Computers and Electronics in Agriculture 153 (2018) 213–225

Contents lists available at ScienceDirect

Computers and Electronics in Agriculture

journal homepage: www.elsevier.com/locate/compag

Original papers

Integration of high resolution remotely sensed data and machine learning T

techniques for spatial prediction of soil properties and corn yield
⁎
Sami Khanala, , John Fultonb, Andrew Klopfensteinb, Nathan Douridasc, Scott Shearerb
a
Department of Food, Agricultural and Biological Engineering, Ohio State University, Wooster, OH 44691, USA
b
Department of Food, Agricultural and Biological Engineering, Ohio State University, Columbus, OH 43210, USA
c
Farm Science Review, Ohio State University, London, OH 43140, USA

A R T I C LE I N FO A B S T R A C T

Keywords: Widespread adoption of precision agriculture requires timely acquisition of low-cost, high quality soil and crop
Remote sensing yield maps. Integration of remotely sensed data and machine learning algorithms offers cost-and time-effective
Soil approach for spatial prediction of soil properties and crop yield compared to conventional approaches. The
DEM objectives of this study were to: (i) evaluate the role of remotely sensed images; (ii) compare the performance of
Yield
various machine learning algorithms; and (iii) identify the importance of remotely sensed image-derived vari-
Mapping
ables, in spatial prediction of soil properties and corn yield. This study integrated field based data on five soil
properties (i.e., soil organic matter (SOM), cation exchange capacity (CEC), magnesium (Mg), potassium (K), and
pH) and yield monitor based corn yield data with multispectral aerial images and topographic data, both col-
lected in 2013, from seven fields at the Molly Caren Farm near London, Ohio. Digital elevation model data, at a
resolution of 1 m, was used to derive topographic properties of the fields. Multispectral images collected at bare-
soil conditions, at a resolution 0.30 m, were used to derive soil and vegetation indices. Models developed for
prediction of soil properties and corn yield using linear regression (LM) and five machine learning algorithms
(i.e., Random Forest (RF); Neural Network (NN); Support Vector Machine (SVM) with radial and linear kernel
functions; Gradient Boosting Model (GBM); and Cubist (CU)) were evaluated in terms of coefficient of de-
termination (R2) and root mean square error (RMSE). Machine learning algorithms were found to outperform LM
algorithm for most of the times with a higher R2 and lower RMSE. Based on models for seven fields, on average,
NN provided the highest accuracy for SOM (R2 = 0.64, RMSE = 0.44) and CEC (R2 = 0.67, RMSE = 2.35); SVM
for K (R2 = 0.21, RMSE = 0.49) and Mg (R2 = 0.22, RMSE = 4.57); and GBM for pH (R2 = 0.15, RMSE = 0.62).
For corn yield, RF consistently outperformed other models and provided higher accuracy (R2 = 0.53,
RMSE = 0.97). Soil and vegetation indices based on bare-soil imagery played a more significant role in de-
monstrating in-field variability of corn yield and soil properties than topographic variables. The accuracy of the
models developed for prediction of soil properties and corn yield observed in this study suggested that the
approach of integrating remotely sensed data and machine learning algorithms are promising for mapping soil
properties and corn yield at a local scale, which can be useful in locating areas of potential concerns and im-
plementing site-specific farming practices.

1. Introduction
Accurate and detailed information on soil properties and crop
health is essential for optimization of farm management practices for
sustainable production of agricultural goods and services (Souza et al.,
2016; Yao et al., 2016), as well as for environmental modeling, and
environmental risk assessment and management. High resolution maps
of soil properties and crop yields enable producers and the agricultural
community to identify in-field variability in soil and crop health and
target areas within the field for soil fertility interventions, improved
crop productivity, and better economic outcomes.
Traditional approaches for mapping soil properties and crop yield
have mostly relied on field surveys and the use of costly equipment. Soil
sampling and laboratory analyses are conducted for evaluating soil
health, and harvester-mounted yield monitors are used for under-
standing the spatial variability in crop yield. These approaches however
are time consuming and expensive, especially when mapping needs to
be done at regional, national, and global scales (Mulder et al., 2011;

⁎
Corresponding author.
E-mail address: Khanal.3@osu.edu (S. Khanal).

