Next Article in Journal
TopoLAP: Topology Recovery for Building Reconstruction by Deducing the Relationships between Linear and Planar Primitives
Previous Article in Journal
Sub-Pixel Crop Type Classification Using PROBA-V 100 m NDVI Time Series and Reference Data from Sentinel-2 Classifications
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Estimation of Rice Growth Parameters Based on Linear Mixed-Effect Model Using Multispectral Images from Fixed-Wing Unmanned Aerial Vehicles

1
National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, China
2
Key Laboratory for Crop System Analysis and Decision Making, Ministry of Agriculture and Rural Affairs, Nanjing Agricultural University, Nanjing 210095, China
3
Jiangsu Key Laboratory for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, China
4
Jiangsu Collaborative Innovation Center for Modern Crop Production, Nanjing Agricultural University, Nanjing 210095, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(11), 1371; https://doi.org/10.3390/rs11111371
Submission received: 19 May 2019 / Revised: 3 June 2019 / Accepted: 4 June 2019 / Published: 8 June 2019
(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)

Abstract

:
The accurate estimation of aboveground biomass (AGB) and leaf area index (LAI) is critical to characterize crop growth status and predict grain yield. Unmanned aerial vehicle (UAV) -based remote sensing has attracted significant interest due to its high flexibility and easiness of operation. The mixed effect model introduced in this study can capture secondary factors that cannot be captured by standard empirical relationships. The objective of this study was to explore the potential benefit of using a linear mixed-effect (LME) model and multispectral images from a fixed-wing UAV to estimate both AGB and LAI of rice. Field experiments were conducted over two consecutive years (2017–2018), that involved different N rates, planting patterns and rice cultivars. Images were collected by a compact multispectral camera mounted on a fixed-wing UAV during key rice growth stages. LME, simple regression (SR), artificial neural networks (ANN) and random forests (RF) models were developed relating growth parameters (AGB and LAI) to spectral information. Cultivar (C), growth stage (S) and planting pattern (P) were selected as candidates of random effects for the LME models due to their significant effects on rice growth. Compared to other regression models (SR, ANN and RF), the LME model improved the AGB estimation accuracy for all stage groups to varying degrees: the R2 increased by 0.14–0.35 and the RMSE decreased by 0.88–1.80 t ha−1 for the whole season, the R2 increased by 0.07–0.15 and the RMSE decreased by 0.31–0.61 t ha−1 for pre-heading stages and the R2 increased by 0.21–0.53 and the RMSE decreased by 0.72–1.52 t ha−1 for post-heading stages. Further analysis suggested that the LME model also successfully predicted within the groups when the number of groups was suitable. More importantly, depending on the availability of C, S, P or combinations thereof, mixed effects could lead to an outperformance of baseline retrieval methods (SR, ANN or RF) due to the inclusion of secondary effects. Satisfactory results were also obtained for the LAI estimation while the superiority of the LME model was not as significant as that for AGB estimation. This study demonstrates that the LME model could accurately estimate rice AGB and LAI and fixed-wing UAVs are promising for the monitoring of the crop growth status over large-scale farmland.

Graphical Abstract

1. Introduction

Monitoring crop growth status efficiently and in a non-destructive way is necessary for precision crop management [1]. Aboveground biomass (AGB) and leaf area index (LAI) are important growth parameters with which to evaluate crop growth status [2,3]. Both have been applied to describe the canopy structure of plants and to predict grain yield [4]. In addition, AGB and LAI have been reported to affect the global carbon cycle and climate change [5,6]. It is therefore critical to efficiently and rapidly measure crop AGB and LAI.
As a developing approach, remote sensing technology has been successfully used for crop growth monitoring in recent decades [1,7,8]; examples are its use as a satellite-based platform, manned airborne platform and in ground-based spectral devices. However, several limitations still apply for these platforms. Satellite-based platforms are restrained by deficient spatio-temporal resolution and cloud cover, manned airborne platforms have relatively high operating costs and ground-based spectral devices are laborious and suffer from inefficient operation [9,10,11]. In comparison, rapid-developed unmanned aerial vehicle (UAV) platforms provide an economical and high-efficiency approach to meet the continuously growing demands for improved spatial, temporal and spectral resolutions [10,11,12].
Among UAV-based crop monitoring studies, sensors have typically been multispectral and hyperspectral cameras that target biomass estimation, LAI monitoring or grain yield prediction [1,13,14]. In recent years, UAV-based multispectral images were used to estimate the rice growth status and predict grain yield. For example, Devia et al. used seven vegetation indices, combined with multivariable regressions to monitor agronomy parameters at different rice growth stages [15]. Duan et al. integrated UAV-based vegetation indices (VIs) and abundance information obtained from spectral mixture analysis to improve the prediction accuracy of rice yield at the heading stage [16]. In addition, most UAV-based studies used multi-rotor UAVs due to their high stability, superior image quality and good controllability. However, many multi-rotor UAVs do not meet the requirements of large-scale crop monitoring with regard to flight speeds and flight duration [10]. In contrast, most fixed-wing UAVs can fly at high speeds and usually have a long flight duration; however, the flight speeds are too fast to capture high-quality images and the operation is more complicated than that of multi-rotor UAVs [17]. As a result, little attention has been directed to fixed-wing UAVs in the field of crop monitoring.
In addition to different remote sensing platforms, scholars have also used various retrieval methods to quantitatively retrieve crop growth parameters [18,19,20]. These methods can generally be divided into two categories: empirical and physical [21]. With advantages of higher computational efficiency and lower instrumental requirements, empirical methods have been more widely applied than physical methods [21]. Furthermore, although empirical methods are commonly established via parametric regression, non-parametric regression is used more frequently, such as artificial neural network (ANN) and random forest (RF) regression models. ANN regression models have been successfully applied to estimate crop properties, such as crop biomass [18], LAI [19] and foliage nitrogen concentrations [22]. A range of studies used the RF regression model to map crop attributes, for example, biomass retrieval [23], LAI retrieval [24] and nitrogen status monitoring [25].
While empirical methods have been widely applied and extended, the empirical regression relationship still cannot control deviation from many secondary experimental factors and its parameters are condition specific [26,27,28]. A review by Corti et al. indicated that the factors (e.g., crop growth stage, sensor type, acquisition mode, sensed target and spatial resolution) exert different effects on the performance of maize variables estimation; furthermore, the estimation models have different forms and performance in response to different factors [26]. Kang et al. also suggested that the relationship between LAI and VI is not unique, especially in the agricultural setting but rather represented by a family of equations as a function of the specific geographical, biological and environmental setting [27]. In addition, other plant-related factors were found to affect canopy reflectance (e.g., plant species, development stage, age and site); however, the empirical regressions did not take these factors into account [28,29]. These issues have been identified as major limitation for the wide application of the empirical method. A powerful approach is needed to generalize empirical relationships to fit global samples across different crop types and growth stages.
The mixed-effect model might provide new insights for the development of universal models for crop growth parameters estimation. The mixed-effect model can quantify the relationships between explanatory variables and response variables by breaking down the regression into both fixed effects and random effects. Fixed effects represent the global relationship between explanatory and response variables, while random effects represent the deviations from the global relationships within each group that are only associated with membership to a particular group [30]. The normal global y = f(x) relationship only takes the effects of explanatory variables to the regression into account, while overlooking the effects of other relevant factors (e.g., site, growth stage and cultivar type). The mixed-effect model also addresses the hierarchical nature of the data by incorporating plot or stand-level variations in the model [31,32]. Due to these advantages, the mixed-effect model has been extensively adopted in the field of forest remote sensing during recent years, with a particular focus on forest biomass estimation with LiDAR data [31,32,33]. Poudel et al. [32] combined linear mixed-effect (LME) models with multi-temporal LiDAR data to estimate changes of aboveground biomass and cubic volume. The authors grouped 78 plots into five plot types based on basal area per hectare in the given plots and the plot type was used as random effect. The estimation based on LME models was more accurate than that based on the differences in LiDAR-based estimates.
This study was conducted to explore the potential of mixed-effect models for estimating rice growth parameters based on the superiority of mixed-effect models to address uncertainty. Thus, the objectives of this study were to, (1) evaluate the potential of the fixed-wing UAV for crop monitoring; (2) estimate rice AGB and LAI by combining a LME model with spectral information derived from UAV multispectral images; (3) compare the performance of different retrieval methods (simple regression (SR), ANN, RF, LME) to estimate rice AGB and LAI. The result is promising to provide technical support for the monitoring of the crop growth status over large-scale farmland based on the UAV remote sensing platform.

2. Materials and Methods

2.1. Study Area and Experimental Details

Field experiments were conducted in two consecutive years (2017–2018) at the experimental station of the Taizhou National Modern Agriculture Demonstration Area located in Taizhou City, Jiangsu Province, China (119°89′E, 33°08′N) (Figure 1). Experiments were conducted with different N rates, planting patterns and rice cultivars (Table 1). In 2017, the experiment used four N rates and three planting patterns with two rice cultivars. In 2018, the experiment used four N rates and two planting methods with two rice cultivars. The distribution of total N at different growth stages was 30% before the transplanting stage, 20% at the tillering stage, 30% at the jointing stage and 20% at the booting stage.
Thirty-five ground control points (GCPs) were built and monitored in the study area (Figure 1) to enable georeferencing of the UAV data. These were set up using circular panels with a 50 cm diameter. The center of each panel was measured using the Trimble GeoExplorer 6000 Series GeoXH (Trimble Navigation, Sunnyvale, CA, USA). The estimated accuracy of the GCPs was 2.5 cm in horizontal coordinates and 4 cm in longitudinal coordinates.

