remote sensing

Article
Prediction of Cereal Rye Cover Crop Biomass and Nutrient
Accumulation Using Multi-Temporal Unmanned Aerial Vehicle
Based Visible-Spectrum Vegetation Indices
Richard T. Roth 1, * , Kanru Chen 2 , John R. Scott 2 , Jinha Jung 3 , Yang Yang 4 , James J. Camberato 2
and Shalamar D. Armstrong 2

1 Department of Crops and Soil Sciences, University of Georgia, 2360 Rainwater Rd., Tifton, GA 31793, USA
2 Department of Agronomy, Purdue University, 915 W State St., West Lafayette, IN 47907, USA
3 Lyles School of Civil Engineering, Purdue University, 550 Stadium Mall Dr., West Lafayette, IN 47907, USA
4 Agricultural Research and Graduate Education, Purdue University, 615 W State St.,
West Lafayette, IN 47907, USA
* Correspondence: [email protected]; Tel.: +1-229-386-3571

Abstract: In general, remote sensing studies assessing cover crop growth are species nonspecific,
use imagery from satellites or modified unmanned aerial vehicles (UAVs), and rely on multispectral
vegetation indexes (VIs). However, using RGB imagery and visible-spectrum VIs from commercial off-
the-shelf (COTS) UAVs to assess species specific cover crop growth is limited in the current scientific
literature. Thus, this study evaluated RGB imagery and visible-spectrum VIs from COTS UAVs for
suitability to estimate concentration (%) and content (kg ha−1 ) based cereal rye (CR) biomass, carbon
(C), nitrogen (N), phosphorus (P), potassium (K), and sulfur (S). UAV surveys were conducted at
two fields in Indiana and evaluated five visible-spectrum VIs—Visible Atmospherically Resistant
Index (VARI), Green Leaf Index (GLI), Modified Green Red Vegetation Index (MGRVI), Red Green
Blue Vegetation Index (RGBVI), and Excess of Greenness (ExG). This study utilized simple linear
regression (VI only) and stepwise multiple regression (VI with weather and geographic data) to
Citation: Roth, R.T.; Chen, K.; Scott, produce individual models for estimating CR biomass, C, N, P, K, and S concentration and content.
J.R.; Jung, J.; Yang, Y.; Camberato, J.J.; The goodness-of-fit statistics were generated using repeated K-fold cross-validation to compare
Armstrong, S.D. Prediction of Cereal
individual model performance. In general, the models developed using simple linear regression were
Rye Cover Crop Biomass and
inferior to those developed using the multiple stepwise regression method. Furthermore, for models
Nutrient Accumulation Using
developed using the multiple stepwise regression method all five VIs performed similarly when
Multi-Temporal Unmanned Aerial
estimating concentration-based CR variables; however, when estimating content-based CR variables
Vehicle Based Visible-Spectrum
Vegetation Indices. Remote Sens. 2023,
the models developed with GLI, MGRVI, and RGBVI performed similarly explaining 74–81% of
15, 580. https://doi.org/10.3390/ the variation in CR data, and outperformed VARI and ExG. However, on an individual field basis,
rs15030580 MGRVI consistently outperformed GLI and RGBVI for all CR characteristics. This study demonstrates
the potential to utilize COTS UAVs for estimating in-field CR characteristics; however, the models
Academic Editor: Giuseppe Modica
generated in this study need further development to expand geographic scope and incorporate
Received: 25 October 2022 additional abiotic factors.
Revised: 10 January 2023
Accepted: 11 January 2023 Keywords: cover crops; cereal rye; unmanned aerial vehicle; remote sensing; vegetation indexes;
Published: 18 January 2023 nutrient accumulation; biomass; RGB; visible spectrum; crop surface models

Copyright: © 2023 by the authors.

1. Introduction
Licensee MDPI, Basel, Switzerland.
This article is an open access article Across the United States, cereal rye (CR) is the most common cover crop species pri-
distributed under the terms and marily due to its relatively inexpensive seed cost, straightforward management, and winter
conditions of the Creative Commons hardy nature allowing for ground cover throughout the traditional fallow
Attribution (CC BY) license (https:// period [1,2]. Additionally, CR scavenges excess soil N leading to reductions in subsur-
creativecommons.org/licenses/by/ face drainage nitrate (NO3 -N) losses [3–6], along with providing a host of soil health
4.0/). benefits [7–9]. However, the accumulation of CR biomass and the associated nutrients,

Remote Sens. 2023, 15, 580. https://doi.org/10.3390/rs15030580 https://www.mdpi.com/journal/remotesensing

Remote Sens. 2023, 15, 580 2 of 18

including carbon (C), nitrogen (N), phosphorus (P), potassium (K), and sulfur (S), could
lead to soil fertility imbalances due to soil nutrients being immobilized by soil microbes
decomposing CR residues [10]. Furthermore, CR establishment, and biomass and nutrient
content are spatially and temporally variable which can increase the complexity of making
management decisions for subsequently grown cash crops [11]. Thus, it is critical for pro-
ducers to be able to quantify CR biomass and nutrient content in-season to make informed
fertility management decisions.
Traditional methods of determining CR biomass and nutrient concentration and
content include collecting CR shoot biomass from a known area and submitting it for
analysis at a plant tissue testing facility. At the testing facility, the CR shoot biomass must
be dried, ground, and analyzed on multiple instruments (dry combustion and inductively
coupled plasma spectrometry). Traditional CR Biomass and nutrient concentration and
content assessment can be time and labor intensive, and costly [12]. Furthermore, with
traditional analyses, there is a lag time between sample collection and receiving analysis
results, meaning that producers who use CR biomass and nutrient content analysis to
make management decisions must wait for results before making decisions at which time
the information regarding the CR may become outdated. Therefore, it is critical that a
simple method for the rapid assessment of CR biomass and nutrient concentration and
content using commercially available products be developed to allow for real-time informed
decisions regarding management decisions for cash crops following CR.
Recently, the use of remotely sensed imaging via UAV or satellite in crop scouting
and plant health monitoring has become increasingly popular amongst researchers and the
production agriculture community [13]. However, assessment of cover crop productivity
via UAV imagery has been somewhat limited. Imagery obtained from UAV platforms can
be processed within a matter of hours allowing for timely receipt of results accounting for
spatial variability that can be used by producers to make informed management decisions.
In research employing UAV platforms, the use of visible spectrum vegetation indices (VIs)
(i.e., visible atmospherically resistant index, VARI) is less commonly studied relative to
multispectral VIs (e.g., normalized difference vegetation index, NDVI) which can require
the addition of costly sensors and modifications to the UAV itself. Studies that examine the
use of UAVs to monitor plant growth primarily focus on the prediction of biomass and N
accumulation [14–19]. Others have used satellite imagery coupled with multispectral VIs
to estimate cover crop biomass and N concentration and content [20–22]. The studies that
focus on cover crops primarily rely on multispectral VIs for prediction, are often species
nonspecific, and are more commonly conducted using satellite imagery or modified UAV
platforms than off-the-shelf UAV platforms with standard RGB sensors.
In addition, there is a dearth of literature examining methods for the prediction of crop
P, K, and S accumulation. Studies developed to assess crop P, K, and S status have relied on
costly handheld multispectral or hyperspectral sensors to evaluate reflectance bands for
computing VIs [23–26]. However, the use of remotely sensed imaging to assess crop P, K,
and S status is limited. Furthermore, no studies have been conducted to evaluate the efficacy
of visible-spectrum VIs obtained from imagery collected with commercially available UAV
platforms to predict C, P, K, and S concentration and content in cover crops, let alone CR.
Accumulation of C, P, K, and S in CR biomass could lead to soil fertility imbalances and
soil nutrient immobilization during residue decomposition; thus, rapid estimation of C, P,
K, and S content is critical to inform timely nutrient management decisions.
In this study, it was hypothesized that visible-spectrum vegetation indices obtained
by commercially available unmanned aerial vehicles outfitted with standard RGB sensors
could be used to accurately predict CR biomass, C, N, P, K, and S concentration and content.
The specific objectives were to: (i) evaluate multiple visible-spectrum vegetation indices
and determine the best predictors of cereal rye biomass, C, N, P, K, and S concentration
and content, and (ii) train and test prediction models for cereal rye biomass, C, N, P, K, and
S concentration and content.
Remote Sens. 2023, 15, 580 3 of 18

2. Materials and Methods

2.1. Experimental Site Description
This study was conducted at two Purdue University Agricultural Centers in the state
of Indiana. Field 1 was located at the Agronomy Center for Research and Education near
West Lafayette, Indiana, and field 2 was located at the Southeast Purdue Agricultural Center
near Butlerville, Indiana. The predominant soil series at field 1 were Drummer silty clay
loam (fine-silty, mixed, superactive, mesic Typic Endoaquolls) and a Raub–Brenton silt loam
(fine-silty, mixed, superactive, mesic Aquic Argiudolls), and the predominant soil series at
field 2 were Cobbsfork silt loam (fine-silty, mixed, active, mesic Fragic Glossaqualfs) and
Avonburg silt loam (fine-silty, mixed, active, mesic Aeric Fragic Glossaqualfs). At both
locations, CR cover crops were drilled at a rate of 56 kg ha−1 following soybean harvest.
Cereal rye planting and termination dates are shown in Table 1.

