Fractional Vegetation Cover Estimation Research Articles

Assessing the Potential of UAV for Large-Scale Fractional Vegetation Cover Mapping with Satellite Data and Machine Learning

Fractional vegetation cover (FVC) is an essential metric for valuating ecosystem health and soil erosion. Traditional ground-measuring methods are inadequate for large-scale FVC monitoring, while remote sensing-based estimation approaches face issues such as spatial scale discrepancies between ground truth data and image pixels, as well as limited sample representativeness. This study proposes a method for FVC estimation integrating uncrewed aerial vehicle (UAV) and satellite imagery using machine learning (ML) models. First, we assess the vegetation extraction performance of three classification methods (OBIA-RF, threshold, and K-means) under UAV imagery. The optimal method is then selected for binary classification and aggregated to generate high-accuracy FVC reference data matching the spatial resolutions of different satellite images. Subsequently, we construct FVC estimation models using four ML algorithms (KNN, MLP, RF, and XGBoost) and utilize the SHapley Additive exPlanation (SHAP) method to assess the impact of spectral features and vegetation indices (VIs) on model predictions. Finally, the best model is used to map FVC in the study region. Our results indicate that the OBIA-RF method effectively extract vegetation information from UAV images, achieving an average precision and recall of 0.906 and 0.929, respectively. This method effectively generates high-accuracy FVC reference data. With the improvement in the spatial resolution of satellite images, the variability of FVC data decreases and spatial continuity increases. The RF model outperforms others in FVC estimation at 10 m and 20 m resolutions, with R2 values of 0.827 and 0.929, respectively. Conversely, the XGBoost model achieves the highest accuracy at a 30 m resolution, with an R2 of 0.847. This study also found that FVC was significantly related to a number of satellite image VIs (including red edge and near-infrared bands), and this correlation was enhanced in coarser resolution images. The method proposed in this study effectively addresses the shortcomings of conventional FVC estimation methods, improves the accuracy of FVC monitoring in soil erosion areas, and serves as a reference for large-scale ecological environment monitoring using UAV technology.

Can Multi-Temporal Vegetation Indices and Machine Learning Algorithms Be Used for Estimation of Groundnut Canopy State Variables?

The objective of this research was to assess the feasibility of remote sensing (RS) technology, specifically an unmanned aerial system (UAS), to estimate Bambara groundnut canopy state variables including leaf area index (LAI), canopy chlorophyll content (CCC), aboveground biomass (AGB), and fractional vegetation cover (FVC). RS and ground data were acquired during Malaysia’s 2018/2019 Bambara groundnut growing season at six phenological stages; vegetative, flowering, podding, podfilling, maturity, and senescence. Five vegetation indices (VIs) were determined from the RS data, resulting in single-stage VIs and cumulative VIs (∑VIs). Pearson’s correlation was used to investigate the relationship between canopy state variables and single stage VIs and ∑VIs over several stages. Linear parametric and non-linear non-parametric machine learning (ML) regressions including CatBoost Regressor (CBR), Random Forest Regressor (RFR), AdaBoost Regressor (ABR), Huber Regressor (HR), Multiple Linear Regressor (MLR), Theil-Sen Regressor (TSR), Partial Least Squares Regressor (PLSR), and Ridge Regressor (RR) were used to estimate canopy state variables using VIs/∑VIs as input. The best single-stage correlations between canopy state variables and VIs were observed at flowering (r > 0.50). Moreover, ∑VIs acquired from vegetative to senescence stage had the strongest correlation with all measured canopy state variables (r > 0.70). In estimating AGB, MLR achieved the best testing performance (R2 = 0.77, RMSE = 0.30). For CCC, RFR excelled with R2 of 0.85 and RMSE of 2.88. Most models performed well in FVC estimation with testing R2 of 0.98–0.99 and low RMSE. For LAI, MLR stood out in testing with R2 of 0.74, and RMSE of 0.63. Results demonstrate the UAS-based RS technology potential for estimating Bambara groundnut canopy variables.

