Computers and Electronics in Agriculture 130 (2016) 13–19

Contents lists available at ScienceDirect

Computers and Electronics in Agriculture

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

Original papers

A computational environment to support research in sugarcane

agriculture
Carlos Driemeier a, Liu Yi Ling a, Guilherme M. Sanches a,b, Angélica O. Pontes a,
Paulo S. Graziano Magalhães a,b,⇑, João E. Ferreira c
a
Brazilian Bioethanol Science and Technology Laboratory (CTBE), National Center for Research in Energy and Materials (CNPEM), Caixa Postal 6192, CEP 13083-970 Campinas,
São Paulo, Brazil
b
School of Agriculture Engineering – FEAGRI, University of Campinas – UNICAMP, Campinas, SP, Brazil
c
Institute of Mathematics and Statistics – IME, University of São Paulo – USP, São Paulo, SP, Brazil

a r t i c l e i n f o a b s t r a c t

Article history: Sugarcane is an important crop for tropical and sub-tropical countries. Like other crops, sugarcane agri-
Received 26 October 2015 cultural research and practice is becoming increasingly data intensive, with several modeling frameworks
Received in revised form 23 August 2016 developed to simulate biophysical processes in farming systems, all dependent on databases for accurate
Accepted 4 October 2016
predictions of crop production. We developed a computational environment to support experiments in
sugarcane agriculture and this article describes data acquisition, formatting, storage, and analysis. The
potential to support creation of new agricultural knowledge is demonstrated through joint analysis of
Keywords:
three experiments in sugarcane precision agriculture. Analysis of these case studies emphasizes spatial
Precision agriculture
Sugarcane
and temporal variations in soil attributes, sugarcane quality, and sugarcane yield. The developed compu-
Database tational framework will aid data-driven advances in sugarcane agricultural research.
Workflow Ó 2016 Elsevier B.V. All rights reserved.

1. Introduction Precision Agriculture (PA), which comprises a set of tools to help

Sugarcane is an important crop mainly in tropical and sub-
tropical countries. Brazil is the largest sugarcane producer, with
9 Mha cultivated to produce 659 million Mg of sugarcane in the
2015/2016 season, resulting in 34,600 Mg of sugar and 29 billion
L of ethanol (CONAB, 2015). In addition to sugar and ethanol, Brazil
is today the country with the largest installed capacity of biomass-
based electricity generation (IRENA, 2015). In 2015, the supply of
electricity from biomass had estimated growth of 7%, with a total
generation over 22 TW h, where sugarcane accounts for 80%.
Several modeling frameworks such as AUSCANE, QCANE,
APSIM, MOSICAS and CANEGRO (Marin et al., 2011) are increas-
ingly being employed to simulate biophysical process in sugarcane
farming systems. They are all dependent on databases, exemplify-
ing the many ways in which agriculture is moving towards inten-
sive data acquisition and processing. In addition, agriculture
worldwide is witnessing a growing adoption of the so-called
⇑ Corresponding author at: Brazilian Bioethanol Science and Technology Labora-
tory (CTBE), National Center for Research in Energy and Materials (CNPEM), Caixa
Postal 6192, CEP 13083-970 Campinas, São Paulo, Brazil.
E-mail address: paulo.graziano@bioetanol.org.br (Paulo S. Graziano Magalhães).
farmers understand and manage soils and crops inherent spatial
and temporal variability. PA relies on collection, analysis, process-
ing, and synthesis of voluminous georeferenced data, which can be
collected from a number of different technologies (Zamykal and
Everingham, 2009). Research and technology on PA have advanced
considerably in the past 20 years (Bramley, 2009). Due to its
intense use of information, PA has grown and evolved to incorpo-
rate the best of multidisciplinary science and technology (Zamykal
and Everingham, 2009), requiring farmers to look at their business
from different perspectives (Srinivasan, 2006).
Sugarcane production system, however, differs substantially
from major staple crops, affecting development and adoption of
agricultural technologies. Comparison between a major cereal
(e.g., wheat) and sugarcane highlights some key differences. Wheat
area worldwide is 215 Mha, primarily in temperate zones, com-
pared to 26 Mha of sugarcane, primarily in tropical developing
countries, especially in Brazil. Furthermore, the harvested part of
cereal crops is the grain, with mean yields of 3.2 Mg ha
1 for wheat,
compared to 71 Mg ha
1 for harvesting the stalks of sugarcane in
2013 (FAO, 2015). Differences in area and location make sugarcane
a small fraction of the global market for agricultural technology. In
addition, the high tonnage of sugarcane requires dedicated

http://dx.doi.org/10.1016/j.compag.2016.10.002
0168-1699/Ó 2016 Elsevier B.V. All rights reserved.
14 C. Driemeier et al. / Computers and Electronics in Agriculture 130 (2016) 13–19