https://doi.org/10.1016/j.compag.2018.07.016
Received 9 January 2018; Received in revised form 17 April 2018; Accepted 8 July 2018
Available online 23 August 2018
0168-1699/ © 2018 Elsevier B.V. All rights reserved.
S. Khanal et al.
Table 1
Basic characteristics of the fields studied, including field size, slope, dominant soil map unit, dominant soil order, number of soil samples, and field management
practices.
Field Size (ha) Slope (%) Soil map unit
1B 11 4.37 Ochraqualfs (40.7%), Argiaquolls (31%), Epiaqualfs (18%), Argiudolls (10.3%)
1C 5.3 5.86 Ochraqualfs (74%), Argiaquolls (26%)
1D 6.5 4.35 Ochraqualfs (94.8%), Argiaquolls (5.2%)
9A 13.3 5.7 Ochraqualfs (58%), Argiaquolls (42%)
12D 17.5 4.98 Argiaquolls (46%), Hapludalfs (27.9%); Ochraqualfs (23.8%)
MISD 12 9.26 Ochraqualfs (82.5%), Argiaquolls (18.5%)
PENIN 3.8 9.6 Ochraqualfs (98%)
Tillage: NT – No Till; CT – conventional tillage (i.e., field cultivator was used prior to planting the crop). Crop Rotation: C- Corn; S- Soybean; W-Wheat.
Yang et al., 2014). Furthermore, these approaches have several lim-
itations. For example, yield monitor based data can only be collected at
harvest and, thus, cannot be used for in-season crop management. Also,
these data are spatially coarse and fail to capture in-field variability in
soil and crop health (Souza et al., 2016).
Remotely sensed images have the potential to overcome the lim-
itations of traditional approaches and improve the spatial coverage of
soil and crop yield data (Peng et al., 2015; Stevens et al., 2013; Yao
et al., 2016). Studies have demonstrated that many soil properties can
be estimated by integrating georeferenced field collected soil and crop
data with spectral properties of soil acquired by sensors onboard sa-
tellite and aircrafts. Dobos et al. (2001) found the Advanced Very High
Resolution Radiometer (AVHRR) satellite data and DEM derived terrain
variables to be powerful in characterizing soil-forming environments
and delineation of soil patterns on a regional scale. Scudiero et al.
(2014) found multi-year spectral reflectance data from the Landsat to
be a reliable indicator of soil salinity in the western San Joaquin Valley
in California, USA. Several studies have also been conducted focusing
on crop yield mapping by integrating remotely sensed images acquired
from satellite (Lobell et al., 2015), aircraft (Yang et al., 2014), and
unmanned aerial vehicles (Geipel et al., 2014; Shi et al., 2016).
Despite prior efforts, further exploration on the application of re-
motely sensed data for mapping of soil properties and crop yield is
needed. The success in prediction and mapping of soil properties, and
crop health and yield using remotely sensed data to a large extent de-
pends on the availability, quality, and timing of remotely sensed data
collection (Blasch et al., 2015), as well as the approaches used for
model development (Forkuor et al., 2017; Morellos et al., 2016). Prior
studies have mostly focused on estimating crop yield and soil properties
at regional scales rather than for individual fields (Lobell et al., 2015).
These studies used satellite acquired remotely sensed images with
coarse spatial resolution. Mapping of soil properties and crop yield at
coarse resolution is of limited use for resource assessment and man-
agement at a field scale; whereas, maps at high resolution can help the
agricultural and environmental community to cost-effectively detect
and characterize the extent of soil and crop health issues. This in-
formation can be used for prescription-based farming that help improve
economic outcome and environmental footprints associated with agri-
cultural practices.
A linear regression algorithm is the most commonly used approach
to estimate crop yield and soil properties (Geipel et al., 2014; Lobell
et al., 2015). However, it has limitations in handling non-linear re-
lationships between response and predictor variables that usually exist
in heterogeneous agricultural landscapes. There are several machine
learning algorithms that can overcome this limitation, and provide
better prediction of soil variables and crop yield. However, comparisons
of the traditional linear regression algorithm to machine learning al-
gorithms for prediction of soil properties and crop yield are limited. In
addition to understanding the performance of various models in map-
ping soil properties and crop yield, there is a need to identify the re-
lative importance of variables for enhancing the predictive ability of the
models.
214
Computers and Electronics in Agriculture 153 (2018) 213–225
Dominant soil order Sample number Tillage Crop rotation
Alfisols 27 NT C-C-S
Alfisols 17 CT C-S-C
Alfisols 20 NT C-S-C
Alfisols 39 CT C-S-C
Mollisols 49 CT W-S-C
Alfisols 36 CT S-W-C
Alfisols 12 NT C-C-S
The objectives of this study were to: (i) examine the role of remotely
sensed images; (ii) evaluate the performance of linear regression and
machine learning algorithms; and (iii) identify the importance of re-
motely sensed image-derived variables, for prediction and mapping of
soil properties and corn yield. Seven statistical models were developed
for predicting corn yield and soil properties. Soil properties examined in
this study included soil organic matter (SOM), cation exchange capacity
(CEC), potassium (K), magnesium (K), and pH. Prior studies (Forkuor
et al., 2017; Morellos et al., 2016) have used remotely sensed data for
mapping of soil properties; however, this is to our knowledge the first
evaluation of remotely sensed images of bare soil surface at a spatial
resolution < 1 m from multiple fields for prediction and mapping of
both soil properties and corn yield.
2. Materials and methods
2.1. Study area
Fields examined in this study are located in the northwest part
(83°26′14.3″–83°26′49.24″W, 39°56′37.82″–39°57′28.7″N) of Madison
County, Ohio, USA. The dominant soil types in these fields are
Ochraqualfs (Crosby-Lewisburg Complex), Argiaquolls (Kokomo Silty
Clay Loam, Westland silty clay loam), and Hapludalfs (Miamian Silt
Loam, Eldean silt loam, Thackery variant silt loam) (Table 1). These
fields are gently rolling, with the mean slope ranging from 4.35 to
9.26%. The average elevation of the fields is 311 m. The mean annual
rainfall (1981–2016) is 998 mm with approximately 58% of annual
rainfall occurring between April and September. The mean annual
temperature is 10.9 °C, with daily temperatures ranging from −6.7
(minimum) to 29.2 °C (maximum).
A strong spatial variability in soil properties was observed in the
study area. Soil properties were characterized by large range and high
standard deviation, with SOM in the range of 1.2–4.9 (%), CEC of
6–27.3 (meq/100 g), K of 1.2–5.9 (%), Mg of 10.2–36.7 (%), and pH of
5–78 (Table 2).
2.2. Data
2.2.1. Soil and crop data
A total of 200 soil samples were collected from seven bare fields
(Table 1) in October 1, 2013. In each field, samples were taken at a
depth of 18 cm on 1-acre intervals. The samples were air-dried at 49 °C
(120 °F) for 24 h, sieved, and sent to the Spectrum Analytic lab (Spec-
trum Analytic, 2017) for soil analyses. As field 12D has very different
soil map units compared to six other fields (Table 1), soil samples were
classified into two dominant soil orders (Alfisols and Mollisols), and a
“group” was introduced as an independent variable for model devel-
opment.
Corn yield data were available for only one field (i.e.,12D), and
thus, the models for corn yield prediction were focused on this field
only. Corn yield data were recorded by a John Deere yield monitoring
system during harvest. The yield monitor was calibrated before and
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

Table 2 2.2.2. Remotely sensed data

Summary of soil properties and corn yield for study area. Remotely sensed data used in this study included high spatial re-
Soil variables Minimum Maximum Mean Standard deviation solution multispectral images collected from bare fields and digital
elevation model (DEM). Multispectral images (Fig. 1) were obtained in
All data May of 2013 under the Ohio Statewide Imagery Program. They were
SOM (%) 1.20 4.90 2.31 0.71
collected with a Leica ADS80 digital camera onboard aircraft, and
CEC (meq/100 g) 6.00 27.30 15.31 4.18
K (%) 1.20 5.90 2.28 0.56
rectified using LiDAR data, and have visible (red, green, and blue) and
Mg (%) 10.20 36.70 26.24 5.24 near-infrared wavebands at 0.30 m spatial resolution. Six soil and ve-
pH 5 7.8 6.75 0.65 getation indices that were found useful in digital soil mapping (Ray
Corn yield (t/ha) 6.4 18.0 14.39 1.47 et al., 2004) were calculated using the combination of spectral bands in
Train data the multispectral images. Table 3 provides further details on the spec-
SOM (%) 1.2 4.9 2.32 0.68 tral indices considered in the study. Terrain variables (Table 4) were
CEC (meq/100 g) 6 27.3 15.35 4.17
extracted using DEM data, with 0.76 m resolution, available from the
K (%) 1.2 5.9 2.29 0.58
Mg (%) 10.2 36.7 26.44 5.10 Ohio Geographically Referenced Information Program. Prior to the
pH 5 7.8 6.76 0.65 calculation of terrain variables for analyses, the DEM was pre-processed
Corn yield (t/ha) 6.11 18.0 14.4 1.47 to generate a depression free DEM. To ensure the proper integration
Test Data between varying datasets, the DEM was resampled at 0.30 m resolution,
SOM (%) 1.2 4.6 2.26 0.77 the resolution of the multispectral images, using the bilinear inter-
CEC (meq/100 g) 7.1 22.5 15.1 4.15 polation method.
K (%) 1.6 3.6 2.2 0.4
To minimize the potential variance among pixels that might have
Mg (%) 11.7 36.7 25.36 5.6
pH 5.4 7.7 6.71 0.66 been introduced by various factors, such as microtopography, image
Corn yield (t/ha) 6.9 17.9 14.41 1.44 processing, and scanning, a low-pass filter with a 5 by 5 cell mask was
applied to each band of the multispectral images and the DEM (Hively
Note: Train and test data indicate soil samples and corn yield observations used et al., 2011). Bare soil imagery for field 12D was classified into three
for model development and validation, respectively. soil color classes – dark, medium and light, using supervised algorithms
including support vector machine (with linear and radial kernel),
during the harvest to minimize the potential error in yield estimates. random forest, and neural network in R software. Among these algo-
Despite proper calibration, due to changes in machine orientation and rithms, support vector machine with radial function provided the
speed, yield monitor is likely to provide erroneous yield estimates in highest classification accuracy of 81%. Details of these algorithms are
field edges (Lyle et al., 2014). Thus, a 20 m buffer was established in- provided in Section 2.3.1.
side the field edges, and the yield data from that buffer were excluded Spectral bands, spectral indices, and terrain properties were ex-
from the analyses. Additionally, yield data was checked for errors, and tracted at locations used for collecting soil samples and yield data using
errors were removed using the workflow discussed by Sudduth and ArcGIS software, and related with soil properties and corn yield to es-
Drumm (2007). tablish the relationship between remotely sensed and field-measured

Fig. 1. Seven fields used in the study. Circles and stars indicate spatial locations of soil samples used for model development and validation, respectively. Field 12D
was used for corn yield prediction. The background image is a multispectral displayed with a combination of red, green and blue wavebands. (For interpretation of
the references to colour in this figure legend, the reader is referred to the web version of this article.)