Monitoring Biophysical Variables (FVC, LAI, LCab, and CWC) and Cropland Dynamics at Field Scale Using Sentinel-2 Time Series

Biophysical variables play a crucial role in understanding phenological stages and crop dynamics, optimizing ultimate agricultural practices, and achieving sustainable crop yields. This study examined the effectiveness of the Sentinel-2 Biophysical Processor (S2BP) in accurately estimating crop dynamics descriptors, including fractional vegetation cover (FVC), leaf area index (LAI), leaf chlorophyll a and b (LCab), and canopy water content (CWC). The evaluation was conducted using estimation quality indicators (EQIs) and comprehensive ground throughout the entire growing season at the field scale. To identify soil and vegetation pixels, the spectral unmixing technique was employed. According to the EQIs, the best retrievals were obtained for FVC in around 99.9% of the 23,976 pixels that were analyzed during the growth season. For LAI, LCab, and CWC, over 60% of the examined pixels had inputs that were out-of-range. Furthermore, in over 35% of the pixels, the output values for LCab and CWC were out-of-range. The FVC, LAI, and LCab estimates agreed well with ground measurements (R2 = 0.62–0.85), whereas a discrepancy was observed for CWC estimates when compared with ground measurements (R2 = 0.51). Furthermore, the uncertainties of FVC, LAI, LCab, and CWC estimates were 0.09, 0.81 m2/m2, 60.85 µg/cm2, and 0.02 g/cm2 through comparisons to ground FVC, LAI, Cab, and CWC measurements, respectively. Considering EQIs and uncertainty metrics, the order of the estimation accuracy of the four variables was FVC > LAI > LCab > CWC. Our analysis revealed that temporal variations of FVC, LAI, and LCab were primarily driven by field-scale events like sowing date, growing period, and harvesting time, highlighting their sensitivity to agricultural practices. The robustness of S2BP results could be enhanced by implementing a pixel identification algorithm, like embedding spectral unmixing. Overall, this study provides detailed, pixel-by-pixel insights into the performance of S2BP in estimating FVC, LAI, LCab, and CWC, which are crucial for monitoring crop dynamics in precision agriculture.

Pretrained Deep Learning Networks and Multispectral Imagery Enhance Maize LCC, FVC, and Maturity Estimation

Crop leaf chlorophyll content (LCC) and fractional vegetation cover (FVC) are crucial indicators for assessing crop health, growth development, and maturity. In contrast to the traditional manual collection of crop trait parameters, unmanned aerial vehicle (UAV) technology rapidly generates LCC and FVC maps for breeding materials, facilitating prompt assessments of maturity information. This study addresses the following research questions: (1) Can image features based on pretrained deep learning networks and ensemble learning enhance the estimation of remote sensing LCC and FVC? (2) Can the proposed adaptive normal maturity detection (ANMD) algorithm effectively monitor maize maturity based on LCC and FVC maps? We conducted the following tasks: (1) Seven phases (tassel initiation to maturity) of maize canopy orthoimages and corresponding ground-truth data for LCC and six phases of FVC using UAVs were collected. (2) Three features, namely vegetation indices (VI), texture features (TF) based on Gray Level Co-occurrence Matrix, and deep features (DF), were evaluated for LCC and FVC estimation. Moreover, the potential of four single-machine learning models and three ensemble models for LCC and FVC estimation was evaluated. (3) The estimated LCC and FVC were combined with the proposed ANMD to monitor maize maturity. The research findings indicate that (1) image features extracted from pretrained deep learning networks more accurately describe crop canopy structure information, effectively eliminating saturation effects and enhancing LCC and FVC estimation accuracy. (2) Ensemble models outperform single-machine learning models in estimating LCC and FVC, providing greater precision. Remarkably, the stacking + DF strategy achieved optimal performance in estimating LCC (coefficient of determination (R2): 0.930; root mean square error (RMSE): 3.974; average absolute error (MAE): 3.096); and FVC (R2: 0.716; RMSE: 0.057; and MAE: 0.044). (3) The proposed ANMD algorithm combined with LCC and FVC maps can be used to effectively monitor maize maturity. Establishing the maturity threshold for LCC based on the wax ripening period (P5) and successfully applying it to the wax ripening-mature period (P5–P7) achieved high monitoring accuracy (overall accuracy (OA): 0.9625–0.9875; user’s accuracy: 0.9583–0.9933; and producer’s accuracy: 0.9634–1). Similarly, utilizing the ANMD algorithm with FVC also attained elevated monitoring accuracy during P5–P7 (OA: 0.9125–0.9750; UA: 0.878–0.9778; and PA: 0.9362–0.9934). This study offers robust insights for future agricultural production and breeding, offering valuable insights for the further exploration of crop monitoring technologies and methodologies.