2.2. Field Data Collection

Ground destructive sampling was conducted just after the UAV campaigns at key rice growth stages (Table 1). For each plot, three hills were randomly selected from different positions in the sampling area (Figure 1) of the plot, the tiller number of which equaled the average tiller number of the plot at the corresponding growth stage. The average tiller number was determined by averaging the tiller number of 20 random hills in the sampling area at corresponding growth stages [34]. Plants were manually uprooted and separated into different organs (leaf, stem and panicle) to determine the dry matter content of different organs.
LAI were immediately measured by using a Li-3000c leaf area meter (Li-Cor., Lincoln, NE, USA) to scan the area of separated fresh green leaves. Based on Equation (1), the LAI of the rice population was calculated to represent the LAI of each plot [35].
LAI = A × 10 4 3 × 1 D
D represents the number of hills in a 1-m2 scope within the plot from a survey of the rice stem tiller dynamic at the nutritive growth stage; A (cm2) represents the total leaf area of the sample (three hills). Descriptive statistics of growth parameters are show in Table 2.

2.3. UAV Image Acquisition

Aerial images were collected using a commercially available fixed-wing eBee SQ UAV (senseFly, Cheseaux-Lausanne, Switzerland) equipped with a compact multispectral Parrot Sequoia sensor (MicaSense, Seattle, WA, USA) (Figure 2). The eBee SQ is a hand-launched, autonomous, flying aircraft that consists of a rigid wing and an electric motor-driven pusher propeller. The maximum flight duration of the eBee SQ (equipped with multispectral sensor) is approximately 55 min during which it can cover a maximum area of about 80 ha (spatial resolution of 8 cm, both forward and lateral image overlaps of 70%). SenseFly’s eMotion software was used to develop the eBee SQ flight plan beforehand and to monitor the flight using a laptop; for more detailed information, please refer to the method described by Chianucci et al. [36]. The Parrot Sequoia sensor consists of five channels, which include a 16 megapixel rolling shutter RGB camera with a 4608 × 3456 pixel resolution and four 1.5 megapixel global-shutter single band cameras at 1280 × 960 pixel resolution in the following spectral bands: green (wavelength = 550 nm, bandwidth = 40 nm), red (wavelength = 660 nm, bandwidth = 40 nm), red edge (wavelength = 735 nm, bandwidth = 10 nm) and near infrared (NIR, wavelength = 790 nm, bandwidth = 40 nm). Radiometric calibration images of the Parrot Sequoia camera were captured on the ground before each flight, using a calibrated reflectance panel (MicaSense) [37]. The Parrot Sequoia camera also depends on a sunshine sensor to automatically adjust the readings to ambient light to minimize error during image capture [38]. Absolute positioning was directly recorded with a georeferencing method using the position/attitude measurements derived from the UAV-embedded GPS/IMU instruments [36].
Flights were conducted at five sampling stages for 2017 and six sampling stages for 2018 during the growing seasons (Table 1). Images were collected in TIFF format with the camera set to automatic mode under stable ambient and clear-sky conditions between 10:00 am and 2:00 pm. The ground pixel resolution was set to 8 cm, corresponding to a flight altitude of about 80 m. The forward and lateral image overlaps were both set to 70%.

2.4. Processing of UAV Spectral Images

After each flight, five image sets were produced: one multispectral image sets each in the green, red, red edge and NIR bands and one RGB image set. Only the four multispectral image sets were selected because VIs and four monochrome image reflectance were needed for this study. Pix4D mapper 4.2 (Pix4D S.A., Lausanne, Switzerland) was used to generate the orthomosaic. The key steps of orthomosaic generation using Pix4D mapper comprised camera alignment, geo-referencing, radiometric calibration, orthomosaic and generating VI maps. 35 GCPs in the Pix4D project were used to georeference the study area, increase the global accuracy and decrease band-to-band misalignment. Reflectance calibration was conducted by using radiometric calibration images with known reflectance values provided by MicaSense. Eight VI maps were produced by using the index calculator of the Pix4D mapper. These VIs are listed in Table 3 and are commonly used for AGB and LAI estimation [39,40,41,42,43,44,45,46,47].
With ENVI 5.3 (Exelis Visual Information Solutions, Boulder, CO, USA), the non-sampling area (Figure 1) of each plot in one orthomosaic image was manually outlined as a “Region of Interest” to extract the average VI. The descriptive statistics of all VIs are show in Table 4.

2.5. AGB and LAI Retrieval Methods

To improve the applicability of the regression model, the data obtained from the two years of experiments were used to examine the relationships between remote sensing variables and AGB or LAI. Four models (SR, ANN, RF and LME) were used to quantify the relationship between remote sensing variables and AGB or LAI. Of these methods, SR is a parametric regression model and the others are non-parametric regression models. All analyses were respectively performed within three growth stage groups, that is, the whole season, pre-heading stages (stages before heading) and post-heading stages (stages after heading).

2.5.1. Baseline Retrieval Methods

In this study, three baseline retrieval methods for crop monitoring (SR, ANN and RF) were used for AGB and LAI retrieval. The statistical analyses for SR and ANN were performed using SPSS 25.0 software (SPSS, IBM, IL, USA) while RF was executed in R.3.2.0 (R Foundation for Statistical Computing, Vienna, Austria). Plots were created in GraphPad Prism 6.0 (GraphPad Software, San Diego, CA, USA).
SR models include both linear and nonlinear (exponential) regression models. The basic function forms of linear (Equation (2)) and exponential (Equation (3)) regressions are given by:
y = a 0 + a 1 x
y = b 0 e b 1 x
where the independent variable x represents the explanatory variable (VI), the dependent variable y represents the response variables (AGB and LAI) and parameters a0, a1, b0 and b1 are estimated by minimizing the least square error. The performance of various regression models is assessed by comparing their coefficient of determination (R2) (Equation (8)) and root mean square error (RMSE) (Equation (9)).
The ANN regression model is based on a gradient learning method, which can realize strong nonlinear mapping between input and output [19]. ANN contains a large number of processing elements (neurons), which are arranged in different layers in a network: an input layer, an output layer and one or more hidden layers [18]. In this study, the number of hidden layers was set to 1. The number of neurons was modified by repeating the setting. Via cross-validation, the coefficient of determination (R2) (Equation (8)) and root mean square error (RMSE) (Equation (9)) from test samples were compared. After comparing the values of R2 and RMSE, the most appropriate numbers were obtained. The scaled conjugate gradient was also selected as training algorithm. Figure 3 shows a schematic of the initial neural network model.
The RF model is derived from the classification tree algorithm and can be used for both classification or regression [48]. An RF model has two parameters: the number of decision trees (Ntree) and the minimum number of observations per tree leaf (mtry). In this research, the RF regression model used relevant parameters that were reported in prior studies, Ntree was set to 500 and mtry was set to 2 for the whole season and different stage groups [19,24].

2.5.2. Linear Mixed-effect Model

The LME model was also used for AGB and LAI retrieval. The LME model was executed using SPSS 25.0 software (SPSS) while plots were created using Graph-Pad Prism (GraphPad Software, San Diego, CA, USA). The LME incorporates two parameters: fixed and random effects [49]. The fixed effects are parameters that are associated with an entire population or with certain repeatable levels of experimental factors; the random effects are parameters associated with individual experimental units drawn at random from the population [30]. The form of the LME model is given by:
y = X β + Z u + ε
where y represents a N × 1 column vector, the response variable; X represents a N × p design matrix of the p predictor variables; β represents a p × 1 column vector of the fixed-effects regression coefficients; Z represents the N × q design matrix for q random effects (the random complement to the fixed X); u represents a q × 1 vector of the random effects (the random complement to the fixed β); and ε represents a N × 1 column vector of the residuals, part of which is not explained by the model, Xβ + Zu.
u ~ N ( 0 , G ) , ε ~ N ( 0 , R )
G = σ s 2 H ( ϕ )
R = τ 2 · I
where G represents the variance-covariance matrix of the random effects. H(·) is defined by the suitable correlation function f(h, ϕ), σ s 2 represents the partial sill, ϕ represents the range and h represents the lag or distance [50]. R represents a N × N positive definite variance-covariance matrix of ε. τ2 is called the nugget effect. I represents the identity matrix (diagonal matrix of 1s). ε is not correlated with the random effect u, that is, Cov(u, ε) = 0.
Simultaneous estimates of correlation parameters (i.e., σs, h, ϕ and τ) and fixed effect coefficients (i.e., β) were obtained by restricted (or residual) maximum likelihood estimation (REML) [50], to reflect the loss of degrees of freedom due to the estimation of the fixed effects coefficients [51]. For both AGB and LAI models, the reflectance of four spectral bands (green, red, red-edge and NIR) were set as fixed effects for the whole season and different stage groups. Random effects have different choices, including three individual factors: cultivar (C, which is a factor variable with two types), planting pattern (P, which is a factor variable with three types), growth stage (S, which is a factor variable with seven types) and their combinations (CP, CS, PS and CSP). The rice population structure is an important indicator for rice growth and rice with the same population structure is relatively homogeneous. These three individual factors (C, S and P) contribute strongly to the formation of rice population and were selected as candidates of random effects [52,53]. Moreover, with these random effects, more group combinations and dataset with greater variability were utilized to improve the robustness of the LAI/AGB models in this study.
With different random effects, Z and u have different dimensions. For instance, if cultivar and growth stage (CS) are set as random effects, the data will be broken down into 2 × 7 = 14 groups, where Z will be a N × 14 design matrix and u will be a 14 × 1 vector of the random effects. Optimal random effects were determined by comparing the RMSE values.

