A Deep Transfer Learning Method for Estimating Fractional Vegetation Cover of Sentinel-2 Multispectral Images

Yu, Ruyi; Li, Shanshan; Zhang, Bing; Zhang, Hongqun; Peng, Dailiang; Gao, Jianwei

doi:10.1109/lgrs.2021.3125429

Cited by 10 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ground sample point design used a five-point sampling method ( Figure 2 ) ( Yu et al., 2021 ). Five photographs (2m scale samples) were taken using a digital camera along two diagonals of the sampling point and their average was used as the FVC sample with a spatial resolution of 10m FVC real , while the FVC sample with a spatial resolution of 2m was only used for the middle of the 10m sample.…”

Section: Methodsmentioning

confidence: 99%

“…In this manuscript, Gaussian fitting and segmentation algorithms are utilized to extract FVC from the image ( Liu et al., 2012 ; Yu et al., 2021 ). The core of the algorithm is to convert the color space of a digital image from RGB to CIE L*a*b*.…”

Section: Methodsmentioning

confidence: 99%

“…Satellite remote sensing has the advantages of long-time series, large scale (even global scale), and multi-scale (spatial and spectral scales), making it a common means of estimating FVC ( Yu et al., 2021 ). Researchers have developed numerous FVC estimation methods based on coarse and medium spatial resolution satellite remote sensing data, including empirical models ( Maurya et al., 2018 ; Riihimäki et al., 2019 ), linear unmixing models( Wang et al., 2020b ; Wu et al., 2021 ), physical-based models ( Jia et al., 2016 ; Tu et al., 2019 ), and machine learning (hereafter ML) methods( Graenzig et al., 2021 ; Maurya et al., 2022 ; Song et al., 2022 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accurate estimation of fractional vegetation cover for winter wheat by integrated unmanned aerial systems and satellite images

Yang,

Li,

Zhang

et al. 2023

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

Accurate estimation of fractional vegetation cover (FVC) is essential for crop growth monitoring. Currently, satellite remote sensing monitoring remains one of the most effective methods for the estimation of crop FVC. However, due to the significant difference in scale between the coarse resolution of satellite images and the scale of measurable data on the ground, there are significant uncertainties and errors in estimating crop FVC. Here, we adopt a Strategy of Upscaling-Downscaling operations for unmanned aerial systems (UAS) and satellite data collected during 2 growing seasons of winter wheat, respectively, using backpropagation neural networks (BPNN) as support to fully bridge this scale gap using highly accurate the UAS-derived FVC (FVCUAS) to obtain wheat accurate FVC. Through validation with an independent dataset, the BPNN model predicted FVC with an RMSE of 0.059, which is 11.9% to 25.3% lower than commonly used Long Short-Term Memory (LSTM), Random Forest Regression (RFR), and traditional Normalized Difference Vegetation Index-based method (NDVI-based) models. Moreover, all those models achieved improved estimation accuracy with the Strategy of Upscaling-Downscaling, as compared to only upscaling UAS data. Our results demonstrate that: (1) establishing a nonlinear relationship between FVCUAS and satellite data enables accurate estimation of FVC over larger regions, with the strong support of machine learning capabilities. (2) Employing the Strategy of Upscaling-Downscaling is an effective strategy that can improve the accuracy of FVC estimation, in the collaborative use of UAS and satellite data, especially in the boundary area of the wheat field. This has significant implications for accurate FVC estimation for winter wheat, providing a reference for the estimation of other surface parameters and the collaborative application of multisource data.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate estimation of fractional vegetation cover for winter wheat by integrated unmanned aerial systems and satellite images

Yang,

Li,

Zhang

et al. 2023

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The introduction of an attention mechanism to capture and interpret the contribution of each time node in the time-series data to the models can be considered; in combination with knowledge of the crop phenological period, this could be used to make estimates of pre-production early yields. In subsequent studies, the use of transfer learning methods to improve the scalability of the model could also be tried; this would be similar to a method of predicting winter wheat FVC using deep transfer learning (Yu et al, 2022).…”