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

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.

SiamC Transformer: Siamese coupling swin transformer Multi-Scale semantic segmentation network for vegetation extraction under shadow conditions

The accuracy of fractional vegetation cover (FVC) estimation has important significance in high-precision agricultural and ecological environment assessments. However, the presence ofshadowsunder natural light conditions can cause problems such as poor vegetation distinguishability and blurred boundaries during vegetation segmentation. This leads to missing or over-segmented vegetation inshadedareas, thus reducing the accuracy of FVC. Polarizationinformation can reflect the texture structure features, edgecharacteristics and surface state information, providing important supplementary information to light intensity information. To address the issue of shadows interfering with vegetation segmentation, a Siamese coupling swin transformer (SiamC Transformer) is proposed in this study. In this network, a dual-flow structure is used to simultaneously retrieve the feature information of vegetation degree of linear polarization (DoLP) images and light intensity images simultaneously to obtain multi-dimensional global semantic information of multi-scale vegetation. In the feature fusion stage, two fusion modules are proposed: an adaptive fusion module (AFM) and an adaptive fusion plus module (AFPM), which can fuse shallow spatial information, texture information and deep semantic information. The AFM and AFPM enable the network to better achieve object localization, region activation and edge sharpening, while improving the segmentation accuracy of small objects. The experimental results show that the mean intersection over union (mIoU) of this network is as high as 97.46% on vegetation datasets consisting of light intensity and polarization images, which is better than that of other algorithms. This network has higher accuracy and adaptability for shadow scenes and improves the accuracy of FVC calculation under shadow conditions.

Analysis of Short-Term Drought Episodes Using Sentinel-3 SLSTR Data under a Semi-Arid Climate in Lower Eastern Kenya

This study uses Sentinel-3 SLSTR data to analyze short-term drought events between 2019 and 2021. It investigates the crucial role of vegetation cover, land surface temperature, and water vapor amount associated with drought over Kenya’s lower eastern counties. Therefore, three essential climate variables (ECVs) of interest were derived, namely Land Surface Temperature (LST), Fractional Vegetation Cover (FVC), and Total Column Water Vapor (TCWV). These features were analyzed for four counties between the wettest and driest episodes in 2019 and 2021. The study showed that Makueni and Taita Taveta counties had the highest density of FVC values (60–80%) in April 2019 and 2021. Machakos and Kitui counties had the lowest FVC estimates of 0% to 20% in September for both periods and between 40% and 60% during wet seasons. As FVC is a crucial land parameter for sequestering carbon and detecting soil moisture and vegetation density losses, its variation is strongly related to drought magnitude. The land surface temperature has drastically changed over time, with Kitui and Taita Taveta counties having the highest estimates above 20 °C in 2019. A significant spatial variation of TCWV was observed across different counties, with values less than 26 mm in Machakos county during the dry season of 2019, while Kitui and Taita Taveta counties had the highest estimates, greater than 36 mm during the wet season in 2021. Land surface temperature variation is negatively proportional to vegetation density and soil moisture content, as non-vegetated areas are expected to have lower moisture content. Overall, Sentinel-3 SLSTR products provide an efficient and promising data source for short-term drought monitoring, especially in cases where in situ measurement data are scarce. ECVs-produced maps will assist decision-makers with a better understanding of short-term drought events as well as soil moisture loss episodes that influence agriculture under arid and semi-arid climates. Furthermore, Sentinel-3 data can be used to interpret hydrological, ecological, and environmental changes and their implications under different environmental conditions.