2.6. Comparison of Different Models

Comparisons of different models were achieved by evaluating their predictive capabilities, which were evaluated by their coefficient of determination (R2) (Equation (8)) and RMSE (Equation (9)) using a k-fold (k = 10) cross-validation procedure.
R 2 = i = 1 n ( x i x ¯ ) 2 ( y i y ¯ ) 2 i = 1 n ( x i x ¯ ) 2 i = 1 n ( y i y ¯ ) 2
RMSE = 1 n i = 1 n ( x i y i ) 2
where xi and yi represent the estimated and measured values (AGB or LAI), x ¯ and y ¯ represent the average estimated and measured values and n represents the sample number.

3. Results

3.1. Relationships between AGB and LAI with VIs Extracted from Multispectral Images

AGB and LAI are the major growth indicators for the monitoring of the rice growth status. Figure 4 shows the relationships between rice AGB and VIs that are generally used for biomass estimation; the best-fit form of the curve is an exponential regression. For the whole season, NDRE and DATT both performed best amongst all VIs and explained 68% of the variability in AGB (Figure 4b,g). For pre-heading stages, NDRE, CIRE and DATT achieved better performance (R2 > 0.70, RMSE < 2.29 t ha−1, Figure 4b,c,g) than other VIs (R2: 0.51–0.57, RMSE: 3.12–3.39 t ha−1). However, for post-heading stages, all selected VIs were weakly related to AGB with the highest R2 values of 0.25 and the lowest RMSE values of 3.49 t ha−1 (DATT).
Figure 5 shows the relationships between LAI and VIs that are commonly used for LAI estimation. The best curve form is also the exponential regression. For the whole season, NDRE, GNDVI and CIRE outperformed other VIs, with R2 values ranging from 0.72–0.74 and RMSE values ranging from 1.46–1.59 (Figure 5b,c,d). For pre-heading stages, NDRE performed best and explained 76% variability in LAI (Figure 5b). Other VIs achieved good performance with R2 values ranging from 0.66–0.74 and RMSE values ranging from 1.33–1.70 except for MTVI1 (Figure 5h). For post-heading stages, all selected VIs had weaker relationships with LAI compared to other stage groups, with highest R2 values of 0.56 and lowest RMSE values of 1.60.
VIs extracted from multispectral images explained the variability of AGB and LAI for the whole season and pre-heading stages, while the relationships between AGB and LAI with the VIs were relatively poor for post-heading stages.

3.2. Determination of Model Parameters for ANN, RF and LME Models

It is critical to identify appropriate model parameters with which to develop the monitoring model. In the ANN model, numbers from 3 to 30 neurons were attempted and the optimal parameter was obtained when R2 reached a maximum and the RMSE reached a minimum on test dataset via cross validation. The parameters for the final models (ANN and RF) are shown in Table 5.
Different random effect combinations and their RMSE values are shown in Figure 6. Optimal random effects were determined by comparing RMSE value results. For the LME model of AGB (Figure 6a), the CSP (i.e., the combination of cultivar, planting method and growth stage) resulted in the minimum RMSE for the whole season and for different stage groups. For the LME model of LAI (Figure 6b), the CSP combination resulted in minimum RMSE values for the whole season and different stage groups. As a result, the combination of cultivar, planting method and growth stage was set as random effects for both AGB and LAI models.

3.3. Comparative Analysis of Four Models Based on Predictive Capability

The LME model was applied to estimate both rice AGB and LAI and a comparative analysis between the LME model and the other three frequently-used models (including a parametric regression model (SR) and two non-parametric regression models (ANN and RF)) was conducted using k-fold (k = 10) cross-validation.
For AGB estimation, Figure 7 displays scatter diagrams of measured AGB values versus estimated values derived from SR (with the best performing VI), ANN, RF and LME models for whole season and different stage groups. For the whole season, SR produced the highest estimation accuracy using DATT, with R2 and RMSE values of 0.54 and 3.55 t ha−1, respectively (Figure 7a). ANN and RF outperformed SR with respective R2 values of 0.75 and 0.70 and RMSE values of 2.63 t ha−1 and 2.86 t ha−1 (Figure 7d,g). The LME model significantly improved estimation accuracy (R2 = 0.89 and RMSE = 1.75 t ha−1) (Figure 7j) and was superior to other models. For the pre-heading stages, SR achieved the highest estimation accuracy (R2 = 0.71 and RMSE = 2.10 t ha−1) using DATT (Figure 7b). Compared to SR, slight improvements were obtained by ANN (R2 = 0.79 and RMSE = 1.80 t ha−1) (Figure 7e) and RF (R2 = 0.73 and RMSE = 2.03 t ha−1) (Figure 7h). Moreover, the LME model achieved moderate improvements with R2 and RMSE values of 0.86 and 1.49 t ha1, respectively (Figure 7k). For the post-heading stages, SR had the highest estimation accuracy using DATT but remained low (R2 = 0.22 and RMSE = 3.49 t ha−1) (Figure 7c). In contrast, ANN and RF outperformed SR, with respective R2 values of 0.54 and 0.40 and RMSE values of 2.69 t ha−1 and 3.06 t ha−1 (Figure 7f,i). The LME model significantly improved the AGB estimation accuracy (R2 = 0.75 and RMSE = 1.97 t ha−1) (Figure 7l) compared to the other tested models. Therefore, the LME model is suggested as a promising model for improving AGB estimation for all growth stages.
For LAI estimation, Figure 8 shows the scatter diagrams for measured LAI values versus estimated values derived from SR (with the best performing VI), ANN, RF and LME models for the whole season and for different stage groups. For the whole season, SR achieved the highest estimation accuracy using NDRE, with R2 and RMSE values of 0.66 and 1.45, respectively (Figure 8a). In contrast, ANN and RF slightly increased estimation accuracy, with respective R2 values of 0.74 and 1.27, RMSE values of 1.27 and 1.36 (Figure 8d,g). The LME model yielded more accurate estimation results than the other models (R2 = 0.79 and RMSE = 1.15) (Figure 8j). For pre-heading stages, SR achieved the highest estimation accuracy (R2 = 0.73 and RMSE = 1.25) using NDRE (Figure 8b). The accuracies of ANN and RF were approximately equal to that of SR, with respective R2 values of 0.75 and 0.74 and RMSE values of 1.19 and 1.22 (Figure 8e,h). In contrast, the LME model outperformed the other models (R2 = 0.81 and RMSE = 1.04) (Figure 8k). For post-heading stages, SR achieved the highest estimation accuracy using CIRE, with respective R2 and RMSE values of 0.53 and 1.59 (Figure 8c). ANN and RF slightly improved the estimation accuracy, with respective R2 values of 0.58 and 0.56 and RMSE values of 1.49 and 1.53 (Figure 8f,i). The LME model yielded the most accurate estimation across all models (R2 = 0.76 and RMSE = 1.16) (Figure 8l). Therefore, the LME model performed better in estimating rice LAI.
In addition, although the LME model improved the estimation accuracy of both AGB and LAI, their degree of improvement differed. For AGB estimation, compared to SR (Figure 7a–c), the R2 of the LME model increased by 0.35 for the whole season, by 0.15 for the pre-heading stages and by 0.53 for the post-heading stages, while the corresponding RMSE values decreased by 1.8 t ha−1, 0.61 t ha−1 and 1.52 t ha−1, respectively (Figure 7j–l). For LAI estimation, compared to SR (Figure 8a–c), the LME model R2 increased by 0.13 for the whole season, by 0.08 for the pre-heading stages and by 0.23 for the post-heading stages; corresponding RMSE values decreased by 0.30, 0.21 and 0.43, respectively (Figure 8j–l). Consequently, the LME model may be more suitable for rice AGB estimation.