Table 1. Location and cereal rye management for the two field sites where UAV flights occurred.

Site Coordinates Cereal Rye Planting Date Cereal Rye Termination Date
Field 1 40◦ 290 17.800 N 86◦ 590 38.800 W 18 September 2020 17 April 2021
Field 2 39◦ 020 00.700 N 85◦ 320 05.700 W 9 October 2020 16 April 2021

2.2. Ground-Truth Sampling

On the same date as each UAV flight, CR shoot biomass samples (0.25 m2 ) were
collected at 30 locations within the field. Sample locations were distributed throughout the
field to capture the range of growth conditions and biomass levels being evaluated with
each UAV flight. All biomass sampling locations were surveyed on the day of the sampling
using a Trimble AgGPS 542 (Trimble, Sunnyvale, CA, USA) portable GPS base station
mounted on a monopod using the real-time kinematic positioning (RTK) GPS technique.
After the GPS survey, biomass samples were oven-dried to a constant weight at 60 ◦ C to
determine CR shoot biomass, then ground to pass a 2 mm sieve. Dried and ground CR
shoot biomass was submitted to United Soils Inc. (Fairbury, IL, USA) for C, N, P, K, and S
content. At United Soils Inc., dried and ground plant tissue samples were batched in groups
of 19 samples, 2 method controls, and 3 tissue samples of known composition similar to
CR residues. Each batch of tissue samples was analyzed for C and N concentration by
combustion analysis (LECO CN 828, St. Josephs, MO, USA). To determine P, K, and S
concentrations, 300 mg subsamples of the unknown, known, and method control samples
from each batch were weighed, mixed with concentrated nitric acid, microwave digested
(CEM Mars 6, Matthews, NC, USA), then analyzed via inductively coupled plasma optical
emission spectrometry (Perkin Elmer Optima 7500, Chicago, IL, USA) [27,28].
Precipitation and temperature data were collected from the Purdue Mesonet available
through the Indiana State Climate Office for both fields for the period from CR planting
to final image acquisition. Temperature data was used to calculate growing degree days
(GDD) as follows:

Tmax + Tmin
Growing Degree Days (GDD) = − Tbase (1)
2
where Tmax is daily maximum air temperature bounded at 30 ◦ C, Tmin is daily minimum
air temperature bounded at 0 ◦ C, and Tbase is the base temperature (0 ◦ C), which represents
the minimum temperature at which CR growth will occur [29–31]. Cumulative GDD and
cumulative precipitation for each field at each sampling date are shown in Table 2.
Remote Sens. 2023, 15, x FOR PEER REVIEW 4 of 18

represents the minimum temperature at which CR growth will occur [29–31]. Cumulative
Remote Sens. 2023, 15, 580 GDD and cumulative precipitation for each field at each sampling date are shown in Table
4 of 18
2.

Table 2.
Table 2. The
The sample
sampledates,
dates,accumulated
accumulatedgrowing
growingdegree
degree days
days (GDD),
(GDD), and
and accumulated
accumulated precipita-
precipitation
tion for field 1 and field 2.
for field 1 and field 2.
Field 1 Field 2
Field 1 Field 2
Cumulative Pre- Cumulative Pre-
Sample Date Cumulative GDD Cumulative Sample Date Cumulative GDD Cumulative
Sample Date Cumulative GDD cipitation, mm Sample Date Cumulative GDD cipitation, mm
Precipitation, mm Precipitation, mm
29 March 2021 1225.2 319.8 3 December 2020 575.0 255.5
29 March2021
6 April 2021 1225.2
1316.1 319.8
322.6 103 December
December 20202020 575.0
600.7 255.5
255.5
6 April 2021 1316.1 322.6 10 December 2020 600.7 255.5
12
12 April 2021
April 2021 1408.2
1408.2 340.1
340.1 22
22 March 2021
March 2021 976.1
976.1 500.1
500.1
11 April 2021
April 2021 1084.9
1084.9 550.7
550.7
88 April
April 2021
2021 1184.2
1184.2 555.5
555.5
16 April 2021
16 April 2021 1286.9
1286.9 584.0
584.0

2.3. Unmanned Aerial Vehicle Image Acquisition

The goal
goal of
ofthis
thisstudy
studywas wastotoutilize
utilize commercial
commercial off-the-shelf
off-the-shelf (COTS)
(COTS) UAV UAVandand soft-
software
ware to provide
to provide a method
a method of predicting
of predicting CR biomass
CR biomass andand nutrient
nutrient accumulation
accumulation applicable
applicable to
to producers, land managers, consultants, and conservation professionals. We used
producers, land managers, consultants, and conservation professionals. We used a DJI
Phantom 44 Pro Pro (DJI,
(DJI,Shenzhen,
Shenzhen,China) China)asasaaCOTSCOTSUAV UAVplatform
platform toto
collect aerial
collect imagery
aerial imagery in
thisthis
in study (Figure
study 1). 1).
(Figure It isItequipped
is equipped with a standard
with a standardgimble mounted
gimble mounted1-inch 20-megapixel
1-inch 20-mega-
CMOS sensor which has an ◦ field-of-view. The RGB sensor captured three separate
pixel CMOS sensor which has84an 84° field-of-view. The RGB sensor captured three sepa-
bands:
rate red (620–700
bands: nm), nm),
red (620–700 greengreen
(495–570 nm), nm),
(495–570 and blue
and (450–495 nm). All
blue (450–495 nm).flights occurred
All flights oc-
during cloud-free periods between 10:00 am and 11:00 am eastern
curred during cloud-free periods between 10:00 am and 11:00 am eastern standard time. standard time. The area
surveyed
The was 17 ha
area surveyed wasfor17field 1 and
ha for field12 ha for
1 and field
12 ha for2,field
and2,the
andsurvey was completed
the survey was completed in a
single flight at an altitude of 85 m and a flying speed of approximately 7.25 m S −1−1. At
in a single flight at an altitude of 85 m and a flying speed of approximately 7.25 m S . At
each field
each field ten
ten ground-control
ground-control points points (GCPs)
(GCPs) were
were evenly
evenly distributed for use
distributed for use in
in enhanced
enhanced
georeferencing during
georeferencing duringimageimagepostprocessing.
postprocessing.The TheGCPs GCPs
were were commercially
commercially available
available 0.25
0.25 m 2 black and white ground targets. Ground control point locations were surveyed via
m black and white ground targets. Ground control point locations were surveyed via
2

RTK using
RTK using aa Trimble
Trimble AgGPS
AgGPS 542 542 portable
portable GPS
GPS base
base station
station mounted
mounted on onaamonopod.
monopod.

Figure 1. (A)
Figure 1. (A) The
The commercial
commercial off-the-shelf
off-the-shelf UAV
UAV used
used in
in this
this project
project was
was aa DJI
DJI Phantom
Phantom 44 Pro
Pro
equipped with the DJI standard 1-inch 20-megapixel CMOS sensor. (B) An example of a final mo-
equipped with the DJI standard 1-inch 20-megapixel CMOS sensor. (B) An example of a final
saicked RGB image. The red dots indicate the location of ground control points within the field. (C)
mosaicked RGB image. The red dots indicate the location of ground control points within the field.
An example of a modified greed red vegetation index (MGRVI) map generated in ArcGIS Pro. The
(C) Andots
black example of a modified
represent greed
ground-truth red vegetation
sampling points. index (MGRVI)
This field mapcover
included generated
crops in ArcGIS
beyond Pro.
cereal
The
rye, black dots represent
ground-truth samplesground-truth samplingfrom
were only collected points. Thisrye
cereal field included cover
monoculture crops beyond cereal
plots.
rye, ground-truth samples were only collected from cereal rye monoculture plots.

The number of images collected during each flight was approximately 300 at field 1
and 150 at field 2 and were acquired using a 75% sidelap and 75% frontlap. Collected images
were first radiometrically calibrated by capturing images of a MAPIR camera reflectance
Remote Sens. 2023, 15, 580 5 of 18

calibration ground target version 2 (MAPIR, Inc., San Diego, CA, USA) collected just prior
to each flight and using the MAPIR Camera Control software (MAPIR, Inc., San Diego, CA,
USA) which employs the empirical line method for radiometric correction. Radiometrically
calibrated images were then processed using Pix4D fields software (Pix4D SA, Lausanne,
Switzerland) to generate 2.3 cm spatial resolution orthomosaic images. Mosaicked images
were then georeferenced in ArcGIS Pro (Esri, Redlands, CA, USA) using the control point
option within the georeferencing tools resulting in an accuracy level within 0.4 cm. The
raster calculator tool within ArcGIS Pro was used to compute vegetation indices.
In this study, five visible-spectrum VIs based on the reflectance values of images at
each sampling date including: Visible Atmospherically Resistant Index (VARI), Green Leaf
Index (GLI), Modified Green Red Vegetation Index (MGRVI), Red Green Blue Vegetation
Index (RGBVI), and Excess of Green (ExG) (Table 3).