Extracting vegetation information from high dynamic range images with shadows: A comparison between deep learning and threshold methods

Due to factors such as light angle and vegetation density, shadows can exist in ground vegetation images; this can lead to highly varying natural illumination in the images, which greatly limits the accuracy of fractional vegetation cover (FVC) estimation. While high dynamic range (HDR) images can reduce the extreme illumination contrast, the characteristic vegetation information in shadow areas is often lost. At present, most threshold methods do not fully utilize the spatial features of vegetation, and the results of vegetation classification under complex shadow conditions are associated with large errors. Thus, two deep learning methods (the HDR U-Net method and HDR U-Net++ method) are proposed in this study based on fully convolutional neural networks to extract vegetation information from HDR images under shadow conditions. These methods are compared with threshold methods. For full HDR images, the kappa coefficient and mean intersection over union (MIoU) of the HDR U-Net method and HDR U-Net++ method are 0.926, 0.931, and 0.874, 0.887, respectively. The FVC estimation accuracy and vegetation segmentation effect of these two deep learning methods are better than those of the three threshold methods considered. In addition, compared with normal exposure (NE) images, camera-based HDR images improve the extraction accuracy of deep learning methods and threshold methods for vegetation under shadow conditions. The results of this study suggest that deep learning methods are not affected by the threshold determination strategy selected and can more completely extract vegetation feature information from HDR images. The classification effect of vegetation under shadow conditions is effectively improved, and the vegetation segmentation and FVC estimation results are more precise. The combination of HDR images and deep learning methods can be applied to field scenes with complex lighting, which is beneficial to improve the ground data verification of remote sensing FVC products.

UAV-Based Remote Sensing for Soybean FVC, LCC, and Maturity Monitoring

Timely and accurate monitoring of fractional vegetation cover (FVC), leaf chlorophyll content (LCC), and maturity of breeding material are essential for breeding companies. This study aimed to estimate LCC and FVC on the basis of remote sensing and to monitor maturity on the basis of LCC and FVC distribution. We collected UAV-RGB images at key growth stages of soybean, namely, the podding (P1), early bulge (P2), peak bulge (P3), and maturity (P4) stages. Firstly, based on the above multi-period data, four regression techniques, namely, partial least squares regression (PLSR), multiple stepwise regression (MSR), random forest regression (RF), and Gaussian process regression (GPR), were used to estimate the LCC and FVC, respectively, and plot the images in combination with vegetation index (VI). Secondly, the LCC images of P3 (non-maturity) were used to detect LCC and FVC anomalies in soybean materials. The method was used to obtain the threshold values for soybean maturity monitoring. Additionally, the mature and immature regions of soybean were monitored at P4 (mature stage) by using the thresholds of P3-LCC. The LCC and FVC anomaly detection method for soybean material presents the image pixels as a histogram and gradually removes the anomalous values from the tails until the distribution approaches a normal distribution. Finally, the P4 mature region (obtained from the previous step) is extracted, and soybean harvest monitoring is carried out in this region using the LCC and FVC anomaly detection method for soybean material based on the P4-FVC image. Among the four regression models, GPR performed best at estimating LCC (R2: 0.84, RMSE: 3.99) and FVC (R2: 0.96, RMSE: 0.08). This process provides a reference for the FVC and LCC estimation of soybean at multiple growth stages; the P3-LCC images in combination with the LCC and FVC anomaly detection methods for soybean material were able to effectively monitor soybean maturation regions (overall accuracy of 0.988, mature accuracy of 0.951, immature accuracy of 0.987). In addition, the LCC thresholds obtained by P3 were also applied to P4 for soybean maturity monitoring (overall accuracy of 0.984, mature accuracy of 0.995, immature accuracy of 0.955); the LCC and FVC anomaly detection method for soybean material enabled accurate monitoring of soybean harvesting areas (overall accuracy of 0.981, mature accuracy of 0.987, harvested accuracy of 0.972). This study provides a new approach and technique for monitoring soybean maturity in breeding fields.