technologies, such as tailored yield monitors (Magalhães and Cerri,

2007). Due to specificities of the sugarcane system, and despite
rapid adoption of auto-steer in tractors and harvesters (Bramley
and Trengove, 2013; Silva et al., 2011), PA is not yet adopted by
the sugarcane-based sugar-ethanol industry as it is for other agri-
cultural systems (Gebbers and Adamchuk, 2010). According to sur-
veys conducted in Brazil (Anselmi et al., 2014; Avanzi et al., 2014;
Silva et al., 2011) and Australia (Bramley and Trengove, 2013),
low PA adoption can be explained by four factors: relative advan-
tage (usefulness), compatibility, trialability and observability. For
sugarcane production, perceived usefulness is correlated with
increased crop yield, reduced costs, and improved management.
On the other hand, high costs of equipment, lack of qualified staff
and lack of information on PA technologies were pointed by sugar-
cane farmers as the main barriers (Silva et al., 2011).
In this context, efforts have been primarily dedicated to exper-
iments aiming at establishing the scientific grounds and demon- Fig. 1. Tasks for handling of raw data prior to insertion into the database.
strating the advantages of PA techniques applied to sugarcane
(Portz et al., 2011; Rodrigues et al., 2012). Because of these goals,
characterization of soil and plant attributes in experiments is much 2.2. Database
more comprehensive than the expected for large-scale PA practice.
Furthermore, testing data acquisition technologies and contextual- A relational database for sugarcane agricultural experiments
izing their outputs are important goals of the experimentation was created and named BDAgro – CTBE Database of Agricultural
stage. Considering the above, treating the diversity of measurable Experiments, as detailed in a Technical Memorandum (Pontes
attributes is a critical point in experimentation for sugarcane PA. et al., 2014). BDAgro was constructed having PostgreSQL as rela-
The data-driven character of PA has attracted the attention of tional database management system and pgAdmin as database
the research community from many different areas. For instance, administration and development platform.
there are studies on clustering algorithm to delineate management BDAgro conceptual model, i.e. entity-relationship model
zones (Tagarakis et al., 2012), data acquisition techniques with (Elmasri and Navathe, 2010), includes entities associated to man-
remote sensing (Mulla, 2013; Song et al., 2009), and software agement and responsibilities (e.g., records of projects and responsi-
architecture for data analysis and integration of sensor based PA ble persons). Nevertheless, more relevant for the analytical
monitoring (Chen et al., 2015). purposes of the computational environment, BDAgro represents
In this work, we present a computational environment created agricultural experiments through the following entities:
to support sugarcane agricultural research, including but not lim-
ited to research in PA. Data acquisition, formatting, verification,
 Experiment is defined by a certain land area during a certain
storage, and analysis are discussed. To demonstrate the applicabil-
period of time. The land area is most often an open agricultural
ity of the computational environment, data of soil chemistry, sug-
field, but may also be inside close environments such as
arcane quality, and sugarcane yield from three experiments are
greenhouses.
jointly analyzed and discussed.
 Event is one important fact within one experiment. Events may
be of three types: (i) intervention, associated with change in
experimental land area (e.g., harvest, soil fertilization); (ii) char-
2. Computational environment
acterization, associated with data acquisition without change in
land area (e.g., characterization of soil attributes); and (iii) plan-
2.1. Handling of raw data
ning, representing a record associated with neither physical
change in land area nor new data acquisition (e.g., nutrient
Sugarcane agricultural experiments may include several
prescription).
sources of raw data, including data acquired by different analytical
laboratories and by various types of sensors. The current version of  Static data is data generated by events. It is termed static
the computational environment is able to process data in matrix because each event is defined at a specific moment within
formats. Processing of images (e.g., from unmanned aerial vehicles one experiment. Static data has x and y spatial coordinates as
and satellite) is foreseen as a future upgrade for the system. attributes. Additional attributes depend on type of static data
The database has an expandable set of allowed matrix formats – (i.e., on type of measurements). Soil attributes, sugarcane qual-
essentially one matrix format for each type of measurement. To ity, and sugarcane yield are examples of types of static data.
assure that matrixes are properly recorded in the database, we rou-  Dynamic data is data acquired continuously during the course
tinely handle raw data following the tasks presented in Fig. 1. of one experiment. Meteorological information is one example
Using spreadsheets, raw data from sensors and laboratory files of dynamic data.
are converted into data matrixes consistent with the predefined
database formats. Such data matrixes are verified and then We will refer to these entities as the article follows. However,
inserted into the database. Importantly, data acquisition and for- the analysis of the case studies does not yet include any dynamic
matting are performed by agricultural field scientist, while verifi- data because of the complexity of agricultural analysis using fine
cation and insertion are performed by computational workers. temporal granularity.