Table 3. Vegetation indices used in this study and their accompanying equations.

Vegetation Index † Equation ‡ Reference

VARI (ρG −ρR) [32]
(ρG +ρR−ρB)
GLI (2×ρG −ρR−ρB) [33]
(2×ρG +ρR+ρB)
MGRVI (ρG )2 −(ρR)2 [14]
(ρG )2 +(ρR)2
RGBVI (ρG )2 −(ρR×ρB) [14]
(ρG )2 +(ρR×ρB)
ExG 2 × ρG − ρR − ρB [34]
† VARI = Visible Atmospherically Resistant Index, GLI = Green Leaf Index, MGRVI = Modified Green Red
Vegetation Index, RGBVI = Red Green Blue Vegetation Index, and ExG = Excess of Green. ‡ ρG is the green
reflectance band, ρR is the red reflectance band, and ρB is the blue reflectance band.

To accurately represent the 0.25 m2 CR shoot biomass sampling area, a 0.25 m radius
buffer area was created around the georeferenced location of each ground-truth sample.
Due to the high spatial resolution of the imagery (0.00053 m2 per pixel), each ground-truth
buffer area contained between 400 and 500 pixels; thus, the mean VI value from each buffer
area was used to build the predictive models. Mean VI values were extracted from the VI
maps using the zonal statistics as table tool in ArcGIS Pro.

2.4. Model Cross-Validation and Fitting

Data from all sampling dates at each field were randomly split into training (70%) and
testing (30%) datasets, then the datasets from individual fields were combined into singular
training and testing datasets to develop the predictive models. This study employed both
simplistic and complex methods for the development of predictive models. Independent
models were developed using the simplistic and complex methods for both content-based
and concentration-based measures of the response variables of CR biomass, CR C, CR N,
CR P, CR K, and CR S. The simplistic method used simple linear regression between the
in-field measured response variables and the VI values obtained from the UAV flights. This
approach represents the most commonly employed method for the prediction of cover crop
characteristics within the literature. The general functional form of the simplistic model is
described in Equation (2):
RV = β0 + β1 VI + ε (2)
where RV is the response variable of CR biomass, CR C, CR N, CR P, CR K, or CR S on either
a concentration or content basis, β0 is the intercept, β1 is the slope associated with VI, VI is
the mean vegetation index (VARI, GLI, MGRVI, RGBVI, or ExG), and ε is an error term.
The complex model is the result of multiple linear regression of the in-field measured
response variables against the vegetation index values obtained from the UAV and other
exogenous factors including location variables (latitude, longitude, and elevation) and
weather variables (accumulated growing degree days and precipitation). These weather
variables were selected because they represent the primary drivers of plant growth (tem-
Remote Sens. 2023, 15, 580 6 of 18

perature and precipitation) and have not been previously included in cover crop biomass
and nutrient estimation models. The geographic information included in this study is
essentially a proxy for location, however, the authors chose to include it because, when
this research is expanded to encompass a larger geographic scope, this information will
be more pertinent and help encompass not only location but other factors, such as soil
type, drainage, etc. The general functional form of the complex model is described in
Equation (3):

RV = β0 + β1 VI + β2 Long + β3 Lat + β4 Elev + β5 GDD + β6 Precip + ε (3)

where βx is the slope associated with the accompanying independent variable, Long is
longitude, Lat is latitude, Elev is elevation, GDD is accumulated growing degree days, and
Precip is accumulated precipitation.
Repeated K-fold cross validation was used to determine the potential predictive
capacity of each VI for each response variable. This method randomly split the data into
n subsets known as folds (n = 10), calibrated the model using n-1 folds, then validated
the model using the final fold. This calibration-validation procedure was repeated until
all folds were used as the validation subset. The process was repeated ten times, with the
data randomly redistributed into n number of folds for each iteration. This method was
chosen because it is computationally efficient and helps control and minimize bias and
variability in the prediction error of the model. This cross-validation procedure produced
an average root mean square error (RMSE, presented in the units of measure), normalized
RMSE (%RMSE, RMSE as a percentage of the range in the measured data), and adjusted
coefficient of determination (Adjusted-R2 ) for the models. Following cross-validation,
concentration and content-based models for each response variable and each VI were fit
to the full training dataset. To determine the significance (α = 0.05) of each independent
variable within the model, forward stepwise linear regression was performed. Model
goodness of fit was determined by assessing the coefficient of determination (multiple-R2 ),
adjusted-R2 , RMSE, and %RMSE.

3. Results
3.1. Model Cross-Validation and Selection
Summary data of concentration- and content-based in-field CR biomass and nutrients
for each field at each flight date are shown in Tables 4 and 5, respectively.

Table 4. Mean (standard error) of content-based in-field cereal rye biomass and nutrient data collected
on the date of each UAV flight.

Biomass C N P K S
Field Date Kg ha−1
29 March2021 1143 (99) 422 (36) 26.4 (2.3) 2.83 (0.48) 22.8 (2.3) 1.93 (0.16)
1 6 April 2021 1762 (144) 651 (52) 37.2 (2.8) 4.90 (0.65) 36.5 (3.5) 2.56 (0.19)
12 April 2021 1550 (161) 574 (59) 33.4 (3.3) 3.66 (0.62) 34.5 (4.0) 2.25 (0.21)
3 December 2020 314 (20) 108 (7) 11.4 (0.6) 1.43 (0.09) 7.17 (0.5) 0.79 (0.04)
10 December 2020 404 (17) 148 (6) 14.4 (0.5) 1.84 (0.09) 8.59 (0.4) 1.03 (0.04)
22 March 2021 868 (27) 316 (10) 22.2 (0.9) 2.64 (0.13) 15.5 (0.8) 1.67 (0.06)
2
1 April 2021 1193 (62) 432 (22) 25.0 (1.5) 3.81 (0.26) 25.7 (1.6) 1.92 (0.10)
8 April 2021 1720 (66) 629 (23) 29.7 (1.3) 5.07 (0.35) 36.8 (2.1) 2.40 (0.11)
16 April 2021 4008 (103) 1469 (37) 58.4 (2.9) 10.79 (0.41) 84.5 (2.8) 4.86 (0.15)
Remote Sens. 2023, 15, 580 7 of 18

Table 5. Mean (standard error) of concentration-based in-field cereal rye nutrient data collected on
the date of each UAV flight.

C N P K S
Field Date %
29 March2021 37.1 (0.13) 2.35 (0.07) 0.213 (0.02) 1.95 (0.05) 0.174 (0.004)
1 6 April 2021 37.1 (0.12) 2.17 (0.06) 0.202 (0.02) 2.03 (0.03) 0.151 (0.005)
12 April 2021 37.2 (0.24) 2.22 (0.07) 0.206 (0.01) 2.17 (0.03) 0.151 (0.005)
3 December 2020 34.7 (0.31) 3.69 (0.06) 0.454 (0.01) 2.29 (0.03) 0.257 (0.004)
10 December 2020 36.7 (0.16) 3.59 (0.06) 0.456 (0.01) 2.12 (0.04) 0.255 (0.004)
22 March 2021 36.4 (0.16) 2.56 (0.06) 0.302 (0.01) 1.76 (0.05) 0.193 (0.003)
2
1 April 2021 36.3 (0.10) 2.09 (0.05) 0.316 (0.01) 2.14 (0.06) 0.162 (0.003)
8 April 2021 36.6 (0.12) 1.72 (0.02) 0.288 (0.01) 2.11 (0.04) 0.139 (0.002)
16 April 2021 36.6 (0.05) 1.45 (0.05) 0.269 (0.01) 2.11 (0.04) 0.121 (0.002)

Repeated K-fold cross-validation was used to assess the potential predictive capac-
ity of different VIs using both simplistic and complex model development methods on
concentration and content-based response variables of CR biomass, C, N, P, K, and S. In
general, the models developed using the simplistic method performed relatively poorly
(R2 = 0.02–0.47); however, the simplistic models developed using content-based CR re-
sponse variables explained a relatively greater proportion of the variation (R2 = 0.04–0.47)
in response variables compared to the concentration-based models (R2 = 0.02–0.20, Table 6).

Table 6. Root mean square error (RMSE), %RMSE, and coefficient of determination (R2 ) for repeated
K-fold cross validation of cereal rye biomass (Bio), nutrient concentration, and content-based models
for different vegetation indices developed using the simple method.