Estimation of Potato Chlorophyll Content from UAV Multispectral Images with Stacking Ensemble Algorithm

Rapid and accurate crop chlorophyll content estimation is crucial for guiding field management and improving crop yields. This study explored the potential for potato chlorophyll content estimation based on unmanned aerial vehicle (UAV) multispectral imagery. To search the optimal estimation method, three parts of research were conducted as following. First, a combination of support vector machines (SVM) and a gaussian mixture model (GMM) thresholding method was proposed to estimate fractional vegetation cover (FVC) during the potato growing period, and the proposed method produced efficient estimates of FVC; among all the selected vegetation indices (VIs), the soil adjusted vegetation index (SAVI) had the highest accuracy. Second, the recursive feature elimination (RFE) algorithm was utilized to screen the VIs and texture features derived from multispectral images: three Vis, including modified simple ratio (MSR), ratio vegetation index (RVI) and normalized difference vegetation index (NDVI); three texture features, including correlation in the NIR band (corr-NIR), correlation in the red-edge band (corr-Red-edge) and homogeneity in the NIR band (hom-NIR), showed higher contribution to chlorophyll content estimation. Finally, a stacking model was constructed with K-Nearest Neighbor (KNN), a light gradient boosting machine (light-GBM), SVM algorithm as the base model and linear fitting as the metamodel, and four machine learning algorithms (SVM, KNN, light-GBM and stacking) were used to build the chlorophyll content estimation model suitable for different growing seasons. The results were: (1) The performance of the estimation model could be improved based on both VIs and texture features over using single-type features, and the stacking algorithm yielded the highest estimation accuracy with an R2 value of 0.694 and an RMSE value of 0.553; (2) When FVC was added, the estimation model accuracy was further improved, and the stacking algorithm also produced the highest estimation accuracy with R2 value of 0.739, RMSE value of 0.511 (3) When comparing modeling algorithms, stacking algorithms had greater advantages in the estimation chlorophyll content with potato plants than using single machine learning algorithms. This study indicates that taking into account the combination of VIs reflecting spectral characteristics, texture features reflecting spatial information and the FVC reflecting canopy structure properties can accomplish higher chlorophyll content estimation accuracy, and the stacking algorithm can integrate the advantages of a single machine learning model, with great potential for estimation of potato chlorophyll content.

Evaluation of the impact of crop residue on fractional vegetation cover estimation by vegetation indices over conservation tillage cropland: a simulation study

ABSTRACT Accurate estimation of fractional vegetation cover (FVC) is of great significance to agricultural production. Crop residue management affect crop residue cover (CRC) over croplands. Crop and crop residue on the soil surface both contribute to overall canopy reflectance. Few studies, however, have examined the effect of crop residue on vegetation indices (VIs) and estimated FVC. The present study evaluated the response of eight commonly used VIs to crop residues and FVC uncertainty caused by crop residue based on the dimidiate pixel model (DPM) by using simulated reflectance of low-tilled cropland via a three-dimensional radiative transfer model. The absolute difference (AD) was used to quantify the spectral difference between crop residues and soils in red and near infrared wavelengths. Increases in normalized difference VI (NDVI), ratio VI (RVI), transformed soil-adjusted VI (TSAVI), and normalized difference phenology index (NDPI) were observed when green crops were mixed with crop residue that had negative ADs with soils, but decreases in enhance VI (EVI), perpendicular VI (PVI), SAVI, and litter-soil-adjusted VI (L-SAVI) were observed when crop residue was present under medium and high vegetation cover. The presence of crop residue with a positive AD with soils reduced NDVI, RVI, TSAVI, and NDPI while increased the other VIs. Crop residue had the least impact on EVI- and SAVI-based DPMs, with FVC-estimated uncertainty less than 0.1, followed by the NDPI- and L-SAVI-based model, while DPMs based on NDVI- and RVI performed poorly. Each VI-based DPM’s estimated uncertainty was highly correlated with AD values. Furthermore, the majority of the VI-based models were sensitive to solar position except for the NDPI-based model. Our findings highlight the need of considering the impact of crop residue on FVC retrieval over low-tilled cropland in future research.