Among other advantages, this division of tasks assures an indepen-
dent verification of data veracity. Verifications include matrix for- 2.3. Data analysis
mats, measurement units, and typical range of values acceptable
for a certain measured attribute. Once verified, data matrixes are We adopted the Work-Event-Data-flow (WED-flow) approach
inserted into the database using python-generated SQL scripts. (Ferreira et al., 2010) as the methodology for modeling analysis
 C. Driemeier et al. / Computers and Electronics in Agriculture 130 (2016) 13–19
workflows. WED-flow addresses the integration of three main flow
paradigms: workflow, event-flow and data-flow. These three flow
paradigms combine the concepts of workflow composition, trans-
actions (i.e., activities), events, and data states. At an abstract level,
the WED-flow is modeled as a SAGA (Garcia-Molina and Salem,
1987), composed from SAGA steps, each of which is enclosed in a
transaction. The main advantage of WED-flow approach is the inte-
gration of three main flow paradigms supporting modeling of anal-
ysis workflows. More concretely, in this paper, we assume that: the
flow of work is a set of analysis steps; the flow of analysis event is a
set of constraints (that once satisfied triggers the following analy-
sis step); and flow of data is a set of data states generated by each
analysis step. An analytical module was created within BDAgro by
constructing a set of tables containing the data states resulting
from analysis workflows. The statistical computing integrated to
the database is performed with the R programming language.
3. Case studies
Data presented in this paper has been collected from 2007 to
2014 in different sugarcane fields. Sugarcane is a semi-perennial
crop, which typically grows in cycles of four to six years, being har-
vested and fertilized annually.
3.1. Three Experiments
The first and second field experiments were conducted from
2010 to 2014 in two adjacent 50 ha areas in a commercial sugar-
cane field in Serra Azul – SP, Brazil (21° 160 4100 S and 47° 320
1000 W), which belongs to Pedra Mill. Before sugarcane planting, a
survey of the area was carry out in November 2010 to establish
the soil chemical and physical conditions and nutrient need for
crop implementation. In the first field experiment (Fig. 2a), the
area was divided into a regular 50 m grid with 204 sample points
located using a differential global positioning system (DGPS)
(Ag114TM, Trimble, Navigation Ltd, Sunnyvale, CA, USA). Additional
refinement points were taken when necessary (Fig. 2a). Soil sample
was taken at two depths (0–0.20 and 0.20–0.40 m) at each grid
point and a wet-chemical analysis was done to determine soil
physical and chemical attributes (macro and micronutrients). In
the second experiment, the area was divided into a regular
150 m grid with 24 sample points (Fig. 2b) located using the same
technology. Soil samples were taken at the same depths, and sent
to a laboratory for wet-chemical analysis. In both areas, sugarcane
was planted in April 2011. Annually the area was fertilized with K,
P and N and soil samples were taken at the same spots.
Fig. 2. Photographs from land areas of experiments 1–3 (A-C). Grid points (black dots), grid refinement points (red crosses, A and C), and the track from the sugarcane
harvester (yellow lines in the rectangular area zoomed at the inset of (A) are shown). (For interpretation of the references to colour in this figure legend, the reader is referred
to the web version of this article.)
15
The third experiment was conducted in a 10-ha commercial
sugarcane field (Fig. 2c) that belongs to GRUPO USJ, a sugar and
ethanol plant located in Araras, São Paulo State in the southeast
region of Brazil (22° 230 3800 S, 47° 180 0400 W). Sugarcane variety
SP80-3280 was planted in 2007 and was mechanically green har-
vested along the cropping seasons. Liming and fertilization were
performed according to usual recommendations for sugarcane crop
planting (Raij et al., 1997) at a fixed rate. For the subsequent ratoon
crops (2009–2011), no fertilizers were applied. A total of 117 sam-
ple points were established on a 30 m regular grid to sample the
sugarcane quality parameters and physical and chemical soil attri-
butes. Additional 14 refinement points were also taken. Plant sam-
pling occurred just before the respective harvests at the peak of the
sugarcane maturity. The three sites (Fig. 2a–c) had been under con-
tinuous sugarcane cultivation for more than 30 years.
Annually the areas were harvested using sugarcane harvesters
equipped with auto-guidance system with a RTK signal (Trimble,
Navigation Ltd, Sunnyvale, CA, USA) and a yield monitor (Simpro-
cana, Enalta, São Carlos, Brazil). Annually, after harvest, soil sam-
ples were taken again at same grid to diagnosis some deficiency
and recommend fertilizer application using VRT when applicable
(field 1 and 2). At each field, the experiment has been conducted
for the whole sugarcane cycle, i.e. from planting, following through
the consecutive ratoons, during 4 cycles.
3.2. Data acquisition techniques
Soil and crop data have been acquired with two types of tech-
niques: (i) sampling at grid points, for physical and chemical soil
attributes and (ii) scanning the area by soil (soil apparent electrical
conductivity) and crop ‘‘on-the-go” sensors (crop spectrum reflec-
tance), which are mounted on vehicles equipped with differential
global positioning system (DGPS). Data acquisition with on-the-
go sensors has relatively lower costs and is promising for large-
scale PA practice. On the other hand, sampling at grid points is
labor intensive, requiring manual collection of samples for offline
laboratory analysis. Such sampling approach is likely of limited
applicability for large-scale PA. However, for the purpose of exper-