Section: Analysis Of the Models And Other Factors Affecting The Yieldmentioning

confidence: 99%

Wheat yield estimation using remote sensing data based on machine learning approaches

et al. 2022

View full text Add to dashboard Cite

Accurate predictions of wheat yields are essential to farmers’production plans and to the international trade in wheat. However, only poor approximations of the productivity of wheat crops in China can be obtained using traditional linear regression models based on vegetation indices and observations of the yield. In this study, Sentinel-2 (multispectral data) and ZY-1 02D (hyperspectral data) were used together with 15709 gridded yield data (with a resolution of 5 m × 5 m) to predict the winter wheat yield. These estimates were based on four mainstream data-driven approaches: Long Short-Term Memory (LSTM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and Support Vector Regression (SVR). The method that gave the best estimate of the winter wheat yield was determined, and the accuracy of the estimates based on multispectral and hyperspectral data were compared. The results showed that the LSTM model, for which the RMSE of the estimates was 0.201 t/ha, performed better than the RF (RMSE = 0.260 t/ha), GBDT (RMSE = 0.306 t/ha), and SVR (RMSE = 0.489 t/ha) methods. The estimates based on the ZY-1 02D hyperspectral data were more accurate than those based on the 30-m Sentinel-2 data: RMSE = 0.237 t/ha for the ZY-1 02D data, which is about a 5% improvement on the RSME of 0.307 t/ha for the 30-m Sentinel-2 data. However, the 10-m Sentinel-2 data performed even better, giving an RMSE of 0.219 t/ha. In addition, it was found that the greenness vegetation index SR (simple ratio index) outperformed the traditional vegetation indices. The results highlight the potential of the shortwave infrared bands to replace the visible and near-infrared bands for predicting crop yields Our study demonstrates the advantages of the deep learning method LSTM over machine learning methods in terms of its ability to make accurate estimates of the winter wheat yield.

show abstract

“…Machine learning methods have evolved as reliable methods of learning nonlinear relationships because they require less parameterization, are implemented at various spatial and temporal scales, and are more robust and covariant to noisy features, small training sizes, and large numbers of dimensions ( Verrelst et al., 2012 ; Liang et al., 2015 ; Houborg and McCabe, 2018 ). These methods have been widely used for estimating various biophysical parameters such as the leaf area index ( Duan et al., 2019 ; Tao et al, 2020 ), vegetation cover ( Niu et al., 2021 ; Yu et al., 2021 ), biomass ( Yue et al., 2019 ; Tao et al, 2020 ), Canopy chlorophyll content ( Jiao et al., 2021 ) and the leaf tilth distribution ( Zou et al., 2022 ). However, few studies have been conducted to estimate the tiller density of winter wheat.…”

Section: Introductionmentioning

confidence: 99%

Estimation of wheat tiller density using remote sensing data and machine learning methods

Zhang

Peng

et al. 2022

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

The tiller density is a key agronomic trait of winter wheat that is essential to field management and yield estimation. The traditional method of obtaining the wheat tiller density is based on manual counting, which is inefficient and error prone. In this study, we established machine learning models to estimate the wheat tiller density in the field using hyperspectral and multispectral remote sensing data. The results showed that the vegetation indices related to vegetation cover and leaf area index are more suitable for tiller density estimation. The optimal mean relative error for hyperspectral data was 5.46%, indicating that the results were more accurate than those for multispectral data, which had a mean relative error of 7.71%. The gradient boosted regression tree (GBRT) and random forest (RF) methods gave the best estimation accuracy when the number of samples was less than around 140 and greater than around 140, respectively. The results of this study support the extension of the tested methods to the large-scale monitoring of tiller density based on remote sensing data.

show abstract

A Deep Transfer Learning Method for Estimating Fractional Vegetation Cover of Sentinel-2 Multispectral Images

Cited by 10 publications

References 20 publications

Accurate estimation of fractional vegetation cover for winter wheat by integrated unmanned aerial systems and satellite images

Accurate estimation of fractional vegetation cover for winter wheat by integrated unmanned aerial systems and satellite images

Wheat yield estimation using remote sensing data based on machine learning approaches

Estimation of wheat tiller density using remote sensing data and machine learning methods

Contact Info

Product

Resources

About