Integrating 250 m MODIS data in spectral unmixing for 500 m fractional vegetation cover estimation

• The 250 m MODIS data are integrated with the 500 m MODIS data for FVC estimation. • The 250 m features are stacked with the 500 m features for spectral unmixing. • The proposed method increases the accuracy of FVC estimation obviously. • The method has great potential for enhancing current 500 m FVC products. Fractional vegetation cover (FVC) is an important indicator to measure the potential for carbon neutrality in the terrestrial ecosystem. Spectral unmixing is a common choice for FVC estimation. To deal with the lack of endmembers and intra-class spectral variation, machine learning-based spectral unmixing methods have been developed, but the training samples were constructed based on the data acquired at a time different from the prediction time, which leads to great uncertainty in FVC estimation. Moreover, the used sample features may not cope with areas with strong heterogeneity, where vegetation cannot be reliably identified from the complex background. In this paper, for 500 m FVC estimation, the recently developed the spatio-temporal spectral unmixing model is applied to deal with the inconsistency between training and predicting data by extracting training samples at prediction time directly. Furthermore, more features from 250 m MODIS data are proposed to be integrated with the original 500 m MODIS data. Specifically, for sample construction, new features from 250 m bands (Red and NIR) are stacked with the original 500 m features. For model training, the random forest (RF) model is applied, which can handle high-dimensional data composed of features from different sources. The trained model is employed to predict the FVC of all 500 m MODIS pixels. The proposed method of incorporating 250 m data in 500 m FVC mapping was validated through experiments in five different areas. The results show that the accuracy of FVC mapping can be increased obviously by integrating 250 m features, and the training samples extracted at the prediction time are more reliable for modeling training. This paper has great potential for enhancing current 500 m FVC products at the global scale.

Estimating grassland vegetation cover with remote sensing: A comparison between Landsat-8, Sentinel-2 and PlanetScope imagery

Grassland fractional vegetation cover (FVC) accurate mapping on a large scale is crucial, since degraded grasslands contribute less to provisioning services, carbon storage, water purification, erosion control and biodiversity conservation. The spatial and temporal resolution of Sentinel-2 (S2) and PlanetScope (PS) data has never been explored for grassland FVC estimation so far and will enable researchers and agencies to quantify and map timelier and more precisely grassland processes. In this paper we compare FVC estimation models developed from Landsat-8 (L8), S2 and PS imagery. The reference grassland FVC dataset was obtained on the Paganella ski runs (46.15°N, 11.01°E, Italy) applying unsupervised classification to nadir grassland RGB photographs taken from 1.35 m above the soil. Fractional Response Models between reference FVC and 18 vegetation indices (VIs) extracted from satellite imagery were fitted and analysed. Then, leave-one-out cross validation and spatiotemporal change analysis were also performed. Our study confirms the robustness of the commonly used VIs based on the difference between NIR and the red wavelength region (R2 = 0.91 for EVI using S2 imagery) and indicate that VIs based on the red-edge spectral region are the best performing for PS imagery (R2 = 0.89 for RECI). Only medium to high spatial resolution imagery (S2 and PS) precisely mapped spatial patterns at the study site, since grasslands FVC varies at a fine scale. Previously available imagery at medium to low spatial and temporal resolution (e.g., L8) may still be interesting for analysis requiring long time-series of data.

Efficient selection of SAR features using ML based algorithms for accurate FVC estimation

Fractional vegetation cover (FVC) is a ratio of vertical projection area of green vegetation to the total area under consideration. Crops infested by pests, diseases or nutrient deficiency show their impact on the crop coverage. Therefore, FVC is a good indicator of crop health and arid soil. Recently, various models have been reported for FVC estimation using optical data, but it is still limited to different weather conditions. Therefore, it is not feasible to continue crop monitoring using optical data. On the other hand, synthetic aperture radar (SAR) data is weather independent, and has a good potential for crop monitoring in all-weather conditions. SAR data has been used for many crop parameters estimation, however has not been much explored for FVC estimation. Plenty SAR features are available which are sensitive to vegetation parameters. Some of the features are sensitive during early crop stages (e.g., entropy, DpRVI-dual polarization radar vegetation index), while others are sensitive during different stages of crops (backscattering signal of VH and VV polarization). Therefore, there is a need to critically assess all the features and find the optimum combination that provides exemplary results during the entire crop cycle. For this purpose, sixteen features are considered using the different combinations of Sentinel-1 SLC data and their temporal analysis is observed for their different phenology stages. Four machine learning (ML) based models i.e., LightGBM, Xgboost, K-nearest neighbor (KNN), and Random Forest have been explored on these features for FVC estimation. The performance of each model is assessed with the error metrics. Xgboost emerges as the best model with a minimum RMSE value of 0.159. Xgboost model has the capability to recognize the most important features. Due to the stochastic nature of the algorithm, feature priority sequence may vary, therefore, algorithm runs multiple times and the probability of each feature for every position is calculated and on the basis of the highest probability, feature importance sequences is decided. Xgboost model is developed by increasing the input features in the order of their importance sequence and the RMSE value is calculated for each input combination. It is noted that initially, the RMSE value improved from 0.22 to 0.15 for the top five input features. When additional features were included, no further improvement in the RMSE was observed. Therefore; entropy, alpha, VH, VH/VV, and VV are the top five features which are used in the Xgboost model for FVC estimation instead of all sixteen features, which delivers satisfactory results.