imentation, sampling-based techniques are employed because
they allow measurement of much more diverse sets of soil and
plant attributes, thus expanding the scope of the experiments.
Sample collection at grid points is recorded in the database as
events of characterization, which generate static data. Measured
attributes of soil chemistry include pH, contents of organic matter
(OM), and concentrations of macronutrients (P and K) and
micronutrients (B, Mg, S, Ca, Mn, Fe, Cu, and Zn). Soil samples were
16 C. Driemeier et al. / Computers and Electronics in Agriculture 130 (2016) 13–19
collected from two soil layers: 0–0.20 and 0.20–0.40 m deep in
experiments 1 and 2; 0–0.20 and 0.20–0.50 m deep in experiment
3. Sugarcane quality parameters (Fiber, Brix, and Pol) were mea-
sured from sugarcane samples collected immediately before har-
vest. Sugarcane yield was measured by an on-the-go yield
monitor that determines sugarcane yield during the harvesting
operation (Magalhães and Cerri, 2007). In the database, yield is a
type of static data associated with a characterization event. Each
event of yield characterization is simultaneous to the intervention
event of harvest (Section 2.2). In this article, we analyze sugarcane
yield, whereas we omit data from other on-the-go sensors (of
apparent electrical conductivity, crop vegetation indexes).
3.3. Analysis workflow
We developed a data analysis workflow aiming at providing
synthetic views of (i) spatiotemporal variability in each measured
attribute and (ii) correlations among soil attributes that are pre-
sumably associated with soil pH. The model of the analysis work-
flow is sketched in Fig. 3, representing flow of analysis
(represented by boxes), flow of events (represented by arrows),
and flow of data states (represented by databases). Note that
results of analysis (Fig. 3) are correlations, spatial autocorrelations,
and outputs from principal component analysis (PCA). In essence,
all these results are based on correlations, which would be detri-
mentally affected by nonlinearities and outliers.
In order to avoid such issues, linearization and filtering steps
are applied beforehand in the workflow. Linearization takes the
logarithm of concentrations of soil components (OM, macronutri-
ents and micronutrients), keeping other attributes unchanged.
The logarithm scale reduced the positive skewness from concen-
tration distributions and is additionally justifiable due to ubiquity
of linear relations with log (concentration) found in physical-
chemistry (Atkins and Paula, 2010). Outliers in data sets are
Fig. 3. Data analysis workflow.
removed by a filtering step. Any entry deviating from the mean
by more than three standard deviations (for a given attribute)
was treated as an outlier.
Following linearization and filtering, the next steps aim at rep-
resenting all measurements of one experiment as a matrix of
entries U = {uij}, where i is the index for grid points and j for mea-
sured attributes. Sampling at grid points straightforwardly gener-
ates data in this matrix format. Nevertheless, in case of proximal
measurements, such as those performed in grid refinement points
(Fig. 2), uij is calculated as the average of the proximal points. On
the other hand, each attribute from on-the-go sensor is a function
uj(x,y), where (x,y) are the spatial coordinates of the sensor track on
the field. The value of uij is estimated by employing linear regres-
sion to fit a plane to uj(x,y) points within a circle of 50 m diameter
centered at the grid point i.
With attributes estimated at grid points, Moran0 s I spatial auto-
correlation, Ij, is calculated by considering the connection matrix M
whose terms equal one for neighbor grid points, and zero other-
wise. The matrix L is obtained by normalizing M to have each
row summing to unit. Then, Ij = zjT L zj, where zj is the vector of
the mean-centered normalized attribute estimated at grid points,
 j)/rj (Cliff and Ord, 1973).
zij = (uij
u
Measured attributes vary widely concerning their range of val-
ues as well as their data acquisition technologies. Therefore, preci-
sion in attribute measurement also vary widely. Typical attribute
precisions were estimated as ‘‘noise” levels sj. For attributes deter-
mined by sampling at grid points, sj was estimated as the standard
deviation of measurements in proximal points. For attributes
obtained from on-the-go sensors, sj was estimated from the stan-
dard error of the linear regression coefficient that estimates uij.
Principal Component Analysis (PCA) was employed to reduce
the dimensionality of the attribute space. Prior to PCA, missing
data in matrix {uij} was imputed by the Expectation-
Maximization (EM) algorithm associated with a multivariate nor-
mal model (Johnson and Wichern, 2007), stopping EM iterations
when imputed uij change way less than sj. This imputation
approach preserves the data covariance structure, thus being well
suited as data preparation method for PCA. PCA was performed
from correlation matrixes, which means that each attribute con-
tributes with normalized, unit variance.
4. Results and discussion
4.1. Spatial autocorrelations
The ‘‘null hypothesis” of PA is uniform management of the field
(Whelan and McBratney, 2000). A corollary is that, to be relevant
for PA, a measured attribute should present positive spatial auto-
correlation. That is, an attribute j having spatial autocorrelation
Ij  0 is consistent with random spatial distribution and, therefore,
cannot be used to justify any site-specific action on the field. On
the other hand, greater values of Ij might justify site-specific
interventions.
Considering the diversity of attributes characterized in the
three experiments, spatial autocorrelation Ij is distributed between