3.4. Comparison of LME Models with Different Random Effects

It is necessary to analyze the results for all combinations of random effects to evaluate the predictive capability within the groups of LME models. Practical application should be expanded on; the results show that the method can be used to make predictions within a single known group as well as across multiple different groups. Groupings do not have to be CSP and it is not the optimal choice for the random effects. Furthermore, similar results were obtained from the LME model of AGB (Figure 9 and Figure 10) and that of LAI (Figure 11 and Figure 12). The analysis was conducted based on the LME model of the AGB.
Figure 9 shows the scatter diagrams for measured AGB values versus estimated values derived from LME models, which were built with different random effects. From the overall performance of modelling, CSP (the combination of cultivar, growth stage and planting pattern) performed best (R2 = 0.89, RMSE = 1.75 t ha1) (Figure 9g). Models that included random effects of growth stage (S) obtained higher prediction accuracy (R2: 0.84–0.89, RMSE: 1.75–2.12 t ha1) (Figure 9c,e,f,g) than other models. In particular, the LME model only used growth stage as random effect and obtained satisfactory estimation accuracy (R2 = 0.84, RMSE = 2.12 t ha1) (Figure 9c). Therefore, growth stage could be an important factor for the rice LME model.
In addition, Figure 9 shows the modelling performance within the groups of LME models. The results indicate that models, which were segmented into more groups (number of groups ≥ 7) obtained higher prediction accuracy (R2: 0.84–0.89, RMSE: 1.75–2.12 t ha−1) (Figure 9c,e,f,g). In contrast, models with fewer groups (number of groups < 7) performed worse (R2: 0.72–0.75, RMSE: 2.60–2.77 t ha−1) (Figure 9a,b,d). This indicates that segmentation of the data inherently improved the results because it learned the mean of the segment; consequently, adding the number of groups could increase prediction accuracy. As shown in Figure 9 and Figure 10, the LME models using C, P or CP as random effects achieved a similar performance within groups to overall model performance (C: R2 = 0.73, RMSE = 2.72 t ha−1; P: R2 = 0.72, RMSE = 2.77 t ha−1; CP: R2 = 0.75, RMSE = 2.60 t ha−1), with average R2 of 0.70, 0.72 and 0.71 and average RMSE of 2.72 t ha−1, 2.77 t ha−1 and 2.60 t ha−1, respectively (Figure 9a,b,d, Figure 10a,b). These models have fewer groups and the highest number of groups is only six (CP). For LME models with more segments (i.e., the models using S, CS and PS as random effects), the model performance within groups was poorer than the overall model performance (S: R2 = 0.84, RMSE = 2.12 t ha−1; CS: R2 = 0.86, RMSE = 1.93 t ha−1; PS: R2 = 0.85, RMSE = 2.04 t ha−1), with average R2 of 0.61, 0.60 and 0.61 and average RMSE of 1.82 t ha−1, 1.66 t ha−1 and 1.88 t ha−1, respectively (Figure 9c,e,f, Figure 10a,b). Still, these models successfully yielded predictions within the groups, since almost all R2 values of groups ranged from 0.4–0.9 (average R2 > 0.60) (Figure 10a,b). This indicated that the LME model offered advantages beyond simply learning the mean of the segment. With regard to the LME model using CSP, the R2 and RMSE within the groups fluctuated greatly, with R2: 0.1–0.87, RMSE: 0.38–2.86 t ha−1 (Figure 10a). The result could be ascribed to the fact that the data were segmented into too many groups (number of groups = 36) when using CSP as random effects. Therefore, the number of points per group was very low (i.e., 12–24) and the modelling performance within the groups suffered from randomness and strong uncertainty. Even though the LME model (using CSP) achieved good performance over all data, this approach would lose statistical significance and simply yield the mean for the group. Consequently, for the practical application of the LME model, the CSP may be not suitable as the random effects given model generalizability. LME models with fewer segments might be promising alternatives, such as the models using S, CS or PS.

4. Discussion

4.1. Advantages of Fixed-Wing UAVs

A low-altitude UAV platform is an affordable and precise tool for the mapping of crop traits and can meet the central requirements of spatial, spectral and temporal resolutions [10]. Among various UAVs, the multi-rotor UAV has been increasingly employed in recent years due to its high stability, superior image quality and good controllability (easy take-off and landing) [17]. Nevertheless, high stability can be a double-edged sword: it provides high quality images but it also limits the multi-rotor UAV flight speed and duration [17]. As an illustration, a multi-rotor UAV required approximately 10 min to cover 1 ha (30–50 m flight altitude) for dynamic wheat NDVI monitoring [9]. Zhang et al. [54] monitored field crop conditions with a multi-rotor UAV (Aeryon Labs Inc., Waterloo, Canada), which has a maximum flight duration of 25 min and can cover close to 10 ha (120 m flight altitude) per battery charge. Compared to a multi-rotor UAV for crop monitoring, fixed-wing UAVs are competitive because they are more efficient and can cover larger areas [17]. For example, a fixed-wing UAV covered an area of 148 ha within 45 min and achieved a total flight duration of up to 60 min [55]. The fixed-wing UAV used in this study was able to cover about 80 ha with a maximum duration of 55 min (80 m flight altitude). A comparison of the flight efficiency for both types of UAVs is shown in Table 6.
This study used an advanced fixed-wing UAV with a compact multispectral sensor Parrot Sequoia to monitor the crop growth status. The fixed-wing has a good flight control system and creates a relatively stable flight attitude. It can also withstand strong wind speeds of up to 12 m s−1. With regard to the SR (most commonly used) validation results, a moderate result (R2 = 0.54 and RMSE = 3.55 t ha−1 from DATT) was obtained for AGB for the whole season and a better result was obtained for LAI for the whole season, with respective R2 and RMSE values of 0.66 and 1.45. Compared to the estimation models based on multi-rotor UAVs (e.g., the best AGB results acquired by best performing VI (R2 = 0.55, RMSE = 2.77 t ha−1) by Zheng et al. [57] and the best LAI model produced by a three-band vegetation index modified triangular vegetation index (MTVI2) with respective R2 and relative root mean squared error (RRMSE) values of 0.80 and 24% reported by Yao et al. [11]), the results obtained with the fixed-wing UAV in this study were relatively reliable.

4.2. Relationship between Growth Parameters and Vegetation Indices

SR has been widely used to explore the relationship between crop growth parameters and VIs, which resulted in the development of a large number of multispectral VIs [11,58,59]. In this study, both for the whole season and pre-heading stages, most VIs that consisted of the NIR and the red edge bands outperformed the other indices both for AGB (e.g., NDRE, CIRE and DATT) and LAI (e.g., NDRE) estimation, which was consistent with previous studies by Li et al. [58] and Zheng et al. [13]. This might be because the canopy reflectance is largely dominated by canopy-structure-related parameters (e.g., LAI and biomass) during the early growth stages. VIs that consist of the NIR and the red edge bands are also sensitive to the canopy structure and therefore performed better than other models [13,60,61]. However, for post-heading stages, most of the selected VIs were weakly related to the growth parameters, especially for AGB (R2 < 0.30, RMSE > 3.49 t ha1). This issue was also encountered in previous studies [14,57] and may be caused by the fact that the NIR and red edge had poor sensitivity to the large biomass during the late stages of crop growth [14,60]. Furthermore, other factors interfered, such as senescent leaves and panicles [57].
Many approaches have been proposed that improve the estimation accuracy for post-heading stages, including the application of three-dimensional information coupled with crop height and hyperspectral information [14] and the combination of texture and spectral information from a UAV image to construct an AGB estimation model [57]. In addition, several studies have also tried to mine information from hyperspectral data: Yao et al. [62] applied continuous wavelet transform to hyperspectral data to improve the estimation accuracy of canopy leaf biomass. However, the models need additional information for these methods and data processing can be tedious and time-consuming (e.g., hyperspectral data). This study applied the LME model to improve the estimation accuracy for post-heading stages. For AGB estimation, the R2 of the LME model increased by 0.53 compared to SR, while corresponding RMSE values decreased by 1.52 t ha1. For LAI estimation, the R2 of LME model increased by 0.23 compared to SR, while corresponding RMSE values decreased by 0.43. The results indicated the LME model as an efficient approach to improve the estimation accuracy for post-heading stages.

4.3. Advantages of the LME Model for Estimating Rice Growth Parameters

As a promising method, the mixed-effect model has been extensively applied for forest remote sensing [31,32,33]. Compared to other models, the mixed-effect model can better deal with data that are hierarchically structured and grouped [31,32,63]. This model could explain these complex and independent data by breaking down the regression into fixed effects and random effects [49]. The random effects are able to model the deviations from the global relationship within each group [30]. Furthermore, several common types of mixed-effect models exist, including linear mixed-effect (LME) models, generalized linear mixed-effect (GLME) models and non-linear mixed-effect (NLME) models [32,33,64]. Of these types, the LME model is the most popular since it has a better generalization capability; therefore, it was selected for this study [63]. To determine whether the LME model is able to accurately estimate crop growth parameters, the LME model was tested in this study. Furthermore, a comparative analysis of the predictive capability was performed between the LME model and the other three baseline retrieval methods (SR, ANN and RF).
For AGB estimation, the LME model outperformed all other models (SR, ANN and RF) both for the whole season and for different stage groups. For the whole season, a significant improvement was recorded (R2 = 0.89 and RMSE = 1.75 t ha−1). Compared to the results of coupling crop height with hyperspectral information (R2 = 0.74 and RMSE = 1.20 t ha−1) by Yue et al. [14] and combining texture and spectral information from UAV images (R2 = 0.78 and RMSE = 1.84 t ha−1) by Zheng et al. [57], the LME model achieved fairly satisfactory performance. This could be explained by the fact that the growth parameters (AGB or LAI) were not completely independent because the growth parameters might aggregate within different experimental factors (e.g., the random terms in this study: cultivar, planting method and growth stage); thus, these variables were more or less similar. The LME model resolved the data aggregation issue, while traditional retrieval methods did not. Forest research has faced the same challenge because the relationship between volume and biomass with LiDAR metrics differs by stands; therefore, the mixed-effect model is preferable to other models because it addresses the hierarchical nature of forest data by incorporating plot or stand level variability [32]. For each stage group, improvements were moderate for the pre-heading stages (R2 = 0.86 and RMSE = 1.49 t ha−1) and significant for the post-heading stages (R2 = 0.75 and RMSE = 1.97 t ha−1). This may be a result of AGB consisting of leaf, stem and panicle biomass after the heading stage. The biomass differences between different organs are more significant, which leads to a more obvious hierarchical nature and aggregation of biological data. This further supports the advantage of the LME model in dealing with hierarchically structured data [63].
With regard to LAI estimation, the ANN and RF regression models showed limited improvements for all stages compared to the SR (whole season: R2 = 0.66 and RMSE = 1.45; pre-heading stages: R2 = 0.73 and RMSE = 1.25; post-heading stages: R2 = 0.53 and RMSE = 1.59). Compared to other models, the LME model achieved a better performance for the whole season (R2 = 0.79 and RMSE = 1.15) and pre-heading stages (R2 = 0.81 and RMSE = 1.04) and a significant improvement was recorded found for the post-heading stages (R2 = 0.76 and RMSE = 1.16). However, the improvements of LAI estimation were not as significant as those of AGB estimation for the post-heading stages. It might be because AGB data aggregation is more palpable than LAI under these random effects. Thus, the LME model was more appropriate for crop AGB estimation.
These results showed that the LME model performs well for rice growth parameters estimation; however, the LME models with different random effects still need to be compared to apply them to practical agricultural production. As shown with the comparison of linear mixed-effect models with different random effects, the combination of cultivar, planting pattern and growth stage performed best (R2 = 0.89, RMSE = 1.75 t ha−1). However, further analysis suggested that part of the reason for its superiority is that it is segmented into most groups and thus benefits from obtaining the mean of the group. The models that include the random effect of the growth stage also obtained better prediction accuracy compared to other models. Especially, the LME model that uses growth stage as random effect obtained satisfactory estimation accuracy (R2 = 0.84, RMSE = 2.12 t ha−1), which indicated the growth stage as an important factor for the rice estimation model. In the practical application, the cultivar, planting pattern and growth stage of rice need to be obtained prior to using this model. China established a complete service system for agricultural technology extension and it is easy to obtain crop planting information. For other countries and regions in the world, these data could be collected in different ways. In the USA, crop statistics can be obtained from the Cropland Data Layer (CDL) products, which are produced by the National Agricultural Statistics Service (NASS) of the US Department of Agriculture (USDA) [65]. Furthermore, Farm Service Agency-Common Land Units (FSA-CLU) can also provide such data [66]. In Europe, the data can be generated by the European Union Global Monitoring of Food Security (GMFS) program and JRC’s Monitoring Agricultural ResourceS (MARS) action of the European Commission in Ispra (Italy) [67]. In other areas, the crop statistics can be obtained from the Global Information and Early Warning System (GIEWS) of the FAO, which continually receives economic, political and agricultural information from a wide variety of sources (UN organizations, 115 governments, four regional organizations and 61 non-governmental organizations) [66]. Even if the planting information is hard to acquire for a particular region, the rice growth stage can easily be obtained via field observation. In such a case, the LME model, which uses growth stage as random effect, would be a feasible alternative, since the model achieves a sufficient estimation accuracy. The model provides technical support for the building estimation model from field to regional scales in the future.