215
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

Table 3
Soil and vegetation indices considered for the analyses.
Indices Formula Index property Reference

Brightness Index (BI) 2 + G2 + B2 0.5 Average reflectance magnitude Ray et al. (2004)
⎛R ⎞
⎝ 3 ⎠
Saturation Index (SI) (R − B ) Spectral slope Ray et al. (2004)
(R + B )
Hue Index (HI) (2 ∗ R − G − B ) Primary colors Ray et al. (2004)
(G − B )
Coloration Index (CI) (R − G ) Soil color Ray et al. (2004)
(R + G )
Redness Index (RI) R2 Hematite content Ray et al. (2004)
(B × G3)
Normalized Difference Vegetation Index (NDVI) (NIR − R) Health and amount of vegetation Ray et al. (2004)
(NIR + R)

Table 4
Terrain variables considered in the study.
Parameters Definition Units References

Elevation (Elev) Height above a sea level Meter

Slope Inclination of the land surface Degree Allen et al. (2014)
Aspect Direction the slope faces Degree Davy and Koen, (2014)
Roughness (Rough) Difference between maximum and minimum elevation – Wilson et al. (2007)
Terrain Ruggedness Index (TRI) Amount of elevation difference between neighboring areas – Riley (1999)
Topographic Position Index (TPI) Measure of where a location is in the overall landscape – Wilson et al. (2007)
Flow Direction (FlowDir) Path of water flow – Kitchingman and Lai (2004)

data. To extract information from images and relate to corn yield, a
rectangle with the length equal to harvester swath width (6.32 m) and
width equal to the distance between logged data points (2 m) in a row
was drawn around each logged yield data point. This is done because
the size of area represented by each logged point in a yield monitor is
proportional to the header width and the distance travelled by the
combine harvester between logged data points. Image related in-
formation was extracted at these polygons using the zonal statistics
function of the Spatial Analyst tool in the ArcGIS. Each rectangle in-
cluded 97 pixels from the images with 0.30 m resolution, and an
average of these pixel values was related to a yield observation. It is our
understanding that the DEM and multispectral images used in this study
are the highest spatial resolution datasets ever used in mapping soil
properties.
2.3. Statistical analyses
All statistical analyses were performed using R software. Six sta-
tistical models - linear regression (LM), random forest regression (RF),
support vector machine (SVM), stochastic gradient boosting model
(GBM), neural network (NN), and cubist (CU), were developed for
predicting soil properties and corn yield. The performance of these
models were then compared to determine the best model. For the model
development, the statistical package “caret” was used. The “caret”
package allows fitting and comparisons of numerous linear and non-
linear regression models under a unified framework (Kuhn and
Johnson, 2013). To provide an unbiased sense of model effectiveness,
the total data was randomly split into training and test sets at a 4:1
ratio, where the training set was used for model calibration and the test
set was used for model evaluation. Although the splitting of data was
random, mean values of corn yield, SOM, CEC, K, Mg, and pH between
the training and test sets were ensured to be similar so that the cali-
brated models were well trained to predict the range of soil properties
and crop yield in the test dataset (Table 2).
2.3.1. Statistical models
During the model design, soil properties and corn yield were the
dependent variables, and spectral, soil color class, and terrain variables
were the independent or predictor variables. One soil property was
modeled at a time as the dependent variable against all predictor
variables. For each model, the adjusted R2 and residual standard error
were considered. During model development, random numbers are
used for splitting data for resampling and parameter estimations (Kuhn
and Johnson, 2013). To control the randomness ensuring that the same
resampling sets were used during cross-validations of models and assure
reproducible results for comparison between models, the same random
number seed was set prior to the development and training of all the
models. Variables were scaled prior to model runs to ensure that all
variables are on the same scale. Seven different models (briefly dis-
cussed below) were developed for each soil parameter and corn yield
estimation. The details on the background and mathematical function
of these models can be found in Kuhn and Johnson (2013).

Table 5
Explanatory variables selected for modeling of each soil parameter, and corn yield after stepwise regression.
Parameter Spectral variables Other variables

Soil Organic Matter (SOM) Red, blue, NIR, NDVI, BI, CI, RI, SI TRI, Group
Cation Exchange Capacity (CEC) Red, green, blue, NDVI, BI FlowDir
Potassium (K) Green, blue, NIR, NDVI, BI, CI, HI, RI, SI, Elev, TRI, Slope
Magnesium (Mg) NIR, BI, CI, HI, RI Elev, Group, Slope, TRI, FlowDir
pH Red, BI, HI, RI Group, FlowDir, Slope, TRI, Rough
Yield (Approach 1) Red, green, blue, NIR, NDVI, BI, CI, HI, RI, SI, soil class Elev, Aspect, TRI, TPI, FlowDir
Yield (Approach 2) SOM, CEC, Mg, K, pH