0.2 and 0.8 (Fig. 4). Negative Ij is observed mainly in experi-
ment 2 (Fig. 4B). Most likely negative Ij can be interpreted as
Ij  0 perturbed by statistical noise, which are greater in experi-
ment 2 due to fewer grid points (24) (Fig. 2). Noteworthy,
Webster and Oliver (2007) recommend that no fewer than 100
sampling points are necessary to estimate the variability of a cer-
tain field. Furthermore, it is important to note that, for the three
experiments, many attributes are close to Ij  0 so that such mea-
sured attributes should not be employed to support site-specific
interventions on the field.
 C. Driemeier et al. / Computers and Electronics in Agriculture 130 (2016) 13–19
Fig. 4. Inter-year correlation against Moran0 s I spatial autocorrelation for attributes of soil chemistry (black; OM, P, K, B, Mg, S, Ca, Mn, Fe, Cu, and Zn), sugarcane quality (blue;
Fbr, Brix, Pol), and sugarcane yield (red; Yi). Results from experiments 1–3 are shown in plots A-C. Year of measurement is represented by the inclination of the labels, as
indicated in the legends. Distinct soil layers are represented by Bold (0–0.20 m) and Italic (either 0.20–0.40 m or 0.20–0.50 m) labels. Diagonal dashed lines (y = x) and
horizontal dotted line (zero inter-year correlation) are shown to guide the eyes. (For interpretation of the references to colour in this figure legend, the reader is referred to the
web version of this article.)
4.2. Spatiotemporal variability in soil attributes
Statistical noise tends to reduce the magnitude of all types of
correlations, including spatial autocorrelation and correlation
between sequential measurements of a given attribute. Fig. 4 plots
inter-year correlation against spatial autocorrelation Ij. The inter-
year correlation is an index for the temporal stability of the spatial
variability of a given attribute. For attributes of soil chemistry
(black labels), a clear trend is observed in experiment 1 (Fig. 4A),
with attributes clustered near the diagonal dashed line (y = x).
Indeed, inter-year correlation is positively correlated (r = 0.73)
with spatial autocorrelation. This trend is consistent with inter-
year correlation and spatial autocorrelation being both substan-
tially reduced by statistical noise. The correlation between inter-
year correlation and spatial autocorrelation is weaker but still pos-
itive in experiments 2 and 3 (r = 0.54, r = 0.32, respectively). This
result indicates that statistical noise is also a major factor reducing
inter-year correlation and spatial autocorrelations in experiments
2 and 3. In these two experiments, most attributes of soil chemical
attributes are above the diagonal dashed line (Fig. 4B and C), i.e., for
most attributes inter-year correlation is greater than spatial auto-
correlation. This observation might result from inherently lower
spatial autocorrelations in experiments 2 and 3, due to the greater
spacing between grid points in experiment 2, and perhaps due to
the more homogeneous, flat terrain of experiment 3.
4.3. Spatiotemporal variability in sugarcane quality
In experiments 1 and 2, attributes of sugarcane quality have
spatial autocorrelation and inter-year correlation of approximately
zero (blue labels in Fig. 4A and B, respectively). This observation
indicates that sugarcane quality is consistent, at least approxi-
mately, with random spatiotemporal variations. Experiment 3
shows a different behavior. In year 2011, Brix and Pol (quality attri-
butes associated with sugar content) have spatial autocorrelation
Ij  0.3 and correlation with previous year of 0.2 (Fig. 4C). These
are significant correlations, demonstrating that within-field spatial
variability and temporal stability of Brix and Pol are possible issues
to be managed by PA techniques. Correlations of even higher mag-
nitudes are observed in sugarcane fiber contents (‘Fbr’ labels in
Fig. 4C), reinforcing that spatiotemporal management of sugarcane
quality is possible, at least in principle. Nevertheless, the fact that
17
appreciable correlations and spatial autocorrelations are only occa-
sionally observed in one (experiment 3) out of three experiments
suggests that significant spatiotemporal variability in sugarcane
quality may often remain undetected.
4.4. Spatiotemporal variability in sugarcane yield
Yield is certainly a major aim in crop management. In other
crops, yield spatial variations are commonly found to be rather
stable across several harvests (Godwin et al., 2003). In sugarcane,
however, we have been observing a lack of temporal stability in
yield spatial variability. In experiment 1, yield in 2014 has a posi-
tive (0.2) correlation with yield in 2013. This level of correlation
locates yield close to the diagonal trend observed in Fig. 4A, which
would be consistent with temporal stability reduced mainly by sta-
tistical noise. On the other hand, yield in 2013 has a near zero cor-
relation with yield in 2012 (Fig. 4A). This yield data is quite below
the diagonal trend of Fig. 4A and the lack of inter-year correlation
cannot be attributed to statistical noise. Even more extreme case is
observed in experiment 2, where correlation between 2012 and
2011 yields is negative (
0.6).
A more detailed investigation indicated two major causes for
the zero or negative inter-year correlations in yield. One cause is
occasional sensor failure. Readings from yield monitor are very
noisy (Fig. 5a), even after removal of outliers (Fig. 5b). The example
of Fig. 5b has mean yield of 93 Mg ha
1 and standard deviation of
47 Mg ha1. Typical precision (sj) in yield is reduced to about 1–
4 Mg ha
1 due to multiple readings used to estimate uij by regres-
sion (Fig. 3). However, with such noisy signal, some sensor failures
remain unfiltered, detrimentally affecting the precision of yield
estimates and reducing associated correlations. The second cause
of low inter-year correlations originates from real changes in yield,
especially due to damages inflicted to the sugarcane crop. Harvest
operation may damage the roots of the sugarcane plants, occasion-
ally pulling roots out of the soil. The result of such damage is a
localized yield reduction in the next harvests, thus reducing
inter-year correlation. Such damages to roots may become visible
as gaps in the sugarcane field. Indeed, field observations by agrono-
mists have been suggesting that crop damaging during harvest is
the major cause for declining yield across the multiyear crop cycles
(Zamykal and Everingham, 2009).
18 C. Driemeier et al. / Computers and Electronics in Agriculture 130 (2016) 13–19

