“…0 ≤ FVC < 0.30 and 0.30 ≤ FVC < 0.45 were considered as the non-vegetation and the low vegetation-covered areas, respectively. 0.45 ≤FVC < 0.60 and FVC ≥ 0.60 were regarded as the medium vegetation and the high vegetation-covered areas, respectively [102]. Fig.…”

Section: F Selection Of Machine Learning Regression Featuresmentioning

confidence: 99%

Combined Sentinel-1A With Sentinel-2A to Estimate Soil Moisture in Farmland

Liu

Qian

Yue

2021

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

View full text Add to dashboard Cite

Section: F Selection Of Machine Learning Regression Featuresmentioning

confidence: 99%

Combined Sentinel-1A With Sentinel-2A to Estimate Soil Moisture in Farmland

Liu

Qian

Yue

2021

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

View full text Add to dashboard Cite

“…The vegetation index method is a common tool for remote sensing to monitor the growth and distribution of vegetation (Mu et al 2018;Osgouei et al 2019). This index is widely used to qualitatively and quantitatively evaluate vegetation coverage (Osgouei and Kaya 2017;Gao et al 2020). At present, the most common vegetation index is the NDVI, and the formula is shown below:…”

Section: Ndvi and Lst Calculationsmentioning

confidence: 99%

Quantification of urban greenery using hemisphere-view panoramas with a green cover index

Zhang

Xiao

et al. 2021

Ecosyst Health Sustain

View full text Add to dashboard Cite

show abstract

“…Usually, the empirical method estimates FVC values by calculating the regression relationship between FVC and reflectance of specific bands or vegetation indices, which presents satisfactory performance at small region for specific vegetation types [30]. However, the established empirical models have great uncertainties when they are applied at a large region, because the relationship is changed with various vegetation types and land conditions [31]. For pixel unmixing models, a basic assumption is that each pixel is composed of several components, referred to as endmembers, and the proportion of green vegetation components is considered as the corresponding FVC value [32].…”

Section: Introductionmentioning

confidence: 99%

“…For pixel unmixing models, a basic assumption is that each pixel is composed of several components, referred to as endmembers, and the proportion of green vegetation components is considered as the corresponding FVC value [32]. With clear physical assumptions, pixel unmixing models are easy to understand and widely used for FVC estimation [31,33]. However, due to the complex land surface conditions and complex spectral characteristics of various land objects over large region, it is difficult to determine the representative endmembers [34].…”

Section: Introductionmentioning

confidence: 99%

Fractional Vegetation Cover Estimation Algorithm Based on Recurrent Neural Network for MODIS 250 m Reflectance Data

Liu

Jia

Xia

et al. 2021

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

View full text Add to dashboard Cite

Fractional Vegetation Cover (FVC) is a critical land surface parameter, and several large-scale FVC products have been generated based on remote sensing data. Among these existing products, the Global Land Surface Satellite (GLASS) FVC product, derived from Moderate Resolution Imaging Spectroradiometer (MODIS) 500 m reflectance data (MOD09A1), has achieved complete spatial-temporal continuity and satisfying accuracy. To further improve the spatial resolution of GLASS FVC product, this study developed a novel FVC estimation algorithm for MODIS 250 m reflectance data based on a Recurrent Neural Network with the Long Short-Term Memory unit (RNN-LSTM). The RNN-LSTM was established using sequence training samples derived from the MODIS 250 m reflectance and GLASS FVC products, which were conducted over three vegetation types in mid-west China. Additionally, two machine learning methods, including the Back Propagation Neural Network (BPNN) and Multivariate Adaptive Regression Splines (MARS), were used to compare with the proposed method. The evaluation results showed that RNN-LSTM derived FVC had reliable spatialtemporal continuity and good consistency with the GLASS FVC product. Furthermore, the smooth temporal profiles of the RNN-LSTM FVC estimation indicated that the proposed method was capable of capturing the temporal characteristics of vegetation growth and reducing the uncertainties from the atmosphere and radiation. Finally, an independent validation case in the Heihe area indicated that the RNN-LSTM algorithm achieved the best accuracy (R 2 =0.8081, RMSE=0.0951) compared with the BPNN (R 2 =0.7320, RMSE=0.1127) and MARS (R 2 =0.7361, RMSE=0.1117). This study provides a new approach by showing the potential of the RNN-LSTM method for land surface parameter estimation and related research.

show abstract

Remote sensing algorithms for estimation of fractional vegetation cover using pure vegetation index values: A review

Cited by 261 publications

References 130 publications

Combined Sentinel-1A With Sentinel-2A to Estimate Soil Moisture in Farmland

Combined Sentinel-1A With Sentinel-2A to Estimate Soil Moisture in Farmland

Quantification of urban greenery using hemisphere-view panoramas with a green cover index

Fractional Vegetation Cover Estimation Algorithm Based on Recurrent Neural Network for MODIS 250 m Reflectance Data

Contact Info

Product

Resources

About