VARI GLI MGRVI RGBVI ExG

Statistic
Conc Content Conc Content Conc Content Conc Content Conc Content
Adj. R2 0.04 0.33 0.25 0.35 0.20
Bio RMSE 1173 983 1038 970 1075
%RMSE 24% 20% 21% 20% 22%
Adj. R2 0.12 0.05 0.04 0.34 0.07 0.25 0.04 0.34 0.05 0.21
C RMSE 1.03 430 1.06 358 1.06 379 1.06 358 1.07 394
%RMSE 12% 24% 12% 20% 13% 21% 12% 20% 12% 21%
Adj. R2 0.02 0.08 0.13 0.47 0.06 0.34 0.13 0.47 0.13 0.26
N RMSE 0.79 17.9 0.75 13.1 0.77 14.9 0.75 13.2 0.75 15.7
%RMSE 25% 15% 24% 11% 24% 12% 24% 11% 23% 13%
Adj. R2 0.15 0.07 0.03 0.37 0.09 0.35 0.03 0.42 0.05 0.19
P RMSE 0.10 3.39 0.11 2.77 0.11 2.80 0.11 2.66 0.11 3.16
%RMSE 21% 22% 23% 18% 23% 18% 23% 17% 23% 21%
Adj. R2 0.04 0.06 0.12 0.39 0.13 0.29 0.12 0.40 0.20 0.24
K RMSE 0.26 25.9 0.25 20.7 0.25 22.4 0.25 20.6 0.24 23.2
%RMSE 21% 23% 20% 18% 20% 20% 20% 18% 19% 20%
Adj. R2 0.05 0.06 0.20 0.38 0.07 0.32 0.17 0.41 0.18 0.21
S RMSE 0.05 1.34 0.05 1.07 0.05 1.13 0.05 1.05 0.05 1.21
%RMSE 24% 22% 22% 17% 24% 18% 23% 17% 22% 20%

Based on these findings, and the fact that the complex models were capable of
explaining a substantially larger proportion of the variation in the response variables
(R2 = 0.16–0.83), the simplistic models were considered inferior, and exploration of these
models ended after the initial model development and cross-validation stage.
Remote Sens. 2023, 15, 580 8 of 18

The complex models developed using concentration-based CR response variables

explained 16–83% of the variation in the response variables; however, performance varied
based upon the response variable being predicted (Table 7).

Table 7. Root mean square error (RMSE), %RMSE, and coefficient of determination (R2 ) for repeated
K-fold cross validation of concentration (conc) and content-based cereal rye biomass (Bio) and nutrient
accumulation models for different vegetation indices developed using the complex method.

VARI GLI MGRVI RGBVI ExG

Statistic
Conc Content Conc Content Conc Content Conc Content Conc Content
Adj. R2 0.63 0.78 0.80 0.78 0.61
Bio RMSE 725 554 556 554 750
%RMSE 15% 11% 11% 11% 15%
Adj. R2 0.16 0.63 0.21 0.78 0.19 0.79 0.20 0.78 0.16 0.62
C RMSE 1.05 266 0.97 208 1.00 203 0.99 205 1.04 272
%RMSE 12% 15% 11% 12% 12% 11% 12% 11% 12% 15%
Adj. R2 0.80 0.50 0.79 0.76 0.79 0.73 0.78 0.77 0.80 0.52
N RMSE 0.35 13.2 0.36 9.11 0.36 9.75 0.37 8.98 0.35 12.7
%RMSE 11% 11% 11% 8% 11% 8% 12% 7% 11% 10%
Adj. R2 0.67 0.55 0.77 0.82 0.73 0.80 0.77 0.83 0.71 0.55
P RMSE 0.07 2.51 0.05 1.50 0.06 1.59 0.05 1.48 0.06 2.44
%RMSE 14% 16% 10% 10% 11% 10% 11% 10% 12% 16%
Adj. R2 0.16 0.61 0.22 0.82 0.22 0.81 0.23 0.82 0.27 0.62
K RMSE 0.28 16.9 0.26 11.1 0.26 11.5 0.25 11.0 0.24 16.5
%RMSE 22% 15% 21% 10% 21% 10% 20% 10% 19% 15%
Adj. R2 0.83 0.56 0.81 0.79 0.81 0.79 0.80 0.79 0.81 0.57
S RMSE 0.02 0.92 0.02 0.63 0.02 0.63 0.02 0.62 0.02 0.91
%RMSE 10% 15% 10% 10% 10% 10% 10% 10% 10% 15%

Poor overall model performance was observed for CR C (adj. R2 = 0.16–0.21) and
K (adj. R2 = 0.16–0.27) concentrations; however, satisfactory predictions of CR N (adj.
R2 = 0.78–0.80), P (adj. R2 = 0.67–0.77), and S (adj. R2 = 0.80–0.83) concentrations were
achieved using this methodology. All content-based models developed using the complex
method were capable of explaining at least 50% (adj. R2 = 0.50–0.83) of the variation in the
response variables (Table 7). In general, VARI and ExG were relatively poor predictors for
all content-based response variables (adj. R2 = 0.50–0.63) when compared to GLI, MGRVI,
and RGBVI (adj. R2 = 0.73–0.83), which all performed relatively similar to each other. Based
on these findings, and the relevance of understanding content-based CR biomass and
nutrient accumulation to the production agriculture community, GLI, MGRVI, and RGBVI
were chosen for further fitting and analysis of both concentration and content-based models.

3.2. Model Fitting and Analysis

To determine the significance of individual independent variables within the fitted
models, forward stepwise multiple linear regression was performed. In general, forward
stepwise multiple linear regression revealed that VI and GDD were significant in the models
for all concentration-based CR response variables except phosphorus, while the significance
of longitude, latitude, elevation, and accumulated precipitation within the models varied
based upon the response variable. Estimated regression coefficients of model parameters
for the C, N, P, K, and S concentration models are shown in Table 8.
Remote Sens. 2023, 15, 580 9 of 18

Table 8. Estimated regression coefficients for cereal rye carbon (C), nitrogen (N), phosphorus (P),
potassium (K), and sulfur (S) concentration model parameters determined by forward stepwise
multiple linear regression (α = 0.05).

Model VI Intercept VI Long Lat Elev GDD Precip

GLI 28.05 −11.02 0.002 −0.002
C MGRVI 10.54 −5.937 −0.232 0.001
RGBVI 23.68 −12.78 0.002 −0.002
GLI 5.503 −2.811 −0.008 −0.002 −0.002
N MGRVI 7.305 −2.269 −0.016 −0.003
RGBVI 3.949 −3.786 −0.008 −0.002 −0.001
GLI 505.2 1.460 10.58 10.30 −0.004 −0.001
P MGRVI 673.8 0.854 14.21 13.93 −0.005 −0.001
RGBVI 516.5 1.928 10.80 10.52 −0.004 −0.001
GLI 1118 3.521 23.45 22.85 0.001 −0.003
K MGRVI 1335 2.654 28.07 27.43 0.002 −0.003
RGBVI 1099 4.856 22.99 22.39 0.001 −0.003
GLI −1.045 −0.277 0.032 −0.0002
S MGRVI −0.402 −0.179 −0.001 −0.0002
RGBVI −1.133 −0.362 0.030 −0.0002

Forward stepwise multiple linear regression of models developed for content-based

CR characteristics showed that VI, GDD, and accumulated precipitation were always
significant within the models regardless of CR response variable while elevation was not
necessary, and the significance of longitude and latitude were model dependent. Estimates
of model parameter regression coefficients for the biomass, C, N, P, K, and S content-based
models are shown in Table 9.

Table 9. Estimated regression coefficients for content-based cereal rye biomass, carbon (C), nitrogen
(N), phosphorus (P), potassium (K), and sulfur (S) model parameters determined by forward stepwise
multiple linear regression (α = 0.05).

Model VI Intercept VI Long Lat Elev GDD Precip

GLI 162,100 20,100 −3871 9.66 −13.15
Bio MGRVI 176,598 15,399 −4252 11.54 −16.55
RGBVI 175,800 27,280 −3926 10.06 −13.91
GLI 59,577 7289.7 −1424 3.57 −4.87
C MGRVI 64,866 5603.7 −1563 4.25 −6.10
RGBVI 64,567 9905.5 −1444 3.71 −5.15
GLI 4119 384.25 45.42 0.115 −0.156
N MGRVI 47,630 271.90 978.2 928.7 0.150 −0.218
RGBVI 4426 518.73 46.45 0.122 −0.170
GLI 8331 78.36 169.5 159.2 0.024 −0.033
P MGRVI 14,150 56.06 293.9 282.6 0.031 −0.046
RGBVI 8260 106.6 166.8 156.3 0.025 −0.036
GLI 3718 506.5 −87.93 0.214 −0.302
K MGRVI 8577 381.3 97.12 0.262 −0.387
RGBVI 4065 688.8 −89.31 0.224 −0.321
GLI 162.4 26.26 −3.764 0.009 −0.012
S MGRVI 378.5 20.05 4.251 0.012 −0.017
RGBVI 180.4 35.71 −3.836 0.010 −0.013
Remote Sens. 2023, 15, 580 10 of 18

3.3. Final Model Goodness-of-Fit

Following cross-validation and forward stepwise multiple linear regression, the final
models were fit for each response variable to the testing data set containing information
from both fields. Model goodness of fit was evaluated by the multiple R2 and adjusted
R2 statistics which describe the percent variation in the dependent variable explained by
the independent variables. Adjusted R2 accounts for the number of independent variables
when analyzing the goodness of fit for the model. Large deviation in the adjusted R2
statistic from the multiple R2 value can indicate overfitting within the model; however, in
this study, little to no difference between multiple and adjusted R2 statistics was observed
indicating that overfitting was not an issue (Table 10).