Fig. 5. Reads from yield monitor before (a) and (b) after the filter step of the analysis workflow. Data from 2013 harvest of experiment 1.

Fig. 6. Loadings plot from principal component analysis of soil attributes presumably associated with soil pH (OM, Ca, Mg, and pH). Results from experiments 1–3 are shown
in plots A-C. Year of measurement is represented by the inclination of the labels, as indicated in the legends. Distinct soil layers are represented by Bold (0–0.20 m) and Italic
(either 0.20–0.40 m or 0.20–0.50 m) labels. Dotted lines are a pair of orthogonal axes rotated to have one axis aligned with the clusters of pH loadings (A and C).

4.5. PCA of attributes associated with soil pH
The numerous soil and plant attributes exist in an abstract
space of high dimensionality where visualization of the informa-
tion is impossible. Hence, reduction of dimensionality is often
desirable and PCA is a statistical technique to do it. Fig. 6 presents
the PC1& PC2 loadings from PCA applied to attributes judged to be
potentially associated with soil pH. The attributes are pH itself, the
main elements of lime (Mg and Ca, applied to soils to increase their
pH), and organic matter (OM, whose decomposition is thought to
decrease soil pH). PCA was applied separately for each experiment.
Analyzed attributes span sequential years as well as the two soil
layers that were characterized. Our interest in soil pH is due to
the possibility of pH control using lime broadcasted on the soil sur-
face with variable rate technology, which could reduce costs by
applying lime prescribed according to site-specific demands.
As a first observation, experiments 1 and 3 show loadings that
are clustered (Fig. 6A and C). In each experiment, there is one clus-
ter for pH, one for lime elements (Mg and Ca), and one for OM. Such
clustering indicates high correlation between soil top and bottom
layers. The clustering also indicates that spatial variations of pH,
Ca, Mg, and OM are mostly preserved along the years. This is
instructive and perhaps surprising, considering that experiments
1 and 3 employed distinct strategies to control soil pH (Section 3.1).
Loadings of OM are comparatively more spread than loadings of
pH, Ca, and Mg (Fig. 6A and C). This observation is consistent with
noisier OM measurements as well as with significant dynamics in
spatial variability of soil OM. Experiment 2 does not present such
clustering of loadings (Fig. 6B), which might be due to poorer
statistics arising from fewer grid points (Fig. 2).
Experiments 1 and 3 also share the relative directions of loading
clusters. The centroids of the pH clusters form an angle slightly
greater than 90° with the centroids of OM clusters
(Fig. 6A and C). This relative direction indicates a tendency to have
slightly negative correlations between pH and OM, consistent with
decreasing pH due to higher levels of decomposing OM. Further-
more, the loading clusters of Ca and Mg are observed in-between
those of pH and OM (Fig. 6A and C). Proximity with loadings of
pH is consistent with Ca and Mg causing increases in soil pH. On
the other hand, the proximity between loadings of OM and of lime
elements (Mg and Ca) is consistent with OM acting as storage med-
ium for Mg and Ca available in soils. These relative directions in
loadings plots demonstrate the possibility of finding common
behavior across multiple sugarcane agricultural experiments.
5. Conclusions
This paper described a computational environment to support
research in sugarcane agriculture. Data acquisition, formatting,