216
S. Khanal et al.
2.3.1.1. Linear regression model (LM). It explains dependent variable by
means of a linear combination of predictor variables. For the LM
analysis, the “lm” function was used. A stepwise regression was
conducted to address a problem of multi-collinearity in the regression
model. Stepwise regression identifies a subset of predictors based on
their statistical significance using stepwise selection using approaches,
such as forward selection, backward elimination, and a combination of
the two. For stepwise regression, the “stepAIC” function based on both
the forward and background search method was used. This function is
available in the “MASS” package of the R software, and it uses the AIC
statistics as the criteria for variable selection. Table 5 provides the list
of predictors identified by stepwise regression.
2.3.1.2. Random forest (RF). It is an ensemble learning method that is
used for both classification and regression problems. It operates by
constructing multiple decision trees and outputting either a class for
classification or mean prediction for regression of the individual trees.
Each tree in the forest is independently constructed using a unique
bootstrap sample of the training data. The best split from a randomly
selected subset of predictors is then selected. Unlike linear regression, it
requires no assumption of the probability distribution of the predictor
variables, and is robust against nonlinearity and overfitting. In the
study, RF model was developed using the “rf” function available
through “randomForest” package. The model’s performance was
optimized by tuning parameters, such as the number of predictors
that are randomly sampled as candidates for each split (i.e., mtry) and
the number of trees to grow in the forest (i.e., ntree).
2.3.1.3. Support Vector Machine (SVM). This is a machine-learning
method that constructs a hyperplane or set of hyperplanes in a high-
or infinite-dimensional space, which can be used for classification or
regression. A good separation between hyperplanes is achieved through
different types of kernel functions such as linear, radial, sigmoid, and
polynomial. For simplicity purpose, only linear and radial kernel
functions were selected in this study. The SVM models were tuned
based on bandwidth cost parameter and insensitive loss function.
2.3.1.4. Stochastic gradient boosting (SGB). This is another data mining
approach that combines the advantages of nonparametric tree-based
methods and strengths of boosting algorithms. Instead of focusing on
the complete training data, it performs boosting by selecting only a
fraction of the training data leading to a gradual improvement in the
prediction accuracy. In the study, the model’s performance was
optimized by tuning parameters such as tree depth, number of trees,
and shrinkage.
2.3.1.5. Neural network (NN). It is one of the powerful nonlinear
regression approaches, which is designed to model or mimic some
properties of biological neural networks. It consists of interconnected
processing elements called nodes or neurons that work together to
produce an output function. The connection between nodes are
described by the weights, which at the beginning are randomly
chosen, but are adjusted interactively if predicted output does not
match output of a training dataset. The resilient backpropagation
algorithm (rprop) was used because of its promising capabilities
compared to other algorithms (Riedmiller and Braun, 1993). NN
models were optimized by tuning parameters such as numbers of
hidden layer and decay rate.
2.3.1.6. Cubist model (CUB). This is a data-mining technique for
generating data driven rule-based predictive models. It works in a
similar way as decision tree regression models do. A tree is created
where the terminal leaves contain linear regression models. At each
step of the tree, there are intermediate linear models. The tree is then
reduced to a set of rules that initially are paths from the top of the tree
to the bottom, and the linear model is then adjusted to reduce the
217
Computers and Electronics in Agriculture 153 (2018) 213–225
absolute error. This model is easy to understand and interpret, and was
found to have a good predictive power (Minasny and McBratney,
2008). The model was tuned with 10 committees and 5 neighbors to
reduce the root mean square error.
The performances of machine learning algorithms were enhanced
by tuning several parameters specific to each model (discussed above)
using the tenfold cross-validation with five repetitions in the “caret”
package. A grid search strategy was used while optimizing the para-
meters specific to models. The parameters selected for model tuning are
provided in the supporting document (Table S1; see supplementary
document).
To provide comparison with other models, the same set of pre-
dictors (Table 5) were maintained for all other models. For corn yield
prediction, two approaches were used. The first approach used only
remotely sensed image-derived independent variables, and the second
approach used only soil variables, which were predicted using remotely
sensed data.
2.3.2. Model assessment and validation
The performances of the statistical models were assessed using a
repeated k-fold cross-validation resampling technique on the training
set, and then validated with the test set. For the k-fold cross-validation,
samples are randomly partitioned into k sets of roughly equal sizes. A
model is fit using all samples except the first subset, and held-out
samples are used to estimate performance measures. The first subset is
treated as the training set, and the process repeats with the second
subset held-out, and so on. This approach tests the performance of a
model on every instance in the available data set without having used it
in the training phase. In this study, a 10-fold cross-validation was re-
peated five times resulting in 50 different subsets for testing the model
efficacy. The results were then aggregated and summarized.
Statistics, including adjusted R square (hereafter referred to as “R2”)
and root mean squared error (RMSE), were used to evaluate the effec-
tiveness of model’s capabilities in predicting soil properties. R2 can be
interpreted as the proportion of the information in the data that is ex-
plained by the model. It is a measure of correlation, not accuracy. A
model with a high R2 value may not necessarily lead to accurate pre-
diction, and could systematically and significantly over and/or under
predict the data. Thus, RMSE, a function of the model residuals (i.e.,
observed values minus model predictions) Eq. (1) that represents how
far, on average, the residuals are from zero or the average distance
between observed (O) and model predictions (P) was also used.
n
1
RMSE =
n
∑ (Pi−Oi )2
i=1 (1)
2.3.3. Variable importance
A variable importance measure was estimated to understand the
relative importance of predictors to the outcome of various models.
Variable importance measure is estimated based on a method specific to
the model (Kuhn, 2017). For instance, in LM, it is computed based on
the absolute value of the t-statistics of each model parameter. In RF, it is
computed based on two common measures – increased mean square
error (IncMSE) and increased impurity index (IncNodePurity). IncMSE
measures the change in predictive power by constructing trees with and
without a predictor. IncCodePurity measures the total decrease in node
impurity from splitting on a predictor in the tree construction process,
and is averaged over all trees. For this study, the IncMSE measure was
used. In NN, variable importance is estimated based on the combination
of the absolute values of weights. In CU, it is estimated based on the
percentage of times each variable is used in a condition and/or linear
model. A varImp function in the package “caret” in the R software was
used for this purpose.
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

Fig. 2. Correlation among 24 variables for all seven fields. The abbreviation of variable are provided in Tables 3 and 4. Red texts indicate the correlation values that
are not significant at p < 0.10. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Table 6
Model performance for estimation of soil properties for all seven fields.
Cross-Validation with Training Dataset
SOM CEC K Mg pH
Model
R2 RMSE R2 RMSE R2 RMSE R2 RMSE R2 RMSE
LM 0.55 0.47 0.65 2.40 0.23 0.55 0.21 4.69 0.14 0.63
RF 0.56 0.47 0.61 2.53 0.19 0.50 0.10 4.96 0.13 0.63
SVML 0.54 0.48 0.65 2.40 0.18 0.50 0.22 4.57 0.14 0.63
SVMR 0.56 0.47 0.62 2.50 0.21 0.49 0.11 4.85 0.09 0.64
GBM 0.58 0.46 0.63 2.45 0.18 0.50 0.08 4.99 0.15 0.62
NN 0.61 0.44 0.67 2.35 0.16 0.51 0.11 5.03 0.12 0.65
CU 0.60 0.46 0.61 2.51 0.22 0.51 0.11 5.04 0.16 0.63
Validation with Test Dataset
LM 0.56 0.61 0.61 3.08 0.12 0.55 0.27 5.16 0.13 0.62
RF 0.56 0.53 0.63 3.02 0.15 0.53 0.01 5.97 0.13 0.62
SVML 0.49 0.63 0.60 3.16 0.08 0.56 0.23 5.21 0.09 0.64
SVMR 0.44 0.55 0.57 3.19 0.11 0.55 0.13 5.57 0.05 0.65
GBM 0.50 0.63 0.62 3.09 0.21 0.51 0.09 5.67 0.07 0.63
NN 0.55 0.53 0.53 3.10 0.11 0.53 0.02 6.10 0.12 0.62
CU 0.51 0.57 0.60 3.15 0.08 0.58 0.04 6.01 0.08 0.68
Overall Dataset
LM 0.55 0.50 0.64 2.54 0.21 0.55 0.22 4.78 0.13 0.63
RF 0.56 0.48 0.62 2.62 0.18 0.51 0.08 5.16 0.13 0.63
SVML 0.53 0.51 0.64 2.55 0.16 0.51 0.22 4.70 0.13 0.63
SVMR 0.54 0.49 0.61 2.64 0.19 0.50 0.11 4.99 0.09 0.64
GBM 0.56 0.49 0.63 2.58 0.18 0.50 0.08 5.13 0.13 0.62
NN 0.60 0.46 0.64 2.50 0.15 0.51 0.09 5.24 0.12 0.64
CU 0.58 0.48 0.61 2.64 0.19 0.52 0.10 5.23 0.14 0.64
Note: LM – Linear Model, RF – Random Forest, SVML– Support Vector Machine with linear kernel, SVMR– Support Vector
Machine with radial kernel, GBM – Gradient Boosting Model, NN – Neural Network, CU – Cubist Model. Bold texts indicate the
model with the least RMSE and the highest R2 for each soil parameter.