5. Conclusions

This study explored the potential for the estimation of rice AGB and LAI with a fixed-wing UAV, using the LME model and three baseline retrieval methods (SR, ANN and RF). The results of SR modelling showed that several NIR-based and red edge-based VIs had preferable relationships with growth parameters (AGB and LAI) both for the whole season and pre-heading stages, while all selected VIs were weakly related to growth parameters for post-heading stages. The LME model outperformed the other models (SR, ANN and RF), with the highest R2 and lowest RMSE for both AGB and LAI estimation. In particular, the LME model significantly improved the estimation accuracy (AGB: R2 = 0.75, RMSE = 1.97 t ha−1; LAI: R2 = 0.76, RMSE = 1.16) for post-heading stages. In summary, this study demonstrates the potential utility of using a fixed-wing UAV combined with the LME model to estimate rice growth parameters. The findings can further serve as a useful reference and technical support for precision farming management and decision-making over large-scale farmland.

Author Contributions

Y.W., K.Z., Q.C. and X.L. conceived and designed the experiments. Y.W., K.Z. and C.T. performed the experiments with support by Y.T., Y.W. and X.L. analyzed the data and wrote the original manuscript, W.C. and Y.Z. provided advice and revised the manuscript. All of the authors have read and approved the final manuscript submitted to the editor.

Funding

The work was funded by the National Key Research and Development Program of China (2016YFD0200602; 2016YFD0300604), the earmarked fund for Jiangsu Agricultural Industry Technology System (JATS(2018)290; JATS(2018)082), the 111 project (B16026) and Jiangsu Province Key Technologies R&D Program (BE2016375).