Table 10. Multiple R2 , adjusted R2 , root mean square error, and percent root mean square error
values of the final fitted models for the response variables of cereal rye biomass, carbon, nitrogen,
phosphorus, potassium, and sulfur.

Response Multiple Adjusted

Units RMSE % RMSE
Variable R2 R2
GLI 0.79 0.79 486 10%
Biomass kg ha−1 MGRVI 0.81 0.81 464 9%
RGBVI 0.80 0.8 480 10%
GLI 0.35 0.34 1.07 12%
% MGRVI 0.35 0.34 1.07 12%
RGBVI 0.34 0.33 1.08 13%
Carbon
GLI 0.80 0.79 177 10%
kg ha−1 MGRVI 0.81 0.81 169 9%
RGBVI 0.80 0.80 175 10%
GLI 0.87 0.87 0.27 10%
% MGRVI 0.87 0.87 0.27 10%
RGBVI 0.87 0.87 0.27 10%
Nitrogen
GLI 0.77 0.76 7.08 6%
kg ha−1 MGRVI 0.80 0.79 6.63 5%
RGBVI 0.78 0.78 6.91 6%
GLI 0.83 0.83 0.05 10%
% MGRVI 0.83 0.83 0.05 11%
RGBVI 0.84 0.84 0.05 10%
Phosphorus
GLI 0.78 0.78 1.50 10%
kg ha−1 MGRVI 0.80 0.80 1.44 9%
RGBVI 0.80 0.79 1.46 9%
GLI 0.34 0.34 0.22 18%
% MGRVI 0.36 0.35 0.22 18%
RGBVI 0.35 0.34 0.22 19%
Potassium
GLI 0.79 0.79 10.7 9%
kg ha−1 MGRVI 0.82 0.81 10.1 9%
RGBVI 0.80 0.80 10.6 9%
GLI 0.85 0.85 0.02 10%
% MGRVI 0.84 0.84 0.02 10%
RGBVI 0.85 0.85 0.02 10%
Sulfur
GLI 0.74 0.74 0.64 10%
kg ha−1 MGRVI 0.78 0.77 0.60 10%
RGBVI 0.78 0.75 0.63 10%

In general, the concentration-based models developed in this study performed ad-

equately in the prediction of N (adj. R2 = 0.87), P (adj. R2 = 0.83–0.84), and S (adj.
R2 = 0.84–0.85); however, less than 36% of variation in CR C and K concentrations could
Remote Sens. 2023, 15, x FOR PEER REVIEW 11 of 18

Remote Sens. 2023, 15, 580 11 of 18

In general, the concentration-based models developed in this study performed ade-
quately in the prediction of N (adj. R2 = 0.87), P (adj. R2 = 0.83–0.84), and S (adj. R2 = 0.84–
0.85); however, less than 36% of variation in CR C and K concentrations could be ex-
be explained
plained using using these models.
these models. In contrast,
In contrast, models developed
models developed for content-based
for content-based CR responseCR
response variable performed adequately regardless of the characteristic
variable performed adequately regardless of the characteristic being modeled and were being modeled
and were
capable ofcapable of explaining
explaining 74–82% of 74–82% of theofvariation
the variation of the
the in-field in-field values
measured measured values
(Table 10).
(Table 10). Simultaneously, the final trained models for GLI, MGRVI,
Simultaneously, the final trained models for GLI, MGRVI, and RGBVI were fit to the and RGBVI were
in-
fit to the testing
dividual individual
datatesting
sets fromdata setsfield.
each fromIneach
this field.
case, In thisgoodness
model case, modelof goodness
fit was of
deter-
fit was determined using the adjusted R 2 values. In general, the models were able to
mined using the adjusted R2 values. In general, the models were able to more accurately
2 = 0.80–0.87) than from field 1 (adj.
more
predictaccurately
the data predict
from the
field 2 data R
(adj. from field 2 (adj.
2 = 0.80–0.87) than Rfrom field 1 (adj. R2 = 0.48–0.75), and
R 2 = 0.48–0.75), and the model trained using MGRVI provided better overall predictions
the model trained using MGRVI provided better overall predictions than those trained
than those trained with GLI and RGBVI (Figures 2 and 3)
with GLI and RGBVI (Figures 2 and 3)

Figure 2. Correlation of in-field measured versus predicted values by field for cereal rye biomass,
Figure 2. Correlation of in-field measured versus predicted values by field for cereal rye biomass,
carbon, and nitrogen obtained from complex content-based models developed using green leaf in-
carbon, and nitrogen obtained from complex content-based models developed using green leaf index
dex (GLI) (A—biomass, B—carbon, and C—nitrogen), modified green red vegetation index (D—
(GLI) (A—biomass,
biomass, E—carbon,B—carbon, and C—nitrogen),
and F—nitrogen), modified
and red green blue green red vegetation
vegetation index (D—biomass,
index (G—biomass, H—car-
E—carbon, and F—nitrogen),
bon, and I—nitrogen). and red green blue vegetation index (G—biomass, H—carbon, and
I—nitrogen).
Remote
Remote Sens. 2023, 15,
Sens. 2023, 15, 580
x FOR PEER REVIEW 12 of
12 of 18
18

Figure 3. Correlation of in-field measured versus predicted values by field for cereal rye phospho-
Figure 3. Correlation of in-field measured versus predicted values by field for cereal rye phosphorus,
rus, potassium, and sulfur obtained from complex content-based models developed using green leaf
potassium, and sulfur obtained from complex content-based models developed using green leaf
index (GLI) (A—phosphorus, B—potassium, and C—sulfur), modified green red vegetation index
index (GLI) (A—phosphorus,
(D—phosphorus, E—potassium, B—potassium, and and
and F—sulfur), C—sulfur), modified
red green green red index
blue vegetation vegetation index
(G—phos-
(D—phosphorus,
phorus, H—potassium,E—potassium, and F—sulfur), and red green blue vegetation index
and I—sulfur).
(G—phosphorus, H—potassium, and I—sulfur).
4. Discussion
4. Discussion
4.1. Can
4.1. Can Visible
Visible Spectrum
Spectrum Vegetation
VegetationIndices
IndicesBe
BeUsed
UsedtotoPredict
PredictConcentration
Concentrationand
andContent-Based
Content-Based
Cereal Cereal
Rye Biomass andRye Biomass
Nutrient and Nutrient Accumulation?
Accumulation?
study, we
In this study, we evaluated
evaluated thethe utility
utility ofof five
five visible-spectrum
visible-spectrum vegetation
vegetation indices to
predict both CR biomass
biomass andand nutrient
nutrient concentration
concentration and and content.
content. The models developed
using simple linear regression between visible-spectrum
visible-spectrum VIs VIs and CR characteristics
characteristics per-
per-
formed relatively poorly
poorly for
for both
both concentration-based
concentration-based (R (R22 = 0.02–0.20) and content-based
measures
measures ofof CR
CRcharacteristics
characteristics(R (R2 2== 0.04–0.47)
0.04–0.47)(Table
(Table6). 6).Contrastingly,
Contrastingly,the thecomplex
complexmodels
mod-
developed in this study including exogenous factors, such as geographic
els developed in this study including exogenous factors, such as geographic and weather and weather data,
provided satisfactory performance for almost all concentration and
data, provided satisfactory performance for almost all concentration and content-based content-based mea-
sures of CR 2 (0.67–0.83)
measures ofbiomass
CR biomassand and
nutrient accumulation.
nutrient accumulation. The The
adjusted-R
adjusted-R andand
2 (0.67–0.83) percent
per-
RMSE (10–14%)
cent RMSE in cross-validation
(10–14%) in cross-validationsuggested that all
suggested five
that allVIs were
five VIs capable of predicting
were capable of pre-
concentration-based CR N, P,
dicting concentration-based CRandN, SP,accumulation
and S accumulation with reasonable modelmodel
with reasonable performance;
perfor-
however, all VIs were insufficient in their predictive capacity of concentration-based
mance; however, all VIs were insufficient in their predictive capacity of concentration- CR
C and K accumulation (Table 7). Likewise, the adjusted-R 2 (0.50–0.83) and percent RMSE
based CR C and K accumulation (Table 7). Likewise, the adjusted-R (0.50–0.83) and per- 2