Estimation and validation of 30 m fractional vegetation cover over China through integrated use of Landsat 8 and Gaofen 2 data

Fractional vegetation cover (FVC) is an important parameter that reflects the status of vegetation and can be used to quantify vegetation dynamics in system models of Earth. Currently, global FVC products are usually available at coarse spatial resolutions, and so cannot satisfy the requirements for detailed investigations of the distribution of vegetation cover in different regions worldwide. Thus, a fine-resolution FVC product that covers a large spatial extent is needed. In this study, we develop an operational framework to produce Landsat-like spatial resolution FVC products using high-resolution images and a machine learning algorithm. We used 1 m Gaofen 2 data to calculate the 30 m FVC, and then applied as training and testing data for modeling. The random forest regression model using Landsat 8 surface reflectance and solar angle as inputs outperformed the other models in terms of accuracy and efficiency and was selected to estimate the 30 m FVC. The model has a high training accuracy, with an R2 of 0.978 and an RMSE of 0.042. When validated using 346 independent ground measurements from 14 sites around the globe, the R2 was 0.814 and the RMSE was 0.170. We compared three coarse-resolution FVC products at both regional and national scales, including GLASS, GEOV2 and CGLOPS FVC products. The 30 m Landsat FVC from this study was spatially and temporally consistent with all reference FVC products, but provided advantages in revealing the fine spatial details of vegetation cover. The performance of the 30 m FVC model varied with vegetation type, but showed the highest consistency with the GLASS FVC for most vegetation types. Finally, by applying the established 30 m FVC model to all Landsat 8 data over China from 2013 to 2018, we derived a seasonal maximum FVC mosaic, which successfully demonstrated the seasonal and spatial variations in vegetation cover in China. We conclude that the proposed framework enables accurate estimation of FVC at a high resolution over a large spatial scale and so, can be used as part of an operational approach for generating a global fine-resolution FVC product.

Smartphone Digital Photography for Fractional Vegetation Cover Estimation

Accurate ground measurements of fractional vegetation cover (FVC) are key for characterizing ecosystem functions and evaluating remote sensing products. The increasing performance of cameras equipped in smartphones opens new opportunities for extensive FVC measurement through citizen science initiatives. However, the wide field of view (FOV) of smartphone cameras constitutes a key source of uncertainty in the estimation of vegetation parameters, which has been largely ignored. We designed a practical method to characterize the FOV of smartphones and improve the FVC estimation. The method was assessed in a mountainous forest based on the comparison with in situ fisheye photographs. After the FOV correction, the agreement of smart-phone and fisheye FVC estimates highly improved: root-mean-square error (RMSE) of 0.103 compared to 0.242 of the original smartphone FVC estimates without considering the FOV effect, mean difference of 0.074 versus 0.213, and coefficient of determination R2 of 0.719 versus 0.353. Smartphone cameras outperform traditional fisheye cameras: the overexposure and low vertical resolution of fisheye photographs introduced uncertainties in FVCestimation while the insensitivity to exposure and high spatial resolution of smartphone cameras make photograph acquisition and analysis more automatic and accurate. The smartphone FVCestimates highly agree with the GF-1 satellite product: RMSE = 0.066, bias = 0.007, and R2 = 0.745. This study opens new perspectives for the validation of satellite products.