218
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

Fig. 3. Plots of predicted versus observed soil organic matter (% SOM), cation exchange capacity (CEC meq/100 g), magnesium (Mg), potassium (K), and pH for the
training and test datasets. Predictions for SOM and CEC were based on neural network; K, Mg and pH were based on support vector machine with radial function,
support vector machines with linear function, and gradient boosting model, respectively; and predicted corn yield was based on random forest algorithm.

3. Results
3.1. Relationship between soil properties, yield and remote sensing data
Soil properties were highly correlated with the individual wave-
bands (Red, Green and Blue) as well as the soil and vegetation indices
than the terrain properties of the fields. Terrain characteristics were
correlated with bare soil imagery, but not as much as the soil proper-
ties. Among seven terrain properties, elevation was found to have the
highest correlation with the individual wavebands such as green and
blue, and RI (Fig. 2). Yield of field 12D was found to have a higher
correlation with soil indices such as BI, HI and CI, followed by Mg, CEC,
SOM and elevation of the field (results not shown).
3.2. Model performance
Assessment of the models used for prediction of five soil properties
for all seven fields suggested that high resolution remotely sensed data
can predict CEC with relatively higher accuracy, followed by SOM, Mg,
K, and pH (Table 6). During cross-validation of the models, average R2
values ranged from 0.61 to 0.67 for CEC, 0.54 to 0.63 for SOM, 0.16 to
0.23 for K, 0.09 to 0.121 for Mg, and 0.09 to 0.16 for pH (Table 6).
Variability in R2 values during cross-validation of models are provided
in the supporting document (Figs. S1 and S2). Except for few models for
CEC, K, and Mg, performances of the majority of the models were found
to be poor for the test sets (Table 6). With the test sets, R2 values were
relatively lower, and RMSE values were relatively higher. This could be
attributed to a larger number of samples allocated for model develop-
ment and fewer for model validation.
While evaluating the models that provided the highest accuracy for
prediction of soil properties at a field level, it was found that although
the overall performance of the models developed by integrating the
information of seven fields together were low, the models could predict
soil properties of some fields with higher accuracy than for others
(Table 8, Fig. 3). For example, for field 1B, NN model predicted SOM
with R2 = 0.85, but for PENIN, R2 = 0.21. Similarly, the overall per-
formance of models for K, Mg and pH were low (R2 = 0.19, 0.22 and
0.13 for K, Mg and pH, respectively), but the model predicted these
variables with higher R2 values for some fields. Mg was predicted with
R2 = 0.55 for 1C; K was predicted with R2 = 0.56 for 1B; and pH was

219
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

Table 7
Model performance for estimation of corn yield based on remotely sensed image-derived variables.
Cross-Validation with
Validation with Test Dataset Overall Dataset
Models Training Dataset
R2 RMSE R 2
RMSE R2 RMSE
LM 0.34 1.14 0.35 1.17 0.34 1.15
RF 0.52 0.97 0.56 0.97 0.53 0.97
SVML 0.33 1.15 0.35 1.18 0.33 1.16
SVMR 0.44 1.05 0.48 1.05 0.45 1.05
GBM 0.40 1.08 0.43 1.10 0.41 1.08
NN 0.37 1.11 0.39 1.14 0.37 1.12
CU 0.51 0.98 0.55 0.98 0.52 0.98
Note: Bold texts indicate the model with the least RMSE and the highest R2.

predicted with R2 = 0.73 for 1C.
Table 7 shows average R2 and RMSE of seven models for both cross-
validation and validation stages during corn yield prediction using re-
motely sensed data-derived variables. R2 values ranged from 0.32 to
0.51 during the model cross-validation, and 0.30 to 0.51 during the
validation phase.
3.3. Comparison of model performance
For five soil properties, no model was found to have a consistently
superior performance during both cross-validation and validation
phases (Table 6). However, for most of the time, machine learning
models performed better than LM. For instance, during model devel-
opment, NN performed better in prediction of SOM and CEC with a
higher R2 and lower RMSE. SVM with linear and radial kernel functions
performed better in prediction of Mg and K, respectively. GBM
performed marginally better in prediction of pH. However, during
model validation with test dataset, RF performed better than NN for
both SOM and CEC. GBM performed better in K prediction, and LM
performed marginally better for pH.
For two approaches (first based on only remotely sensed data-de-
rived variables, and the second based on only soil variables) for corn
yield prediction, RF and CU models consistently performed better (i.e.,
higher R2 and lower RMSE) than other models during both cross-vali-
dation and validation phases. Although RF and CU models had the same
R2, RF performed marginally better, as indicated by its lower RMSE
(Table 7).
Superiority of machine learning models over LM model could be
attributed to the existence of non-linear relationships between the re-
sponse and predictor variables that machine learning algorithms can
integrate during model development. Differences in accuracy of corn
yield prediction models developed using only remotely sensed data-

Table 8
Model performance for prediction of soil properties at field level.
SOM CEC K Mg pH
Field Dataset
R2 RMSE R2 RMSE R2 RMSE R2 RMSE R2 RMSE
All 0.60 0.46 0.64 2.50 0.19 0.50 0.22 4.70 0.13 0.62
Overall Train 0.61 0.44 0.67 2.35 0.11 0.55 0.22 4.57 0.15 0.62
Test 0.55 0.53 0.53 3.10 0.19 0.50 0.23 5.21 0.13 0.62
All 0.85 0.43 0.78 2.31 0.56 0.16 0.20 4.78 0.27 0.63
1B Train 0.91 0.43 0.78 2.13 0.60 0.16 0.36 4.12 0.35 0.58
Test 0.41 0.45 0.77 2.64 0.45 0.17 0.09 6.98 0.05 0.82
All 0.75 0.42 0.71 2.27 0.15 0.44 0.55 3.25 0.73 0.45
1C Train 0.66 0.44 0.73 2.18 0.23 0.41 0.55 3.19 0.85 0.44
Test 1.00 0.26 1.00 2.87 1.00 0.60 1.00 3.65 0.77 0.48
All 0.53 0.30 0.47 2.32 0.05 0.50 0.04 4.28 0.41 0.49
1D Train 0.62 0.30 0.52 2.29 0.08 0.51 0.09 4.03 0.38 0.49
Test 0.79 0.35 0.00 2.46 0.97 0.44 0.32 5.46 0.99 0.46
All 0.76 0.49 0.67 2.55 0.07 0.42 0.18 5.37 0.42 0.66
9A Train 0.76 0.40 0.67 2.31 0.07 0.46 0.18 4.98 0.42 0.56
Test 0.76 0.68 0.92 3.15 0.51 0.30 0.23 6.37 0.05 0.90
All 0.20 0.33 0.17 2.31 0.00 0.62 0.00 4.10 0.01 0.49
PENIN Train 0.07 0.34 0.26 2.81 0.00 0.73 0.00 4.25 0.07 0.39
Test 0.91 0.33 0.31 0.49 0.01 0.27 0.07 3.79 0.02 0.63
All 0.68 0.45 0.57 2.40 0.33 0.41 0.33 5.21 0.24 0.65
MISD Train 0.69 0.44 0.55 2.50 0.33 0.45 0.31 5.38 0.25 0.64
Test 0.69 0.50 0.77 1.92 0.79 0.12 0.62 4.48 0.35 0.71
All 0.32 0.48 0.67 2.07 0.37 0.68 0.22 3.82 0.36 0.38
12D Train 0.31 0.46 0.72 2.03 0.37 0.70 0.17 4.02 0.33 0.39
Test 0.43 0.59 0.20 2.27 0.64 0.50 0.69 2.29 0.52 0.31
*Texts that are bold and highlighted for overall dataset indicate R2 > 0.50.