(7–16%)
cent RMSEin cross-validation for the complex
(7–16%) in cross-validation for themodels
complexdeveloped
models using content-based
developed mea-
using content-
sures of cereal rye biomass and nutrient suggested that all five VIs were
based measures of cereal rye biomass and nutrient suggested that all five VIs were capable capable of predict-
ing CR biomass,
of predicting CRC,biomass,
N, P, K, C,
andN,S P,
withK, satisfactory
and S with model performance
satisfactory (Table 7). However,
model performance (Table
in general across all dependent variables, models trained with GLI,
7). However, in general across all dependent variables, models trained with GLI, MGRVI, MGRVI, and RGBVI
explained
and RGBVI a greater proportion
explained of variation
a greater proportion in theof dependent
variation in variable compared variable
the dependent to those
Remote Sens. 2023, 15, 580 13 of 18

trained with VARI and ExG. The previous literature typically evaluated some combination
of visible-spectrum and multispectral VIs to determine the best predictor of crop growth
parameters; thus, all five VIs utilized in this study were rarely evaluated at the same time.
In contrast to the current study, Barbosa et al. [35] evaluated visible-spectrum VIs in grass
production and determined MGRVI was effective at differentiating vegetation from soil, but
GLI, RGBVI, and ExG were not. However, they had no method for radiometric correction,
and concluded that high radiometric variability of images contributed to the inefficacy
of GLI, RGBVI, and ExG. Radiometric variability was controlled for in the current study,
which could help explain the low variability between models developed for all five Vis.
Likewise, Lussem et al. [16] also reported that RGBVI and GLI were poor predictors of
biomass production in grass forage systems and warned that VARI is prone to saturation
effects at later growth stages which is a common issue amongst all visible-spectrum and
multispectral vegetation indices. Prabhakara et al. [21] also stated that VARI could effec-
tively predict grass cover crop biomass levels at early growth stages, but its predictive
capacity was significantly reduced later in the growing season likely due to saturation
issues. However, many studies have reported that RGBVI performs moderate to well at
predicting biomass levels in grassland production systems [14,15,36]. Specifically, Bareth
et al. [36] reported that RGBVI showed high correlation with NDVI, which is one of the
most commonly utilized multispectral Vis in agricultural research. From this finding they
concluded that visible-spectrum Vis computed from imagery captured by UAVs with RGB
sensors could be used to monitor grassland performance. Bendig et al. [14] determined
that MGRVI and RGBVI were relatively good at predicting barley biomass accumulation
prior to the boot growth stage. Similarly, Yeom et al. [37] concluded that MGRVI was able
to reliably discern differences in cotton and sorghum growth across the growing season
and tillage treatments and could represent an efficient and economical alternative to mul-
tispectral imaging. In the current study, the inclusion of exogenous factors that control
crop growth and performance likely reduced the potential impact of any saturation effect
on the predictive models, coupled with all UAV flights occurring prior to CR reaching
the boot growth stage and transitioning into reproductive growth. Further research is
needed to determine if visible-spectrum Vis coupled with weather and geographic data
can produce reliable predictions after CR reaches the boot growth stage and proceeds to
reproductive growth.

4.2. How Accurately Can Visible-Spectrum Vegetation Indices Predict Cereal Rye Biomass, Carbon,
Nitrogen, Phosphorus, Potassium, and Sulfur Concentration and Content?
Goodness-of-fit statistics including adjusted-R2 and %RMSE were used to evaluate the
trained models for CR biomass and nutrient concentration and content using the complete
testing dataset (Table 10). Due to Vis coupled with weather and geographic data produced
models with satisfactory performance for all content-based response variables investigated
in the current experiment and CR biomass is a content-based measure only, the discussion
on model prediction accuracy will focus on the complex models developed using CR
biomass and nutrient content.
The CR biomass predictive models developed in this study tested using the complete
testing dataset had an adjusted-R2 of 0.79 to 0.81 and %RMSE of 9–10%, respectively,
meaning that the model explained 80–81% of the variation in the dependent variable and
that the difference between predicted and actual values were 9–10% of the range in the
measured data. However, when examining model performance on an individual field basis
the model trained with each of the vegetation indices had greater predictive capacity for
field 2 (adj. R2 = 0.85) than field 1 (adj. R2 = 0.55–0.68), a trend that held true for all content-
based CR response variables (Figure 2A–C). Previous literature evaluating the predictive
capacity of visible-spectrum VIs for crop biomass accumulation produced models with
R2 values of 0.36 to 0.83, though many of these studies were not for cover crops and none
were specific to CR [14–16,21]. Other studies which evaluated cover crop biomass using
multispectral VIs produced models for biomass accumulation with R2 values between
Remote Sens. 2023, 15, 580 14 of 18

0.32 and 0.93, which were comparable to the results obtained in this study using visible-
spectrum VIs [18,20–22]. However, other studies have showed poor correlation between
VIs and cover crop biomass with poor results primarily contributed to small ranges of
biomass and VI values collected in the studies [38,39]. The variation in results within
the previous literature could be explained by studies demonstrating that the correlation
between VIs and crop characteristics decreases as crop growth stage increases [40–44].
Furthermore, much of the previous literature focused on simple linear regression between
VIs and crop biomass in order to develop predictive models and used images from a single
point in time rather than multitemporal imaging to capture changes in biomass over time.
Therefore, the goodness-of-fit for the CR biomass accumulation model in this study could
be explained by the multitemporal nature of the imaging, the use of radiometric calibration,
the inclusion of geographic and weather data that help control CR growth, and the fact that
all imaging occurred prior to reproductive growth while CR was at the early booting stage
or younger, helping to avoid issues of VI saturation and radiometric variability observed in
other studies [16,35,36].
No studies have been conducted using UAV imagery to compute VIs for the predic-
tion of C accumulation in CR or other crop species. In this study, the C accumulation
models that were developed had adjusted-R2 values of 0.79 to 0.81 and %RMSE of 9–10%.
When tested on individual fields adjusted R2 of field 1 was 0.55–0.68 and 0.85 for field 2
(Figure 2D–F). These goodness-of-fit statistics suggest that content-based CR C accumula-
tion can be predicted with relative accuracy using UAV-based RGB imagery coupled with
geographic and weather data. Carbon accumulation is strongly correlated to crop biomass
production hence the strong similarities between the models for carbon and biomass. Cover
cropping can improve average annual soil organic carbon stock increases [45]. Thus, cover
cropping is an essential method of potential carbon sequestration in the emerging carbon
credit market, which is developed to provide producers employing regenerative agricul-
tural practices with payments per unit of carbon sequestered within their cropping systems.
Having a method for rapidly and effectively predicting CR C content could aid in streamlin-
ing the evaluation of C sequestration in cropping systems containing CR. Thus, the model
developed in this study for the estimation of CR C could be of utmost importance to these
developing C markets.
The ability to predict CR N accumulation could prove critical to identifying N fertilizer
management strategies for cash crops grown following CR. It could allow producers to
vary nitrogen rates based on the spatial variability of CR N accumulation predicted using
imagery from UAV platforms. In this experiment, the model performance for content-based
CR N from the complete testing dataset (adj. R2 = 0.76–0.79, %RMSE = 5–6%) proved
adequate, suggesting that estimation of CR N accumulation using visible-spectrum VIs
coupled with weather and geographic data is possible. Testing the model prediction
capacity on an individual field basis results in adjusted-R2 of 0.62–0.74 for field 1 and 0.80
for field 2 (Figure 2G–I). Similar to biomass, studies have been conducted to estimate crop
N status using UAV based VIs though the majority represent crops other than cover crops
and focus on simple linear regression models between VIs and crop N status. For example,
Fu et al. [46] used visible spectrum VIs to estimate winter wheat N status and found that
they could explain 39%–56% of the variation in winter wheat N content. Similarly, Lu
et al. [19] found R2 values of 0.25–0.47 when utilizing UAV-based RGB VIs to estimate leaf
nitrogen content in corn. Studies specific to cover crop N content estimation have found R2
values between 0.17 and 0.93, though these studies focused on the use of multispectral VIs
rather than visible-spectrum VIs [18,22]. Again, similar to previous findings for biomass,
there is potential for saturation effects of VIs at later growth stages. However, the CR
N prediction model developed in the experiments performed satisfactorily and was able
to avoid issues of VI saturation observed in the previous literature, likely due to the
multitemporal nature of the imaging, the use of radiometric calibration, the inclusion of
geographic and weather data that help control CR growth, and the fact that all imaging
occurred prior to reproductive growth while CR was at the early booting stage or younger.
Remote Sens. 2023, 15, 580 15 of 18

Within the current literature there are limited studies which evaluate the use of spectral
reflectance to estimate the P, K, and S status of growing crops. Studies that have been con-
ducted relied on multispectral and hyperspectral reflectance data collected while walking
fields with handheld sensors [23–26]. Furthermore, no studies exist that utilize visible
spectrum VIs computed from UAV-based RGB imagery to predict P, K, and S accumulation
in CR, or any other crop. Thus, the satisfactory performance as evaluated by goodness-
of-fit statistics for the CR P (adj. R2 = 0.78–0.80, %RMSE = 9–10%), K (adj. R2 = 0.79–0.81,
%RMSE = 9%), and S (adj. R2 = 0.74–0.77, %RMSE = 10%) accumulation models in this
study could prove to be of utmost importance in the development of future models for P, K,
and S accumulation in other crops. Results of model performance on an individual field
basis can be seen in Figure 3.