and verification steps are performed prior to data insertion into a
dedicated database named BDAgro. Data analysis is integrated to
the database by recording data states generated through data anal-
ysis workflows. Such workflows can be tailored for the specific
aims of each study.
The computational environment was employed to jointly ana-
lyze three experiments in sugarcane precision agriculture (PA).
 C. Driemeier et al. / Computers and Electronics in Agriculture 130 (2016) 13–19
These experiments comprised characterization of soil attributes,
sugarcane quality, and sugarcane yield. Our analysis showed low
spatial autocorrelations and low inter-year correlations for most
of the sugarcane quality and yield attributes. This finding revealed
important limitations in measurements of sugarcane quality, while
yield seems to be primarily impaired by crop damages inflicted by
the mechanical harvest processes, such as ratoon damage and soil
compaction. Furthermore, our multivariate analysis of features
associated with soil pH revealed common behavior in two experi-
ments, evidencing the possibility of common underlying principles
to be identified across multiple sugarcane agricultural environ-
ments. Overall, these case studies demonstrate the usefulness of
the computational environment for supporting research in sugar-
cane agriculture, which will positively impact the sustainability
and competitiveness of the sugar-ethanol industry.
Acknowledgements
Project funded by CNPq and Fundação de Amparo à Pesquisa do
Estado de São Paulo (FAPESP grants 2011/01817-9 and
2015/01587-0).
References
Anselmi, A.A., Bredemeier, C., Federizzi, L.C., Molin, J.P., 2014. Factors related to
adoption of precision agriculture technologies in southern Brazil. In: ISPA (Ed.),
Proc. of the 12th International Conference on Precision Agriculture. ISPA,
Sacramento, California, p. 11.
Atkins, P., Paula, J. de, 2010. Physical Chemistry. Oxford University Press, Oxford.
Avanzi, J.C., Borghi, E., Bortolon, L., Bortolon, E.S.O., Luchiari Jr., A., Inamasu, R.Y.,
Bernardi, A.C.C., 2014. Adoption Level of Precision Agriculture for Brazilian
Farmers - 2011/2012 crop year. In: ISPA (Ed.), Proc. of the 12th International
Conference on Precision Agriculture. ISPA, Sacramento, California, pp. 1–2.
Bramley, R., Trengove, S.A.M., 2013. Precision agriculture in Australia: present
status and recent development. Eng. Agric. 33, 575–588.
Bramley, R.G.V., 2009. Lessons from nearly 20 years of Precision Agriculture
research, development, and adoption as a guide to its appropriate application.
Crop Pasture Sci. 60, 197–217. http://dx.doi.org/10.1071/CP08304.
Chen, N., Zhang, X., Wang, C., 2015. Integrated open geospatial web service enabled
cyber-physical information infrastructure for precision agriculture monitoring.
Comput. Electron. Agric. 111, 78–91.
Cliff, A.D., Ord, J.K., 1973. Spatial Autocorrelation. Pion, London.
CONAB, Ministério da Agricultura, Abastecimento, P., 2015. SAFRA 2015/16 -
Terceiro levantamento.
Elmasri, R., Navathe, S.B., 2010. Fundamental of Database Systems. Addison-
Wesley.
FAO, Food and Agricultere Organization of the United Nations, 2015. Statistics
Division – FAOSTAT) [www Document]. URL http://faostat3.fao.org (accessed
10.1.15).
Ferreira, J., Takai, O., Malkoviski, S., Pu, C., 2010. Reducing Exception Handling
Complexity in Business Process Modeling and Implementation: The WED-Flow
19
Approach. In: Meersman, R., Dillon, T., Herrero, P. (Eds.), On the Move to
Meaningful Internet Systems: Otm 2010, PT I, Hersonissos, Greece, pp. 150–167.
Garcia-Molina, H., Salem, K., 1987. Sagas. In: ACM SIGMOD International Conference