Acknowledgments

We would like to thank undergraduate student Tai An, Rui Zhang and Ziyi Wang for assistance with field data collection, Wenhui Wang, Xiao Zhang and Penglei Li for their help with sample processing.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Maimaitijiang, M.; Ghulam, A.; Sidike, P.; Hartling, S.; Maimaitiyiming, M.; Peterson, K.; Shavers, E.; Fishman, J.; Peterson, J.; Kadam, S.; et al. Unmanned Aerial System (UAS)-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine. ISPRS J. Photogramm. Remote Sens. 2017, 134, 43–58. [Google Scholar] [CrossRef]
  2. Wei, C.; Huang, J.; Mansaray, L.; Li, Z.; Liu, W.; Han, J. Estimation and Mapping of Winter Oilseed Rape LAI from High Spatial Resolution Satellite Data Based on a Hybrid Method. Remote Sens. 2017, 9, 488. [Google Scholar] [CrossRef]
  3. Ballesteros, R.; Ortega, J.F.; Hernandez, D.; Moreno, M.A. Onion biomass monitoring using UAV-based RGB imaging. Precis. Agric. 2018, 19, 840–857. [Google Scholar] [CrossRef]
  4. Gao, S.; Niu, Z.; Huang, N.; Hou, X. Estimating the Leaf Area Index, height and biomass of maize using HJ-1 and RADARSAT-2. Int. J. Appl. Earth. Obs. 2013, 24, 1–8. [Google Scholar] [CrossRef]
  5. Bahn, M.; Rodeghiero, M.; Anderson-Dunn, M.; Dore, S.; Gimeno, C.; Drösler, M.; Williams, M.; Ammann, C.; Berninger, F.; Flechard, C.; et al. Soil Respiration in European Grasslands in Relation to Climate and Assimilate Supply. Ecosystems 2008, 11, 1352–1367. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  6. Arora, V.K.; Boer, G.J. A parameterization of leaf phenology for the terrestrial ecosystem component of climate models. Glob. Change Biol. 2005, 11, 39–59. [Google Scholar] [CrossRef]
  7. Drusch, M.; Del Bello, U.; Carlier, S.; Colin, O.; Fernandez, V.; Gascon, F.; Hoersch, B.; Isola, C.; Laberinti, P.; Martimort, P.; et al. Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services. Remote Sens. Environ. 2012, 120, 25–36. [Google Scholar] [CrossRef]
  8. Yao, Y.; Liu, Q.; Liu, Q.; Li, X. LAI retrieval and uncertainty evaluations for typical row-planted crops at different growth stages. Remote Sens. Environ. 2008, 112, 94–106. [Google Scholar] [CrossRef]
  9. Duan, T.; Chapman, S.C.; Guo, Y.; Zheng, B. Dynamic monitoring of NDVI in wheat agronomy and breeding trials using an unmanned aerial vehicle. Field Crop Res. 2017, 210, 71–80. [Google Scholar] [CrossRef]
  10. Yang, G.; Liu, J.; Zhao, C.; Li, Z.; Huang, Y.; Yu, H.; Xu, B.; Yang, X.; Zhu, D.; Zhang, X.; et al. Unmanned Aerial Vehicle Remote Sensing for Field-Based Crop Phenotyping: Current Status and Perspectives. Front. Plant Sci. 2017, 8, 1111. [Google Scholar] [CrossRef]
  11. Yao, X.; Wang, N.; Liu, Y.; Cheng, T.; Tian, Y.; Chen, Q.; Zhu, Y. Estimation of Wheat LAI at Middle to High Levels Using Unmanned Aerial Vehicle Narrowband Multispectral Imagery. Remote Sens. Basel 2017, 9, 1304. [Google Scholar] [CrossRef]
  12. Zhang, C.; Kovacs, J.M. The application of small unmanned aerial systems for precision agriculture: A review. Precis. Agric. 2012, 13, 693–712. [Google Scholar] [CrossRef]
  13. Zheng, H.; Cheng, T.; Li, D.; Yao, X.; Tian, Y.; Cao, W.; Zhu, Y. Combining Unmanned Aerial Vehicle (UAV)-Based Multispectral Imagery and Ground-Based Hyperspectral Data for Plant Nitrogen Concentration Estimation in Rice. Front. Plant Sci. 2018, 9, 936. [Google Scholar] [CrossRef] [PubMed]
  14. Yue, J.; Yang, G.; Li, C.; Li, Z.; Wang, Y.; Feng, H.; Xu, B. Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models. Remote Sens. Basel 2017, 9, 708. [Google Scholar] [CrossRef]
  15. Devia, C.A.; Rojas, J.P.; Petro, E.; Martinez, C.; Mondragon, I.F.; Patino, D.; Rebolledo, M.C.; Colorado, J. High-Throughput Biomass Estimation in Rice Crops Using UAV Multispectral Imagery. J. Intell. Robot Syst. 2019, 1–17. [Google Scholar] [CrossRef]
  16. Duan, B.; Fang, S.; Zhu, R.; Wu, X.; Wang, S.; Gong, Y.; Peng, Y. Remote Estimation of Rice Yield with Unmanned Aerial Vehicle (UAV) Data and Spectral Mixture Analysis. Front. Plant Sci. 2019, 10, 204. [Google Scholar] [CrossRef] [PubMed]
  17. Sankaran, S.; Khot, L.R.; Espinoza, C.Z.; Jarolmasjed, S.; Sathuvalli, V.R.; Vandemark, G.J.; Miklas, P.N.; Carter, A.H.; Pumphrey, M.O.; Knowles, N.R.; et al. Low-altitude, high-resolution aerial imaging systems for row and field crop phenotyping: A review. Eur. J. Agron. 2015, 70, 112–123. [Google Scholar] [CrossRef]
  18. Yang, S.; Feng, Q.; Liang, T.; Liu, B.; Zhang, W.; Xie, H. Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region. Remote Sens. Environ. 2018, 204, 448–455. [Google Scholar] [CrossRef]
  19. Yuan, H.; Yang, G.; Li, C.; Wang, Y.; Liu, J.; Yu, H.; Feng, H.; Xu, B.; Zhao, X.; Yang, X. Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN and SVM Regression Models. Remote Sens. Basel 2017, 9, 309. [Google Scholar] [CrossRef]
  20. Wang, L.; Zhou, X.; Zhu, X.; Dong, Z.; Guo, W. Estimation of biomass in wheat using random forest regression algorithm and remote sensing data. Crop J. 2016, 4, 212–219. [Google Scholar] [CrossRef] [Green Version]
  21. Li, H.; Chen, Z.; Jiang, Z.; Wu, W.; Ren, J.; Liu, B.; Tuya, H. Comparative analysis of GF-1, HJ-1 and Landsat-8 data for estimating the leaf area index of winter wheat. J. Integr. Agric. 2017, 16, 266–285. [Google Scholar] [CrossRef]
  22. Huang, Z.; Turner, B.J.; Dury, S.J.; Wallis, I.R.; Foley, W.J. Estimating foliage nitrogen concentration from HYMAP data using continuum removal analysis. Remote Sens. Environ. 2004, 93, 18–29. [Google Scholar] [CrossRef]
  23. Shen, W.; Li, M.; Huang, C.; Tao, X.; Wei, A. Annual forest aboveground biomass changes mapped using ICESat/GLAS measurements, historical inventory data and time-series optical and radar imagery for Guangdong province, China. Agric. For. Meteorol. 2018, 259, 23–38. [Google Scholar] [CrossRef]
  24. Li, Z.; Wang, J.; Tang, H.; Huang, C.; Yang, F.; Chen, B.; Wang, X.; Xin, X.; Ge, Y. Predicting Grassland Leaf Area Index in the Meadow Steppes of Northern China: A Comparative Study of Regression Approaches and Hybrid Geostatistical Methods. Remote Sens. Basel 2016, 8, 632. [Google Scholar] [CrossRef]
  25. Näsi, R.; Viljanen, N.; Kaivosoja, J.; Alhonoja, K.; Hakala, T.; Markelin, L.; Honkavaara, E. Estimating Biomass and Nitrogen Amount of Barley and Grass Using UAV and Aircraft Based Spectral and Photogrammetric 3D Features. Remote Sens. Basel 2018, 10, 1082. [Google Scholar] [Green Version]
  26. Corti, M.; Cavalli, D.; Cabassi, G.; Marino Gallina, P.; Bechini, L. Does remote and proximal optical sensing successfully estimate maize variables? A review. Eur. J. Agron. 2018, 99, 37–50. [Google Scholar] [CrossRef]
  27. Kang, Y.; Özdoğan, M.; Zipper, S.; Román, M.; Walker, J.; Hong, S.; Marshall, M.; Magliulo, V.; Moreno, J.; Alonso, L.; et al. How Universal Is the Relationship between Remotely Sensed Vegetation Indices and Crop Leaf Area Index? A Global Assessment. Remote Sens. Basel 2016, 8, 597. [Google Scholar] [CrossRef]
  28. Tremblay, N.; Wang, Z.; Ma, B.; Belec, C.; Vigneault, P. A comparison of crop data measured by two commercial sensors for variable-rate nitrogen application. Precis. Agric. 2009, 10, 145–161. [Google Scholar] [CrossRef]
  29. Shaver, T.M.; Khosla, R.; Westfall, D.G. Evaluation of two crop canopy sensors for nitrogen variability determination in irrigated maize. Precis. Agric. 2011, 12, 892–904. [Google Scholar] [CrossRef]
  30. Pinheiro, J.; Bates, D. Mixed-Effects Models in S and S-PLUS; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2006. [Google Scholar]
  31. Zuur, A.F.; Ieno, E.N.; Walker, N.J.; Saveliev, A.A.; Smith, G.M. Mixed Effects Models and Extensions in Ecology with R; Springer: New York, NY, USA, 2009. [Google Scholar]
  32. Poudel, K.; Flewelling, J.; Temesgen, H. Predicting Volume and Biomass Change from Multi-Temporal Lidar Sampling and Remeasured Field Inventory Data in Panther Creek Watershed, Oregon, USA. Forests 2018, 9, 28. [Google Scholar] [CrossRef]
  33. Chen, D.; Huang, X.; Zhang, S.; Sun, X. Biomass Modeling of Larch (Larix spp.) Plantations in China Based on the Mixed Model, Dummy Variable Model and Bayesian Hierarchical Model. Forests 2017, 8, 268. [Google Scholar] [CrossRef]
  34. Liu, X.; Cao, Q.; Yuan, Z.; Liu, X.; Wang, X.; Tian, Y.; Cao, W.; Zhu, Y. Leaf area index based nitrogen diagnosis in irrigated lowland rice. J. Integr. Agric. 2018, 17, 111–121. [Google Scholar] [CrossRef] [Green Version]
  35. Zhang, K.; Ge, X.; Shen, P.; Li, W.; Liu, X.; Cao, Q.; Zhu, Y.; Cao, W.; Tian, Y. Predicting Rice Grain Yield Based on Dynamic Changes in Vegetation Indexes during Early to Mid-Growth Stages. Remote Sens. Basel 2019, 11, 387. [Google Scholar] [CrossRef]
  36. Chianucci, F.; Disperati, L.; Guzzi, D.; Bianchini, D.; Nardino, V.; Lastri, C.; Rindinella, A.; Corona, P. Estimation of canopy attributes in beech forests using true colour digital images from a small fixed-wing UAV. Int. J. Appl. Earth Obs. 2016, 47, 60–68. [Google Scholar] [CrossRef] [Green Version]
  37. Han, L.; Yang, G.; Dai, H.; Xu, B.; Yang, H.; Feng, H.; Li, Z.; Yang, X. Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data. Plant Methods 2019, 15, 10. [Google Scholar] [CrossRef] [PubMed]
  38. Hassan, M.; Yang, M.; Rasheed, A.; Jin, X.; Xia, X.; Xiao, Y.; He, Z. Time-Series Multispectral Indices from Unmanned Aerial Vehicle Imagery Reveal Senescence Rate in Bread Wheat. Remote Sens. Basel 2018, 10, 809. [Google Scholar] [CrossRef]
  39. Rouse, J.W.; Haas, R.H.; Schell, J.A.; Deering, D.W. Monitoring vegetation systems in the great plains with ERTS. In Third Earth Resources Technology Satellite-1 Symposium-Volume I: Technical Presentation; NASA SP-351; NASA: Washington, DC, USA, 1974. [Google Scholar]
  40. Gitelson, A.; Merzlyak, M.N. Quantitative estimation of chlorophyll-a using reflectance spectra: Experiments with autumn chestnut and maple leaves. J. Photochem. Photobiol. B Biol. 1994, 22, 247–252. [Google Scholar] [CrossRef]
  41. Gitelson, A.A. Remote estimation of canopy chlorophyll content in crops. Geophys. Res. Lett. 2005, 32, 1–4. [Google Scholar] [CrossRef]
  42. Qi, J.; Chehbouni, A.; Huete, A.R.; Kerr, Y.H.; Sorooshian, S.S. A modified soil adjusted vegetation index. Remote Sens. Environ. 1994, 48, 119–126. [Google Scholar] [CrossRef]
  43. Rondeaux, G.; Steven, M.; Baret, F. Optimization of soil-adjusted vegetation indices. Remote Sens. Environ. 1996, 55, 95–107. [Google Scholar] [CrossRef]
  44. Sankaran, S.; Mishra, A.; Ehsani, R.; Davis, C. A review of advanced techniques for detecting plant diseases. Comput. Electron. Agric. 2010, 72, 1–13. [Google Scholar] [CrossRef]
  45. Haboudane, D. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sens. Environ. 2004, 90, 337–352. [Google Scholar] [CrossRef]
  46. Datt, B. Visible/near infrared reflectance and chlorophyll content in Eucalyptus leaves. INT J. Remote Sens. 2010, 20, 2741–2759. [Google Scholar] [CrossRef]
  47. Gitelson, A.A.; Kaufman, Y.J.; Merzlyak, M.N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sens. Environ. 1996, 58, 289–298. [Google Scholar] [CrossRef]
  48. Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
  49. Bennington, C.C.; Thayne, W.V. Use and Misuse of Mixed Model Analysis of Variance in Ecological Studies. Ecology 1994, 75, 717–722. [Google Scholar] [CrossRef]
  50. Pollice, A.; Bilancia, M. Kriging with mixed effects models. Statistica 2002, 62, 405–429. [Google Scholar]
  51. Cressie, N. Statistics for spatial data. Terra Nova 1992, 4, 613–617. [Google Scholar] [CrossRef]
  52. Liu, H.J.; Zheng, J.C.; Chen, L.G.; Zhou, W. Effects of different planting modes on the growth and development characteristics of rice. Chin. J. Ecol. 2013, 32, 2326–2331. [Google Scholar]
  53. Yan, D.; Zhu, Y.; Wang, S.; Cao, W. A quantitative knowledge-based model for designing suitable growth dynamics in rice. Plant Prod. Sci. 2006, 9, 93–105. [Google Scholar] [CrossRef]
  54. Zhang, C.; Walters, D.; Kovacs, J.M. Applications of Low Altitude Remote Sensing in Agriculture upon Farmers’ Requests—A Case Study in Northeastern Ontario, Canada. PLoS ONE 2014, 9, e112894. [Google Scholar] [CrossRef] [PubMed]
  55. Zarco-Tejada, P.J.; Diaz-Varela, R.; Angileri, V.; Loudjani, P. Tree height quantification using very high resolution imagery acquired from an unmanned aerial vehicle (UAV) and automatic 3D photo-reconstruction methods. Eur. J. Agron. 2014, 55, 89–99. [Google Scholar] [CrossRef]
  56. Vivoni, E.R.; Rango, A.; Anderson, C.A.; Pierini, N.A.; Schreiner-McGraw, A.P.; Saripalli, S.; Laliberte, A.S. Ecohydrology with unmanned aerial vehicles. Ecosphere 2014, 5, 1–14. [Google Scholar] [CrossRef]
  57. Zheng, H.; Cheng, T.; Zhou, M.; Li, D.; Yao, X.; Tian, Y.; Cao, W.; Zhu, Y. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery. Precis. Agric. 2018, 1–19. [Google Scholar] [CrossRef]
  58. Li, S.; Ding, X.; Kuang, Q.; Ata-UI-Karim, S.T.; Cheng, T.; Liu, X.; Tian, Y.; Zhu, Y.; Cao, W.; Cao, Q. Potential of UAV-Based Active Sensing for Monitoring Rice Leaf Nitrogen Status. Front. Plant Sci. 2018, 9, 1834. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  59. Liu, X.; Ferguson, R.; Zheng, H.; Cao, Q.; Tian, Y.; Cao, W.; Zhu, Y. Using an Active-Optical Sensor to Develop an Optimal NDVI Dynamic Model for High-Yield Rice Production (Yangtze, China). Sensors Basel 2017, 17, 672. [Google Scholar] [CrossRef]
  60. Cheng, T.; Song, R.; Li, D.; Zhou, K.; Zheng, H.; Yao, X.; Tian, Y.; Cao, W.; Zhu, Y. Spectroscopic Estimation of Biomass in Canopy Components of Paddy Rice Using Dry Matter and Chlorophyll Indices. Remote Sens. Basel 2017, 9, 319. [Google Scholar] [CrossRef]
  61. Knipling, E.B. Physical and physiological basis for the reflectance of visible and near-infrared radiation from vegetation. Remote Sens. Environ. 1970, 1, 155–159. [Google Scholar] [CrossRef]