4.3. What Potential Limitations Exist in the Currently Developed Models for Cereal Rye Biomass
and Nutrient Concentration and Content?
Potential limitations in the current study include geographic scale, year-to-year ap-
plicability, and applicability to species other than CR. In this study, UAV flights were only
performed at two fields in Indiana. The capacity to extrapolate the developed models based
on longitude and latitude is limited due to only having two field locations in the current
study. However, the authors felt it was important to include these variables within the
current models to allow room for future expansion and incorporation of data from other
sources. Moving forward, this study should be repeated in fields across multiple states
encompassing greater geographic and climatic variability. This could allow for the models
to better incorporate differences in weather and geographic data, potentially leading to
CR biomass and nutrient concentration and content models applicable at scale within
different regions in the United States. In addition, other input variables that can affect CR
growth should be collected and utilized within the models, such as soil type, drainage
class, and soil fertility data. Another potential limitation of the current study is in the
year-to-year applicability of the biomass and nutrient accumulation models. Since the data
used for developing the models was collected during a single CR growing season, the
study should be repeated to investigate the year-to-year efficacy of the models to estimate
content-based CR biomass, C, N, P, K, and S. Finally, the models developed in the current
study are limited to the prediction of biomass and nutrient accumulation in CR cover crops
prior to the booting growth stage. Further research is needed to collect model input data
for CR at growth stages beyond the boot stage, and to determine the efficacy of models
developed in the current study to predict CR biomass and nutrient accumulation at later
growth stages. Additionally, while CR is the most commonly utilized cover crops species
in the United States, other overwintering grasses and legumes are growing in popularity in
certain regions. Thus, the scope of the current study should be expanded to include the
development of models for other cover crop species including grasses other than CR and
overwintering legumes.

5. Conclusions
Prior to conducting this experiment, it was hypothesized that visible-spectrum veg-
etation indices obtained by commercially available unmanned aerial vehicles outfitted
with standard RGB sensors could be used to accurately predict CR biomass, C, N, P, K,
and S accumulation. The results from this study indicate that models developed using
simple linear regression between visible-spectrums VIs and measured CR characteristics
performed poorly in the prediction of both concentration and content-based CR variables.
However, complex models developed by coupling visible-spectrum VIs with weather and
geographic data can be used to develop individual models with satisfactory performance
for content-based measures of CR biomass, C, N, P, K, and S and concentration-based
measures of CR N, P, and S accumulation. Specifically, GLI, MGRVI, and RGBVI provided
similar predictive capacity and comparatively outperformed VARI and ExG. The complex
content-based models developed in this study were able to explain 74–81% of the varia-
Remote Sens. 2023, 15, 580 16 of 18

tion within the measured CR data. However, when testing the models on an individual
field basis, MGRVI outperformed GLI and RGBVI for all content-based CR characteristics
regardless of field.
The results from this study have the potential to influence key on-farm management
decisions, including CR termination and soil fertility management. The capacity to use
commercially available UAVs and publicly available geographic and weather data to rapidly
assess CR biomass and nutrient accumulation could allow producers to analyze real-time
data and make informed decisions regarding CR termination. Furthermore, utilizing
the models developed in this study to understand spatial variability in CR biomass and
nutrient accumulation could elucidate the effect of CR biomass and nutrient accumulation
on subsequently grown cash crops, allow producers to make informed decisions regarding
cover crop and soil fertility management, and aid in the development of variable rate maps
for fertilizer applications based on CR growth.

Author Contributions: Conceptualization, R.T.R. and S.D.A.; methodology, R.T.R., J.R.S., K.C. and
Y.Y.; software, R.T.R. and K.C.; validation, J.J.C., J.J. and Y.Y.; formal analysis, R.T.R. and K.C.;
investigation, R.T.R.; resources, R.T.R., J.R.S. and S.D.A.; data curation, R.T.R.; writing—original
draft preparation, R.T.R.; writing—review and editing, R.T.R., J.R.S., K.C., J.J., Y.Y., J.J.C. and S.D.A.;
visualization, R.T.R. and K.C.; supervision, S.D.A., J.J.C., J.J. and Y.Y.; project administration, R.T.R.
and S.D.A. All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: The data presented in this study are available upon reasonable request
from the corresponding author.
Acknowledgments: The authors would like to acknowledge the following individuals for providing
technical support throughout the course of the project: Joel Wahlman, Alex Helms, Asmita Gautam,
Adebukola Dada, and Isaac Armstrong.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. SARE-CTIC. 2015 Cover Crop Survey. Sustainable Agriculture Research and Education Conservation Technology Information
Center, 2015. Available online: https://www.sare.org/wp-content/uploads/2014-2015-Cover-Crop-Report.pdf (accessed on
7 July 2021).
2. SARE-CTIC. 2017 Cover Crop Survey. Sustainable Agriculture Research and Education Conservation Technology Information
Center, 2017. Available online: https://www.sare.org/wp-content/uploads/2016-2017-Cover-Crop-Survey-Report.pdf (accessed
on 7 July 2021).
3. Strock, J.S.; Porter, P.M.; Russelle, M.P. Cover cropping to reduce nitrate loss through subsurface drainage in the northern US
Corn Belt. J. Environ. Qual. 2004, 33, 1010–1016. [CrossRef]
4. Kaspar, T.C.; Jaynes, D.B.; Parkin, T.B.; Moorman, T.B.; Singer, J.W. Effectiveness of oat and rye cover crops in reducing nitrate
losses in drainage water. Agric. Water Manag. 2012, 110, 25–33. [CrossRef]
5. Lacey, C.G.; Armstrong, S.D. In field measurements of nitrogen mineralization following fall applications of N and the termination
of winter cover crops. Air Soil Water Res. 2014, 7, ASWR-S13861. [CrossRef]
6. Ruffatti, M.D.; Roth, R.T.; Lacey, C.G.; Armstrong, S.D. Impacts of nitrogen application timing and cover crop inclusion on
subsurface drainage water quality. Agric. Water Manag. 2019, 211, 81–88. [CrossRef]
7. Odell, R.T.; Melsted, S.W.; Walker, W.M. Changes in organic carbon and nitrogen of Morrow Plot soils under different treatments,
1904–1973. Soil Sci. 1984, 137, 160–171. [CrossRef]
8. Danso, S.K.; Labandera, C.; Pastorini, D.; Curbelo, S. Herbage yield and nitrogen fixation in a triple species mixed sward of white
clover, lotus and fescue. Soil Biol. Biochem. 1991, 23, 65–70. [CrossRef]
9. Hartwig, N.L.; Ammon, H.U. Cover crops and living mulches. Weed Sci. 2002, 50, 688–699. [CrossRef]
10. Nevins, C.J.; Lacey, C.; Armstrong, S. The synchrony of cover crop decomposition, enzyme activity, and nitrogen availability in a
corn agroecosystem in the Midwest United States. Soil Tillage Res. 2020, 197, 104518. [CrossRef]
11. Muñoz, J.D.; Steibel, J.P.; Snapp, S.; Kravchenko, A.N. Cover crop effect on corn growth and yield as influenced by topography.
Agric. Ecosyst. Environ. 2014, 189, 229–239. [CrossRef]
12. Muñoz, J.D.; Finley, A.O.; Gehl, R.; Kravchenko, S. Nonlinear hierarchical models for predicting cover crop biomass using
Normalized Difference Vegetation Index. Remote Sens. Environ. 2010, 114, 2833–2840. [CrossRef]
13. Hassler, S.C.; Baysal-Gurel, F. Unmanned aircraft system (UAS) technology and applications in agriculture. Agronomy 2019, 9, 618.
[CrossRef]
Remote Sens. 2023, 15, 580 17 of 18