Using a Vegetation Index-Based Mixture Model to Estimate Fractional Vegetation Cover Products by Jointly Using Multiple Satellite Data: Method and Feasibility Analysis

Remote sensing fractional vegetation cover (FVC) requires both finer-resolution and high-frequency in climate and ecosystem research. The increasing availability of finer-resolution (≤ 30 m) remote sensing data makes this possible. However, data from different satellites have large differences in spatial resolution, spectral response function, and so on, making joint use difficult. Herein, we showed that the vegetation index (VI)-based mixture model with the appropriate VI values of pure vegetation (Vv) and bare soil (Vs) from the MODIS BRDF product via the multi-angle VI method (MultiVI) was feasible to estimate FVC with multiple satellite data. Analyses of the spatial resolution and spectral response function differences for MODIS and other satellites including Landsat 8, Chinese GF 1, and ZY 3 predicted that (1) the effect of Vv and Vs downscaling on FVC estimation uncertainty varied from satellite to satellite due to the positioning differences, and (2) after spectral normalization, the uncertainty (RMSDs) for FVC estimation decreased by ~2.6% compared with the results without spectral normalization. FVC estimation across multiple satellite data will help to improve the spatiotemporal resolution of FVC products, which is an important development for numerous biophysical applications. Herein, we proved that the VI-based mixture model with Vv and Vs from MultiVI is a strong candidate.

Improving Fractional Vegetation Cover Estimation With Shadow Effects Using High Dynamic Range Images

Measured fractional vegetation cover (FVC) on the ground is very important for validation of the remote sensing products and algorithms. However, because of the influence of some factors such as the angle of illumination and vegetation density, the existence of vegetation shadows limits the accuracy of FVC estimation. This article proposes a deep learning method to reduce the FVC estimation error based on high dynamic range (HDR) images with vegetation shadows (HDR REC-DL method). The HDR REC-DL method can accurately extract FVC from HDR images with complex texture information on vegetation shadows. This method is based on the U-Net convolutional network structure for semantic segmentation of images containing vegetation shadows, and the segmentation results are less affected by vegetation types. Results from the HDR REC-DL method were highly similar to the vegetation segmentation results from visual interpretation. Values of the kappa coefficient, F1 score (F1), recall, and mean intersection over union of the HDR REC-DL method were 0.926, 0.942, 0.924, 0.916 for sunny weather and 0.903, 0.974, 0.983, and 0.895 for cloudy weather, respectively. Compared with the vegetation segmentation accuracy of the shadow-resistant algorithm, the HDR REC-DL method increases the kappa coefficient, F1, and mIOU by 21%, 16%, and 29% for sunny weather, and by 11.1%, 3.6%, and 10.3% for cloudy weather, respectively. The HDR REC-DL method provides a novel method for accurately estimating FVC from images containing vegetation shadows.

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

Fractional vegetation cover (FVC) is an important indicator for exploring hydrosphere, pedosphere, atmosphere, biosphere, and their interactions. Deep learning (DL) is a potential tool to handle large-scale data and approximate the complex nonlinear relationship between variables. It is, therefore, suitable for FVC estimation. However, few DL-based algorithms have been developed to estimate FVC as it is difficult to obtain a large amount of training data. This letter presents a novel method by means of deep transfer learning to address this issue. The proposed technique consists of two steps. In the first step, a large amount of simulated training samples were generated by a physical model (PROSPECT + SAIL radiative transfer model, PROSAIL). In the second step, a long short-term memory (LSTM) network was pretrained with the simulated training dataset obtained in the first step. Then limited real samples from satellite images were used to fine-tune the pretrained network. Experiments were conducted for the Sentinel-2 multispectral satellite images of two areas and the results were compared with those obtained by the traditional the Normalized Difference Vegetation Index (NDVI)-based method and two machine learning approaches. The results demonstrate that the performance of our method outperforms other advanced FVC estimation methods.

Comparative Study of Fractional Vegetation Cover Estimation Methods Based on Fine Spatial Resolution Images for Three Vegetation Types

Comparative Study of Fractional Vegetation Cover Estimation Methods Based on Fine Spatial Resolution Images for Three Vegetation Types