on Management of Data. San Francisco, pp. 249–259.
Gebbers, R., Adamchuk, V.I., 2010. Precision agriculture and food security. Science
327, 828–831. http://dx.doi.org/10.1126/science.1183899.
Godwin, R.J., Wood, G.A.A., Taylor, J.C., Knight, S.M., Welsh, J.P., 2003. Precision
farming of cereal crops : a review of a six year experiment to develop
management guidelines. Biosyst. Eng. 84, 375–391. http://dx.doi.org/10.1016/
S1537-5110(03)00031-X.
IRENA, 2015. Renewable energy capacity statistics 2015. Irena 44. http://dx.doi.org/
10.1016/j.renene.2014.09.059.
Johnson, R.A., Wichern, D.W., 2007. Statistical Analysis. Pearson - Prentice Hall,
Upper Saddle River.
Magalhães, P.S.G., Cerri, D.G.P., 2007. Yield monitoring of sugar cane. Biosyst. Eng.
96, 1–6. http://dx.doi.org/10.1016/j.biosystemseng.2006.10.002.
Marin, F.R., Jones, J.W., Royce, F., Suguitani, C., Donzeli, J.L., Filho, W.J.P., Nassif, D.S.
P., 2011. Parameterization and evaluation of predictions of DSSAT/CANEGRO for
Brazilian sugarcane. Agron. J. 103, 304. http://dx.doi.org/10.2134/
agronj2010.0302.
Mulla, D.J., 2013. Twenty five years of remote sensing in precision agriculture: key
advances and remaining knowledge gaps. Biosyst. Eng. 114, 358–371. http://dx.
doi.org/10.1016/j.biosystemseng.2012.08.009.
Pontes, A.O., Ling, L.Y., Sanches, G.M., Magalhães, P.S.G., Ferreira, J.E., Driemeier, C.E.,
2014. BDAgro – CTBE Database of Agricultural Experiments, Technical
Memorandum, MeT 11. Campinas. available at <https://forms.cnpem.
br/formularios/prodbiblio/DB/2338/MeT%20112014.pdf>.
Portz, G., Molin, J.P., Jasper, J., 2011. Active crop sensor to detect variability of
nitrogen supply and biomass on sugarcane fields. Precis. Agric. 13, 33–44.
http://dx.doi.org/10.1007/s11119-011-9243-4.
van Raij, B., Cantarella, H., Quaggio, J.A., Furlani, A.M.C., 1997. Recomendações de
adubação e calagem para o Estado de São Paulo. Instituto Agronômico,
Fundação IAC, Campinas. 285p.
Rodrigues Jr., F.A., Magalhães, P.S.G., Franco, H.C.J., 2012. Soil attributes and leaf
nitrogen estimating sugar cane quality parameters: brix, pol and fibre. Precis.
Agric. 14, 270–289. http://dx.doi.org/10.1007/s11119-012-9294-1.
Silva, C.B., de Moraes, M.A.F.D., Molin, J.P., 2011. Adoption and use of precision
agriculture technologies in the sugarcane industry of São Paulo state, Brazil.
Precis. Agric. 12, 67–81. http://dx.doi.org/10.1007/s11119-009-9155-8.
Song, X., Wang, J., Huang, W., Liu, L., Yan, G., Pu, R., 2009. The delineation of
agricultural management zones with high resolution remotely sensed data.
Precis. Agric. 10, 471–487. http://dx.doi.org/10.1007/s11119-009-9108-2.
Srinivasan, A., 2006. Precision Agriculture: An overview. Handbook of Precision
Agriculture, pp. 3–18.
Tagarakis, A., Liakos, V., Fountas, S., Koundouras, S., Gemtos, T.A., 2012.
Management zones delineation using fuzzy clustering techniques in
grapevines. Precis. Agric. 14, 18–39. http://dx.doi.org/10.1007/s11119-012-
9275-4.
Webster, R., Oliver, M.A., 2007. Geostatistics for Environmental Sciences. John Wiley
& Sonns, Ltd. http://dx.doi.org/10.1002/9780470517277.
Whelan, B.M., McBratney, A.B., 2000. The ‘‘null hypothesis” of precision agriculture
management. Precis. Agric. 2, 265–279.
Zamykal, D., Everingham, Y.L., 2009. Sugarcane and Precision Agriculture:
Quantifying Variability Is Only Half the Story – A Review. In: Lichtfouse, E.
(Ed.), Climate Change, Intercropping, Pest Control and Beneficial
Microorganisms. Springer, Netherlands, Dordrecht, pp. 189–218. http://dx.doi.
org/10.1007/978-90-481-2716-0.