220
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

derived variables (Table 7), and only soil parameters (Table S2; see
supplementary document) suggested that remotely sensed data-derived
variables have high potential to provide better estimates of corn yield
than based on soil properties.
3.4. Variable importance in model development
Of the 18 variables considered in the model development, only few
variables were found to have significant influence on the prediction of
soil properties (Table 5). While only six variables were found to have

Fig. 4. A comparison of importance scores for selected variables used in six statistical models for: (a) Soil Organic Matter, (b) Cation Exchange Capacity, (c)
Potassium, (d) Magnesium, (e) pH, and (f) corn yield. Importance scores for variables were scaled between 0 and 100. Importance scores of variables in SVM models
with radial and linear kernel functions were the same.

221
S. Khanal et al. Computers and Electronics in Agriculture 153 (2018) 213–225

significant influence on the prediction of CEC, ten variables were found
to be significant for prediction of SOM and Mg. For CEC, K and pH, 6,
12 and 9 variables, respectively, had significant influence. For corn
yield prediction, 15 variables were found to have significant influence.
Based on the analyses of importance scores of selected variables for
prediction of soil properties and corn yield (Table 5), the influence of
variables was found to vary with the model. For instance, the variable
Group contributed the most to the prediction accuracy of LM and NN
based models for SOM, suggesting the importance of soil type during
SOM estimation. However, the variable NIR contributed the most for
RF, SVM, GBM and CU models for SOM. In general, the predictors that
contributed the most to the accuracy of the majority of models for SOM
(Fig. 4a) were NIR, Red, and SI. Similarly, red, green and BI were three
top predictors for the majority of the models for CEC. Unlike SOM and
CEC, importance scores of selected variables for Mg, K, pH and corn
yield prediction were more distributed. The top three variables were CI,
HI, and BI for Mg; NIR, SI, and CI for K; TRI, Rough, and Slope for pH;
SI, CI, and HI for corn yield. Except for pH, spectral bands and indices
were consistently identified as important predictors for soil properties.
For corn yield prediction, variables such as FlowDir, SI, and NDVI were
found to contribute the most to the RF model, which had superior
performance compared to other models (Fig. 4f).

Fig. 5. Maps showing (a) visual image of bare soil, and predicted (b) SOM (%), (c) CEC, (d) K, (e) Mg, and (f) pH in the study region with observed values at sampling
locations overlaid. Note: Predicted maps for SOM and CEC was based on NN model. SVM with radial and linear kernel functions were used for K and Mg, respectively;
and GBM was used for pH prediction.