  62. Yao, X.; Si, H.; Cheng, T.; Jia, M.; Chen, Q.; Tian, Y.; Zhu, Y.; Cao, W.; Chen, C.; Cai, J.; et al. Hyperspectral Estimation of Canopy Leaf Biomass Phenotype per Ground Area Using a Continuous Wavelet Analysis in Wheat. Front. Plant Sci. 2018, 9, 1360. [Google Scholar] [CrossRef] [Green Version]
  63. Goldstein, H. Multilevel Statistical Models; John Wiley & Sons: Hoboken, NJ, USA, 2011. [Google Scholar]
  64. Rigling, A.; Bigler, C.; Eilmann, B.; Feldmeyer-Christe, E.; Gimmi, U.; Ginzler, C. Driving factors of a vegetation shift from Scots pine to pubescent oak in dry Alpine forests. Glob. Change Biol. 2013, 19, 229–240. [Google Scholar] [CrossRef]
  65. Boryan, C.; Yang, Z.; Mueller, R.; Craig, M. Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program. Geocarto Int. 2011, 26, 341–358. [Google Scholar] [CrossRef]
  66. Gallego, J.; Carfagna, E.; Baruth, B. Accuracy, objectivity and efficiency of remote sensing for agricultural statistics. In Agricultural Survey Methods; John Wiley & Sons, Ltd.: Hoboken, NJ, USA, 2010; pp. 193–211. [Google Scholar]
  67. Atzberger, C. Advances in remote sensing of agriculture: Context description, existing operational monitoring systems and major information needs. Remote Sens. Basel 2013, 5, 949–981. [Google Scholar] [CrossRef]
Figure 1. Study site: the rice experiment was conducted at the Taizhou Experimental Station in Jiangsu Province of China in 2017.
Figure 1. Study site: the rice experiment was conducted at the Taizhou Experimental Station in Jiangsu Province of China in 2017.
Remotesensing 11 01371 g001
Figure 2. Unmanned aerial vehicle (UAV) platform (eBee SQ) and sensors used in this study: (a) Front of the UAV; (b) sunshine sensor; (c) back of the UAV; (d) multispectral camera; (e) truncated images of four magnified orthomosaic images generated at the stem elongation stage.
Figure 2. Unmanned aerial vehicle (UAV) platform (eBee SQ) and sensors used in this study: (a) Front of the UAV; (b) sunshine sensor; (c) back of the UAV; (d) multispectral camera; (e) truncated images of four magnified orthomosaic images generated at the stem elongation stage.
Remotesensing 11 01371 g002
Figure 3. Schematic of the initial neural network model.
Figure 3. Schematic of the initial neural network model.
Remotesensing 11 01371 g003
Figure 4. Aboveground biomass (t ha−1) plotted against vegetation indices: (a) NDVI; (b) NDRE; (c) CIRE; (d) MSAVI; (e) OSAVI; (f) MCARI1; (g) DATT; (h) MTVI2. WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Figure 4. Aboveground biomass (t ha−1) plotted against vegetation indices: (a) NDVI; (b) NDRE; (c) CIRE; (d) MSAVI; (e) OSAVI; (f) MCARI1; (g) DATT; (h) MTVI2. WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Remotesensing 11 01371 g004
Figure 5. Leaf area index plotted against vegetation indices: (a) NDVI; (b) NDRE; (c) GNDVI; (d) CIRE; (e) MCARI1; (f) OSAVI; (g) MSAVI; (h) MTVI1. WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Figure 5. Leaf area index plotted against vegetation indices: (a) NDVI; (b) NDRE; (c) GNDVI; (d) CIRE; (e) MCARI1; (f) OSAVI; (g) MSAVI; (h) MTVI1. WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Remotesensing 11 01371 g005
Figure 6. Determination of optimal model parameters (random effects) for linear mixed-effect (LME) model using RMSE: (a) AGB; (b) LAI; (c) grouping situation with different random effects. N represents no random effects (fixed effects only). C represents cultivar, P represents planting method, S represents growth stage, WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Figure 6. Determination of optimal model parameters (random effects) for linear mixed-effect (LME) model using RMSE: (a) AGB; (b) LAI; (c) grouping situation with different random effects. N represents no random effects (fixed effects only). C represents cultivar, P represents planting method, S represents growth stage, WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Remotesensing 11 01371 g006
Figure 7. Validation of above ground biomass (AGB) estimation models for the whole season and different stage groups: (a) SR for the whole season, (b) pre-heading stages and (c) post-heading stages; (d) ANN for the whole season, (e) pre-heading stages and (f) post-heading stages; (g) RF for the whole season, (h) pre-heading stages and (i) post-heading stages; (j) LME model for the whole season, (k) pre-heading stages and (l) post-heading stages.
Figure 7. Validation of above ground biomass (AGB) estimation models for the whole season and different stage groups: (a) SR for the whole season, (b) pre-heading stages and (c) post-heading stages; (d) ANN for the whole season, (e) pre-heading stages and (f) post-heading stages; (g) RF for the whole season, (h) pre-heading stages and (i) post-heading stages; (j) LME model for the whole season, (k) pre-heading stages and (l) post-heading stages.
Remotesensing 11 01371 g007
Figure 8. Validation of LAI estimation models for the whole season and different stage groups: (a) SR for the whole season, (b) pre-heading stages and (c) post-heading stages; (d) ANN for the whole season, (e) pre-heading stages and (f) post-heading stages; (g) RF for the whole season, (h) pre-heading stages and (i) post-heading stages; (j) LME model for the whole season, (k) pre-heading stages and (l) post-heading stages.
Figure 8. Validation of LAI estimation models for the whole season and different stage groups: (a) SR for the whole season, (b) pre-heading stages and (c) post-heading stages; (d) ANN for the whole season, (e) pre-heading stages and (f) post-heading stages; (g) RF for the whole season, (h) pre-heading stages and (i) post-heading stages; (j) LME model for the whole season, (k) pre-heading stages and (l) post-heading stages.
Remotesensing 11 01371 g008
Figure 9. Comparison of LME models (for AGB estimation) with different random effects: (a) C, cultivar, (b) P, planting pattern, (c) S, growth stage, (d) CP, combination of cultivar and planting pattern, (e) CS, combination of cultivar and growth stage, (f) PS, combination of planting pattern and growth stage and (g) CSP, combination of cultivar, growth stage and planting pattern. C1-2, P1-3, S1-7, CP1-6, CS1-14, PS1-18 and CSP1-36 represent the groupings of corresponding random effects, respectively.
Figure 9. Comparison of LME models (for AGB estimation) with different random effects: (a) C, cultivar, (b) P, planting pattern, (c) S, growth stage, (d) CP, combination of cultivar and planting pattern, (e) CS, combination of cultivar and growth stage, (f) PS, combination of planting pattern and growth stage and (g) CSP, combination of cultivar, growth stage and planting pattern. C1-2, P1-3, S1-7, CP1-6, CS1-14, PS1-18 and CSP1-36 represent the groupings of corresponding random effects, respectively.
Remotesensing 11 01371 g009
Figure 10. Comparison of predictive capability within the groups of LME models (for AGB estimation) using different random effects: (a) the R2 and RMSE of the groups of different random effects; (b) the average R2 and RMSE of the groupings of different random effects. C represents cultivar; P represents planting pattern; S represents growth stage; CP represents combination of cultivar and planting pattern; CS represents combination of cultivar and growth stage; PS represents combination of planting pattern and growth stage; CSP represents combination of cultivar, growth stage and planting pattern.
Figure 10. Comparison of predictive capability within the groups of LME models (for AGB estimation) using different random effects: (a) the R2 and RMSE of the groups of different random effects; (b) the average R2 and RMSE of the groupings of different random effects. C represents cultivar; P represents planting pattern; S represents growth stage; CP represents combination of cultivar and planting pattern; CS represents combination of cultivar and growth stage; PS represents combination of planting pattern and growth stage; CSP represents combination of cultivar, growth stage and planting pattern.
Remotesensing 11 01371 g010
Figure 11. Comparison of LME models (for LAI estimation) with different random effects: (a) C, cultivar, (b) P, planting pattern, (c) S, growth stage, (d) CP, combination of cultivar and planting pattern, (e) CS, combination of cultivar and growth stage, (f) PS, combination of planting pattern and growth stage and (g) CSP, combination of cultivar, growth stage and planting pattern. C1-2, P1-3, S1-7, CP1-6, CS1-14, PS1-18 and CSP1-36 represent the groupings of corresponding random effects, respectively.
Figure 11. Comparison of LME models (for LAI estimation) with different random effects: (a) C, cultivar, (b) P, planting pattern, (c) S, growth stage, (d) CP, combination of cultivar and planting pattern, (e) CS, combination of cultivar and growth stage, (f) PS, combination of planting pattern and growth stage and (g) CSP, combination of cultivar, growth stage and planting pattern. C1-2, P1-3, S1-7, CP1-6, CS1-14, PS1-18 and CSP1-36 represent the groupings of corresponding random effects, respectively.
Remotesensing 11 01371 g011
Figure 12. Comparison of predictive capability within the groups of LME models (for LAI estimation) using different random effects: (a) the R2 and RMSE of the groups of different random effects; (b) the average R2 and RMSE of the groupings of different random effects. C represents cultivar; P represents planting pattern; S represents growth stage; CP represents combination of cultivar and planting pattern; CS represents combination of cultivar and growth stage; PS represents combination of planting pattern and growth stage; CSP represents combination of cultivar, growth stage and planting pattern.
Figure 12. Comparison of predictive capability within the groups of LME models (for LAI estimation) using different random effects: (a) the R2 and RMSE of the groups of different random effects; (b) the average R2 and RMSE of the groupings of different random effects. C represents cultivar; P represents planting pattern; S represents growth stage; CP represents combination of cultivar and planting pattern; CS represents combination of cultivar and growth stage; PS represents combination of planting pattern and growth stage; CSP represents combination of cultivar, growth stage and planting pattern.
Remotesensing 11 01371 g012
Table 1. Basic information about experimental design and data acquisition.
Table 1. Basic information about experimental design and data acquisition.
ExperimentTransplantingCultivarsN Rate (kg ha−1)Planting PatternsPlot SizeSampling Stages
EXP.1 201714-JunNanjing-9108N0(0)PMT150 m2Stem elongation (25-Jul)
(Japonica)N1(135)CMT(15 m × 10 m)Booting (10-Aug)
Yongyou-2640N2(270)DS Heading (23-Aug)
(Indica/JaponicaN3(405) Flowering (1-Sep)
Hybrid) Grain filling (14-Sep)
EXP.2 201818-JunNanjing-9108N0(0)PMT300 m2Tillering (22-Jul)
(Japonica)N1(135)CMT(20 m × 15 m)Stem elongation (28-Jul)
Yongyou-2640N2(270) Panicle initiation (12-Aug)
(Indica/JaponicaN3(405) Booting (19-Aug)
Hybrid) Heading (31-Aug)
Grain filling (21-Sep)
Note: PMT represents pot-seeding mechanical transplanting, CMT represents carpet-seeding mechanical transplanting and DS represents direct-sowing.
Table 2. Descriptive statistics of growth parameters for experiments in 2017 and 2018.
Table 2. Descriptive statistics of growth parameters for experiments in 2017 and 2018.
TypeVariableNMeanMinimumMaximumSDCV (%)
GrowthAGB (t ha−1)6489.050.5422.835.2258
parametersLAI6484.810.4014.832.4952
Note: N represents the number of samples, SD represents the standard deviation and CV represents the coefficient of variation.
Table 3. Selected vegetation indices used for aboveground biomass and leaf area index estimation.
Table 3. Selected vegetation indices used for aboveground biomass and leaf area index estimation.
Vegetation IndexFormulationApplicationReference
NDVI ( R 790 R 660 ) / ( R 790 + R 660 ) AGB & LAI[39]
NDRE ( R 790 R 735 ) / ( R 790 + R 735 ) AGB & LAI[40]
CIRE ( R 790 / R 735 ) 1 AGB & LAI[41]
MSAVI 0.5 [ 2 R 790 + 1 ( 2 R 790 + 1 ) 2 8 ( R 790 R 660 ) ] AGB & LAI[42]
OSAVI ( 1 + 0.16 ) ( R 790 R 660 ) / ( R 790 + R 660 + 0.16 ) AGB & LAI[43]
MCARI1 1.2 [ 2.5 ( R 790 R 660 ) 1.3 ( R 790 R 560 ) ] AGB & LAI[44]
MTVI2 1.5 ( 1.2 ( R 790 R 550 ) 2.5 ( R 660 R 550 ) ) / ( 2 R 790 + 1 ) 2 ( 6 R 790 5 R 660 ) 0.5 AGB[45]
DATT ( R 790 R 735 ) / ( R 790 R 660 ) AGB[46]
GNDVI ( R 790 R 560 ) / ( R 790 + R 560 ) LAI[47]
MTVI1 1.2 [ 1.2 ( R 790 R 560 ) 2.5 ( R 660 R 560 ) ] LAI[45]
Table 4. Descriptive statistics of vegetation indices for the experiments in 2017 and 2018.
Table 4. Descriptive statistics of vegetation indices for the experiments in 2017 and 2018.
TypeVariableNMeanMinimumMaximumSDCV (%)
NDVI6480.870.510.940.078
NDRE6480.330.050.470.0928
CIRE6481.020.111.760.3837
MSAVI6480.650.160.910.1827
VegetationOSAVI6480.730.310.900.1116
indicesMCARI16480.310.010.910.1755
MTVI16480.610.151.130.1829
MTVI26480.690.160.970.1928
DATT6480.520.120.660.1122
GNDVI6480.740.390.850.0811
Note: N represents the number of samples, SD represents the standard deviation and CV represents the coefficient of variation.
Table 5. Parameters for artificial neural networks (ANN) and random forests (RF) regression models.
Table 5. Parameters for artificial neural networks (ANN) and random forests (RF) regression models.
Growth IndexGrowth StageANN Model Parameter
Number of Hidden NeuronsTraining Algorithm
WS27Scaled Conjugate Gradient
AGBPre-HD21
Post-HD23
WS17Scaled Conjugate Gradient
LAIPre-HD15
Post-HD14
Note: WS represents the whole season, Pre-HD represents pre-heading stages and Post-HD represents post-heading stages.
Table 6. Flight efficiency comparison for two types of UAVs.
Table 6. Flight efficiency comparison for two types of UAVs.
TypeNo.Maximum Speed (m s−1)Endurance (min)Reference
Multi-rotorMR INot given16–22[9]
(MR)MR II1325[54]
MR III1215[10]
Fixed-wingFW I17.560[55]
(FW)FW II33120–360[56]
FW III3055This paper