14. Bendig, J.; Yu, K.; Aasen, H.; Bolten, A.; Bennertz, S.; Broscheit, J.; Gnyp, M.L.; Bareth, G. Combining UAV-based plant height
from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley. Int. J. Appl. Earth Obs.
Geoinf. 2015, 39, 79–87. [CrossRef]
15. Possoch, M.; Bieker, S.; Hoffmeister, D.; Bolten, A.; Schellberg, J.; Bareth, G. Multi-temporal crop surface models combined with
the RGB vegetation index from UAV-based images for forage monitoring in grassland. Int. Arch. Photogramm. Remote Sens. Spat.
Inf. Sci. 2016, 41, 991. [CrossRef]
16. Lussem, U.; Bolten, A.; Gnyp, M.L.; Jasper, J.; Bareth, G. Evaluation of RGB-based vegetation indices from UAV imagery to
estimate forage yield in grassland. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2018, 42, 1215–1219. [CrossRef]
17. Acorsi, M.G.; das Dores Abati Miranda, F.; Martello, M.; Smaniotto, D.A.; Sartor, L.R. Estimating biomass of black oat using
UAV-based RGB imaging. Agronomy 2019, 9, 344. [CrossRef]
18. Yuan, M.; Burjel, J.C.; Isermann, J.; Goeser, N.J.; Pittelkow, C.M. Unmanned aerial vehicle–based assessment of cover crop biomass
and nitrogen uptake variability. J. Soil Water Conserv. 2019, 74, 350–359. [CrossRef]
19. Lu, J.; Cheng, D.; Geng, C.; Zhang, Z.; Xiang, Y.; Hu, T. Combining plant height, canopy coverage and vegetation index from
UAV-based RGB images to estimate leaf nitrogen concentration of summer maize. Biosyst. Eng. 2021, 202, 42–54. [CrossRef]
20. Hively, W.D.; Lang, M.; McCarty, G.W.; Keppler, J.A.S.O.N.; Sadeghi, A.; McConnell, L.L. Using satellite remote sensing to
estimate winter cover crop nutrient uptake efficiency. J. Soil Water Conserv. 2009, 64, 303–313. [CrossRef]
21. Prabhakara, K.; Hively, W.D.; McCarty, G.W. Evaluating the relationship between biomass, percent groundcover and remote
sensing indices across six winter cover crop fields in Maryland, United States. Int. J. Appl. Earth Obs. Geoinf. 2015, 39, 88–102.
[CrossRef]
22. Xu, M.; Lacey, C.G.; Armstrong, S.D. The feasibility of satellite remote sensing and spatial interpolation to estimate cover crop
biomass and nitrogen uptake in a small watershed. J. Soil Water Conserv. 2018, 73, 682–692. [CrossRef]
23. Mutanga, O.; Kumar, L. Estimating and mapping grass phosphorus concentration in an African savanna using hyperspectral
image data. Int. J. Remote Sens. 2007, 28, 4897–4911. [CrossRef]
24. Mahajan, G.R.; Sahoo, R.N.; Pandey, R.N.; Gupta, V.K.; Kumar, D. Using hyperspectral remote sensing techniques to monitor
nitrogen, phosphorus, sulphur and potassium in wheat (Triticum aestivum L.). Precis. Agric. 2014, 15, 499–522. [CrossRef]
25. Lu, J.; Yang, T.; Su, X.; Qi, H.; Yao, X.; Cheng, T.; Zhu, Y.; Cao, W.; Tian, Y. Monitoring leaf potassium content using hyperspectral
vegetation indices in rice leaves. Precis. Agric. 2020, 21, 324–348. [CrossRef]
26. Ma, B.L.; De Haan, B.; Zheng, Z.; Xue, A.G.; Chen, Y.; de Silva, N.D.; Byker, H.; Mountain, N.; Yan, W. Exploring the relationships
between biomass production, nutrient acquisition, and phenotypic traits: Testing oat genotypes as a cover crop. J. Plant Nutr.
2022, 45, 2931–2944. [CrossRef]
27. Havlin, J.L.; Soltanpour, P.N. A nitric acid plant tissue digest method for use with inductively coupled plasma spectrometry.
Commun. Soil Sci. Plant Anal. 1980, 11, 969–980. [CrossRef]
28. USEPA. Method 3052: Microwave-Assisted Acid Digestion of Siliceous and Organically Based Matrices; United States Environmental
Protection Agency: Washington, DC, USA, 1996.
29. McMaster, G.S.; Wilhelm, W.W. Growing degree-days: One equation, two interpretations. Agric. For. Meteorol. 1997, 87, 291–300.
[CrossRef]
30. Honeycutt, C.W.; Potaro, L.J. Field evaluation of heat units for predicting crop residue carbon and nitrogen mineralization. Plant
Soil 1990, 125, 213–220. [CrossRef]
31. Rusch, H.L.; Coulter, J.A.; Grossman, J.M.; Johnson, G.A.; Porter, P.M.; Garcia y Garcia, A. Towards sustainable maize production
in the US upper Midwest with interseeded cover crops. PLoS ONE 2020, 15, e0231032. [CrossRef]
32. Gitelson, A.A.; Kaufman, Y.J.; Stark, R.; Rundquist, D. Novel algorithms for remote estimation of vegetation fraction. Remote Sens.
Environ. 2002, 80, 76–87. [CrossRef]
33. Louhaichi, M.; Borman, M.M.; Johnson, D.E. Spatially located platform and aerial photography for documentation of grazing
impacts on wheat. Geocarto Int. 2001, 16, 65–70. [CrossRef]
34. Woebbecke, D.M.; Meyer, G.E.; Von Bargen, K.; Mortensen, D.A. 1995. Color indices for weed identification under various soil,
residue, and lighting conditions. Trans. ASAE 1995, 38, 259–269. [CrossRef]
35. Barbosa, B.D.S.; Ferraz, G.A.S.; Gonçalves, L.M.; Marin, D.B.; Maciel, D.T.; Ferraz, P.F.P.; Rossi, G. RGB vegetation indices applied
to grass monitoring: A qualitative analysis. Agron. Res. 2019, 17, 349–357.
36. Bareth, G.E.; Bolten, A.N.; Hollberg, J.E.; Aasen, H.; Burkart, A.; Schellberg, J. Feasibility study of using non-calibrated UAV-based
RGB imagery for grassland monitoring: Case study at the Rengen Long-term Grassland Experiment (RGE), Germany. DGPF Tag.
2015, 24, 55–62.
37. Yeom, J.; Jung, J.; Chang, A.; Ashapure, A.; Maeda, M.; Maeda, A.; Landivar, J. Comparison of vegetation indices derived from
UAV data for differentiation of tillage effects in agriculture. Remote Sens. 2019, 11, 1548. [CrossRef]
38. Hunt, E.R.; Hively, W.D.; McCarty, G.W.; Daughtry, C.S.T.; Forrestal, P.J.; Kratochvil, R.J.; Carr, J.L.; Allen, N.F.; Fox-Rabinovitz,
J.R.; Miller, C.D. NIR-green-blue high-resolution digital images for assessment of winter cover crop biomass. GIScience Remote
Sens. 2011, 48, 86–98. [CrossRef]
39. Roth, L.; Streit, B. Predicting cover crop biomass by lightweight UAS-based RGB and NIR photography: An applied photogram-
metric approach. Precis. Agric. 2018, 19, 93–114. [CrossRef]
Remote Sens. 2023, 15, 580 18 of 18

40. Naveed, M.; Et, T. Hyperspectral estimation model for nitrogen contents of summer corn leaves under rainred conditions. Pak. J.
Bot. 2013, 45, 1623–1630.
41. Yu, K.; Li, F.; Gnyp, M.L.; Miao, Y.; Bareth, G.; Chen, X. Remotely detecting canopy nitrogen concentration and uptake of paddy
rice in the Northeast China Plain. ISPRS J. Photogramm. Remote Sens. 2013, 78, 102–115. [CrossRef]
42. Cheng, T.; Rivard, B.; Sánchez-Azofeifa, A.G.; Féret, J.B.; Jacquemoud, S.; Ustin, S.L. Deriving leaf mass per area (LMA) from
foliar reflectance across a variety of plant species using continuous wavelet analysis. ISPRS J. Photogramm. Remote Sens. 2014, 87,
28–38. [CrossRef]
43. Li, F.; Miao, Y.; Feng, G.; Yuan, F.; Yue, S.; Gao, X.; Liu, Y.; Liu, B.; Ustin, S.L.; Chen, X. Improving estimation of summer maize
nitrogen status with red edge-based spectral vegetation indices. Field Crops Res. 2014, 157, 111–123. [CrossRef]
44. Xu, X.G.; Zhao, C.J.; Wang, J.H.; Zhang, J.C.; Song, X.Y. Using optimal combination method and in situ hyperspectral measure-
ments to estimate leaf nitrogen concentration in barley. Precis. Agric. 2014, 15, 227–240. [CrossRef]
45. Poeplau, C.; Don, A. Carbon sequestration in agricultural soils via cultivation of cover crops–A meta-analysis. Agric. Ecosyst.
Environ. 2015, 200, 33–41. [CrossRef]
46. Fu, Y.; Yang, G.; Li, Z.; Song, X.; Li, Z.; Xu, X.; Wang, P.; Zhao, C. Winter wheat nitrogen status estimation using UAV-based RGB
imagery and gaussian processes regression. Remote Sens. 2020, 12, 3778. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.