222
S. Khanal et al.
Fig. 6. Maps of (left) observed, and (right) predicted corn yield in t/ha. Note: predicted yield map was based on RF model.
3.5. Mapping the spatial distribution of soil properties and corn yield
The model with the highest R2 and the lowest RMSE (Table 6) was
selected to create high resolution maps for each soil property, and corn
yield (Figs. 5–6). The geographical distribution of predicted soil prop-
erties was found to be similar to that of observed soil properties for
most of the fields. For fields 1B, 1C, 1D, 9A, and MISD, the geographical
distributions of observed and predicted SOM and CEC were very si-
milar. When the geographical distribution of soil properties were ex-
amined against three soil color classes, it was found that both SOM and
CEC were highly correlated with soil color (results not shown). Dark
color soil corresponded to areas with higher SOM and CEC, and lower K
and pH, and vice versa (Fig. 5a–c). This congruence of soil properties
with soil color suggested that in-field variability of some soil properties
can be estimated based on color of bare soil images.
The model predicted corn yield reasonably well with an average
difference of 1.48% ( ± 8.85% standard deviation) between predicted
and observed corn yield. The observed corn yield ranged from 6.1 to
17.9 t⋅ha−1, and predicted corn yield ranged from 9.5 to 15.24 t⋅ha−1
(Fig. 6). Except for few locations in the center and west parts of the
field, the geographical distribution of predicted corn yield was found to
be similar to the pattern of observed corn yield, suggesting that the
model could capture the spatial variability for most of the observed low
and high spots in field.
4. Discussion
4.1. Models for prediction of soil properties and corn yield
In the study, remotely sensed image-derived variables were in-
tegrated with field collected data to develop models for predicting soil
properties and corn yield. Because the fields were heterogeneous (i.e.,
different in terms of agricultural practices and soil properties; Table 1)
and models were developed for all seven fields, combined, instead for
each field, the overall accuracy of the models were reported low. When
the models’ performances were evaluated for individual fields, the ac-
curacies however were higher for some fields (Table 8). This suggests
that a model developed at a plot or field level performs better than a
model developed at a larger geographic scale. Studies (Barnes et al.,
2000; Stevens et al., 2013) have also noted that the use of multispectral
data for predicting the spatial distribution of soil properties can achieve
optimal results when the study is conducted at a plot level or in an area
with uniform soil surface characteristics. Nonetheless, the range of R2
223
Computers and Electronics in Agriculture 153 (2018) 213–225
values obtained in this study is better than or comparable to other
studies conducted at local (Morellos et al., 2016; Thomasson et al.,
2001) or regional scales (Forkuor et al., 2017; Peng et al., 2015) that
considered only spectral data or a combination of spectral, climate and
terrain variables.
The accuracy of the models in this study might have been influenced
by several things, including the difference in timing between soil
sample collection and image acquisition, and the use of limited machine
learning algorithms. For instance, the bare soil imagery was acquired in
May and the soil samples were collected in October. Thus, the model
developed based on data collected around the same time might be of
interest to improve the accuracy of the prediction. In the study, we
observed improvement in prediction of soil properties and corn yield
with the use of machine learning algorithms than the linear regression
algorithm. For example, NN model, closely followed by CU, produced
the most accurate prediction for SOM. Similarly, CU and RF models
produced the most accurate prediction of CEC and corn yield, respec-
tively. These findings are similar to prior studies that have found
models based on machine learning algorithms to be superior to ones
using linear regression (Hahn and Gloaguen, 2008; Minasny and
McBratney, 2008; Peng et al., 2015). Increase in model accuracy by
using machine learning algorithm is due to the ability of these algo-
rithms to handle the non-linear relationships, which is typically ob-
served between crop, soil, environmental and topographical variables.
This study suggested that no single machine learning algorithm is
best for evaluating all soil parameters and crop yield at all locations,
and that multiple models should be evaluated to enhance the accuracy
of prediction estimates. Similar observations were found in prior studies
as well. Ließ et al. (2016) reported that GBM performed better than NN,
RF, and SVM in prediction of soil organic carbon in a complex tropical
mountain landscape in Ecuador. However, Were et al. (2015) found
SVM to be the best method to predict SOC stocks in the Afromontane
Forest in Eastern Africa. Rossel and Behrens (2010) reported that the
smallest RMSE values were found with the SVM approach used for
prediction of three soil properties, including SOC, clay content, and pH.
Jeong et al. (2016) found RF to be a more effective machine learning
method for crop yield predictions at regional and global scales com-
pared to LM. Uno et al. (2005) reported NN to provide better corn yield
prediction compared to LM approach.
In this study, we evaluated the performance of seven most popular
models. There are however other machine learning algorithms, such as
multivariate adaptive regression splines, K Nearest Neighbor, and var-
ious types of neural network (e.g., convolutional, recursive, recurrent,
S. Khanal et al.
feedforward). The use of these machine learning algorithms may help
improve accuracy of the models than the algorithms examined in the
study. Thus, we suggest to examine the performance of these models for
future works.
The another approach to improve the model accuracy might be the
use of advanced algorithms for variable selection such as genetic al-
gorithms. In this study, variables for the linear regression models were
selected using the most commonly used stepwise AIC approach. Genetic
algorithms, inspired by the laws of genetics, try to find optimal solu-
tions to complex problems, which is usually the case in the context of
agriculture. It is thus useful to explore the role of genetic algorithms in
future studies related to soil properties and yield estimation.
4.2. Important variables for modeling of soil properties and corn yield
This study demonstrated that the information derived from multi-
spectral images contributes more to improve the prediction of soil
properties than terrain information derived from DEM. This is con-
sistent with the findings of Dobos et al (2001) that combined coarse
resolution AVHRR satellite data and DEM derived terrain variables to
characterize the soil-forming environment. Among the variables de-
rived using spectral information of multispectral images, it was inter-
esting to note that NDVI of bare soil imagery was found to have sig-
nificant influence on prediction of majority of the soil properties
evaluated in this study, including SOM, CEC, K and pH, although it is a
commonly used index for representing vegetation growth. This finding
was found to be consistent with previous studies (Escadafal and Huete,
1993; Huete and Tucker, 1991) that also found NDVI to be sensitive to
mineral constituents of soil. This study also showed that bare soil
imagery can be a good indicator of potential corn yield pattern in a
field. Understanding of the potential spatial variability in corn yield
patterns based on soil spectral information and topographic conditions
prior to planting might give farmers enough time to take preventive
actions, such as levelling of high elevation areas, fertilization of areas
with poor fertility, to maintain crop quality and yield.
4.3. Applicability of the models
The statistical models for prediction of soil properties in this study
were calibrated and tested with data collected from seven fields in one
year. The corn yield was predicted based on one field with one year of
data. Thus, the models developed in this study cannot be generalized
for the prediction of the same soil parameters and corn yield in other
soil types and geographic regions. To reinforce the findings of this study
as well as to strengthen the model’s predictive capability over the wide
range of soil properties and field management practices, further studies
should be carried out with more data from multiple years, and from
other fields with varying management practices and soil types.
Nevertheless, the analyses presented in this study demonstrated that
remotely sensed data and machine learning approaches could be
adopted for cost-effective prediction of soil properties and crop yield at
high spatial resolution.
5. Conclusions
High spatial resolution mapping of soil properties and crop yield is
required for proper management of crop and soil health which is
needed for improving crop productivity and lowering agriculture re-
lated negative environmental footprint. This study demonstrated that
the use of high spatial resolution (< 1 m) multispectral bare soil image
and terrain data can capture in-field variability of soil properties, in-
cluding SOM, CEC, K, Mg, and pH, and corn yield. The performance of
seven statistical models, including LM, RF, SVM with linear and radial
kernel functions, SGB, NN, and CUB, were compared for their ability to
predict soil properties and corn yield, and the machine learning algo-
rithms were found to outperform the LM algorithm most of the time.
224
Computers and Electronics in Agriculture 153 (2018) 213–225
However, no model was found to consistently outperform other models
for prediction of soil properties. NN performed better in prediction of
SOM and CEC with a higher R2 and lower RMSE, while SVM model with
linear and radial kernel function performed better for prediction of Mg
and K, respectively. For pH and corn yield prediction, GBM and RF
models, respectively, performed better than other models. For seven
fields, models for SOM, CEC, Mg, K, and pH showed R2 in the range of
0.2–0.85, 0.17–0.78, 0.0–0.55, 0.0–0.56, and 0.0–0.73, respectively.
For corn yield, RF consistently outperformed other models and pro-
vided R2 = 0.53. These findings suggest that remotely sensed data can
serve as a surrogate for more intensive soil sampling and costly yield
monitoring systems.
Variables based on multispectral bare soil images were found to be
the most important predictors for enhancing the model’s accuracy for
the spatial prediction of soil properties, including SOM, CEC, K and Mg.
Topographic variables were found to have more influence in the pre-
diction of pH. For corn yield, both spectral and topographic information
were important. Despite the high variability in topography and farm
management practices of the seven fields, the accuracy obtained in
prediction of soil properties and corn yield in this study are promising
for high resolution mapping of soil properties and corn yield at a local
scale. High resolution maps of soil properties and crop yield help
farmers to identify areas of potential concerns prior to planting and
manage them for improved crop productivity.
Acknowledgements
This work was supported in parts by funds from programs at the
Ohio State University- the Field to Faucet program (Grants No. F2F-
000004), and Ohio Agricultural Research and Development Center
(OARDC) (SEEDS: the OARDC Research Enhancement Competitive
Grants Program).
Appendix A. Supplementary material
Supplementary data associated with this article can be found, in the
online version, at https://doi.org/10.1016/j.compag.2018.07.016.
References
Allen, D.E., Pringle, M.J., Bray, S., Hall, T.J., O’Reagain, P.O., Phelps, D., Cobon, D.H.,
Bloesch, P.M., Dalal, R.C., 2014. What determines soil organic carbon stocks in the
grazing lands of north-eastern Australia? Soil Res. 51, 695–706.
Barnes, E.M., Baker, M.G., et al., 2000. Multispectral data for mapping soil texture:
possibilities and limitations. Appl. Eng. Agric. 16, 731–746.
Blasch, G., Spengler, D., Itzerott, S., Wessolek, G., 2015. Organic matter modeling at the
landscape scale based on multitemporal soil pattern analysis using rapideye data.
Remote Sens. 7, 11125–11150. https://doi.org/10.3390/rs70911125.
Davy, M.C., Koen, T.B., 2014. Variations in soil organic carbon for two soil types and six
land uses in the Murray Catchment, New South Wales, Australia. Soil Res. 51,
631–644.
Dobos, E., Montanarella, L., Nègre, T., Micheli, E., 2001. A regional scale soil mapping
approach using integrated AVHRR and DEM data. Int. J. Appl. Earth Obs. Geoinf. 3,
30–42.
Escadafal, R., Huete, A.R., 1993. Soil optical properties and environmental applications of
remote sensing. Int. Arch. Photogramm. Remote Sens. 29, 709–715.
Forkuor, G., Hounkpatin, O.K.L., Welp, G., Thiel, M., 2017. High resolution mapping of
soil properties using Remote Sensing variables in south-western Burkina Faso: a
comparison of machine learning and multiple linear regression models. PLoS One 12,
1–21. https://doi.org/10.1371/journal.pone.0170478.
Geipel, J., Link, J., Claupein, W., 2014. Combined spectral and spatial modeling of corn
yield based on aerial images and crop surface models acquired with an unmanned
aircraft system. Remote Sens. 6, 10335–10355.
Hahn, C., Gloaguen, R., 2008. Estimation of soil types by non linear analysis of remote
sensing data. Nonlinear Process. Geophys. 15, 115–126.
Hively, W.D., McCarty, G.W., Reeves, J.B., Lang, M.W., Oesterling, R.A., Delwiche, S.R.,
2011. Use of airborne hyperspectral imagery to map soil properties in tilled agri-
cultural fields. Appl. Environ. Soil Sci.
Huete, A.R., Tucker, C.J., 1991. Investigation of soil influences in AVHRR red and near-
infrared vegetation index imagery. Int. J. Remote Sens. 12, 1223–1242.
Jeong, J.H., Resop, J.P., Mueller, N.D., Fleisher, D.H., Yun, K., Butler, E.E., Timlin, D.J.,
Shim, K.M., Gerber, J.S., Reddy, V.R., Kim, S.H., 2016. Random forests for global and
regional crop yield predictions. PLoS One 11, 1–15. https://doi.org/10.1371/journal.
S. Khanal et al.
pone.0156571.
Kitchingman, A., Lai, S., 2004. Inferences on potential seamount locations from mid-
resolution bathymetric data. Focus (Madison). 32, 128.
Kuhn, M., 2017. CARET: Classification and Regression Training [WWW Document].
URL < https://github.com/topepo/caret/ > (accessed 10.1.17).
Kuhn, M., Johnson, K., 2013. Applied Predictive Modeling. < https://doi.org/10.1007/
978-1-4614-6849-3 > .
Ließ, M., Schmidt, J., Glaser, B., 2016. Improving the spatial prediction of soil organic
carbon stocks in a complex tropical mountain landscape by methodological specifi-
cations in machine learning approaches. PLoS One 11, e0153673.
Lobell, D.B., Thau, D., Seifert, C., Engle, E., Little, B., 2015. A scalable satellite-based crop
yield mapper. Remote Sens. Environ. 164, 324–333. https://doi.org/10.1016/j.rse.
2015.04.021.
Lyle, G., Bryan, B.A., Ostendorf, B., 2014. Post-processing methods to eliminate erroneous
grain yield measurements: review and directions for future development. Precis.
Agric. 15, 377–402.
Minasny, B., McBratney, A.B., 2008. Regression rules as a tool for predicting soil prop-
erties from infrared reflectance spectroscopy. Chemom. Intell. Lab. Syst. 94, 72–79.
https://doi.org/10.1016/j.chemolab.2008.06.003.
Morellos, A., Pantazi, X.-E., Moshou, D., Alexandridis, T., Whetton, R., Tziotzios, G.,
Wiebensohn, J., Bill, R., Mouazen, A.M., 2016. Machine learning based prediction of
soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectro-
scopy. Biosyst. Eng. 152, 104–116. https://doi.org/10.1016/j.biosystemseng.2016.
04.018.
Mulder, V.L., De Bruin, S., Schaepman, M.E., Mayr, T.R., 2011. The use of remote sensing
in soil and terrain mapping-a review. Geoderma 162, 1–19.
Peng, Y., Xiong, X., Adhikari, K., Knadel, M., Grunwald, S., Greve, M.H., 2015. Modeling
soil organic carbon at regional scale by combining multi-spectral images with la-
boratory spectra. PLoS One 10. https://doi.org/10.1371/journal.pone.0142295.
Ray, S.S., Singh, J.P., Das, G., Panigrahy, S., 2004. Use of high resolution remote sensing
data for generating site-specific soil management plan. Int. Arch. Photogramm.
Remote Sens. Spat. Inf. Sci. 35, 127–132.
Riedmiller, M., Braun, H., 1993. A direct adaptive method for faster backpropagation
learning : the RPROP algorithm. In: Neural Networks, International Conference on.
pp. 586–591.
Riley, S.J., 1999. Index that quantifies topographic heterogeneity. Intermt. J. Sci. 5,
23–27.
Rossel, R.A.V., Behrens, T., 2010. Using data mining to model and interpret soil diffuse
reflectance spectra. Geoderma 158, 46–54. https://doi.org/10.1016/j.geoderma.
225
Computers and Electronics in Agriculture 153 (2018) 213–225
2009.12.025.
Scudiero, E., Skaggs, T.H., Corwin, D.L., 2014. Regional scale soil salinity evaluation
using Landsat 7, western San Joaquin Valley, California. USA. Geoderma Reg. 2,
82–90.
Shi, Y., Thomasson, J.A., Murray, S.C., Pugh, N.A., Rooney, W.L., Shafian, S., Rajan, N.,
Rouze, G., Morgan, C.L.S., Neely, H.L., et al., 2016. Unmanned aerial vehicles for
high-throughput phenotyping and agronomic research. PLoS One 11, e0159781.
Souza, E.G., Bazzi, C.L., Khosla, R., Uribe-Opazo, M.A., Reich, R.M., 2016. Interpolation
type and data computation of crop yield maps is important for precision crop pro-
duction. J. Plant fcenNutr. 39, 531–538. https://doi.org/10.1080/01904167.2015.
1124893.
Spectrum Analytic, 2017. Analysis Services [WWW Document]. URL < https://www.
spectrumanalytic.com/services/analysis/agsoil.html > .
Stevens, A., Nocita, M., Tóth, G., Montanarella, L., van Wesemael, B., 2013. Prediction of
soil organic carbon at the European scale by visible and near infrared reflectance
spectroscopy. PLoS One 8, e66409.
Sudduth, Kenneth, A., Drumm, 2007. Yield editor: software for removing errors from crop
yield maps. Agron. J. 99, 1471–1482. https://doi.org/10.2134/agronj2006.0326.
Thomasson, J.A., Sui, R., Cox, M.S., Al–Rajehy, A., 2001. Soil reflectance sensing for
determining soil properties in precision agriculture. Trans. ASAE 44, 1445–1453
https://doi.org/10.13031/2013.7002.
Uno, Y., Prasher, S.O., Lacroix, R., Goel, P.K., Karimi, Y., Viau, A., Patel, R.M., 2005.
Artificial neural networks to predict corn yield from Compact Airborne
funoSpectrographic Imager data. Comput. Electron. Agric. 47, 149–161. https://doi.
org/10.1016/j.compag.2004.11.014.
Were, K., Bui, D.T., Dick, Ø.B., Singh, B.R., 2015. A comparative assessment of support
vector regression, artificial neural networks, and random forests for predicting and
mapping soil organic carbon stocks across an Afromontane landscape. Ecol. Indic. 52,
394–403.
Wilson, M.F.J., O’Connell, B., Brown, C., Guinan, J.C., Grehan, A.J., 2007. Multiscale
terrain analysis of multibeam bathymetry data for habitat mapping on the continental
slope. Mar. Geod. 30, 3–35.
Yang, C., Westbrook, J.K., Suh, C.P.-C., Martin, D.E., Hoffmann, W.C., Lan, Y., Fritz, B.K.,
Goolsby, J.A., 2014. An airborne multispectral imaging system based on two con-
sumer-grade cameras for agricultural remote sensing. Remote Sens. 6, 5257–5278.
Yao, R.J., Yang, J.S., Wu, D.H., Xie, W.P., Gao, P., Wang, X.P., 2016. Characterizing
spatial-temporal changes of soil and crop parameters for precision management in a
coastal rainfed agroecosystem. Agron. J. 108, 2462–2477.