Share and Cite

MDPI and ACS Style

Wang, Y.; Zhang, K.; Tang, C.; Cao, Q.; Tian, Y.; Zhu, Y.; Cao, W.; Liu, X. Estimation of Rice Growth Parameters Based on Linear Mixed-Effect Model Using Multispectral Images from Fixed-Wing Unmanned Aerial Vehicles. Remote Sens. 2019, 11, 1371. https://doi.org/10.3390/rs11111371

AMA Style

Wang Y, Zhang K, Tang C, Cao Q, Tian Y, Zhu Y, Cao W, Liu X. Estimation of Rice Growth Parameters Based on Linear Mixed-Effect Model Using Multispectral Images from Fixed-Wing Unmanned Aerial Vehicles. Remote Sensing. 2019; 11(11):1371. https://doi.org/10.3390/rs11111371

Chicago/Turabian Style

Wang, Yanyu, Ke Zhang, Chunlan Tang, Qiang Cao, Yongchao Tian, Yan Zhu, Weixing Cao, and Xiaojun Liu. 2019. "Estimation of Rice Growth Parameters Based on Linear Mixed-Effect Model Using Multispectral Images from Fixed-Wing Unmanned Aerial Vehicles" Remote Sensing 11, no. 11: 1371. https://doi.org/10.3390/rs11111371

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop