Improved Approach to the Development of the Crop Monitoring System Based on the Use of Multi-Source Spatial Data

Abstract

The study describes the stages of conceptual modeling to provide a crop monitoring system based on multi-source spatial data to assess the state of agricultural crops. The process of developing geodatabase models, which is the basis of the crop monitoring system, considered the construction of a set of diagrams of the Unified Modeling Language (UML).
The UML Sequence diagrams have been developed to describe the specific properties of crop monitoring system components and their behavior. The developed Data flow diagram showed the data flow in the crop monitoring system and described the processes involved in the system for the transfer of data from source files to the geodatabase.
The approach presented in the study can be suggested as a methodology that is suitable for a wide range of developers of monitoring systems.

Full text

108
INTRODUCTION
In the modern world, the information about
the changes in the crop condition growth during
the season needs the integration of multi-source
data in one information system. Currently, the
conceptual model is a key component of the envi-
ronmental monitoring systems, which ensures the
integration of heterogeneous data between crop
state indicators and remote sensing data. The ap-
proach of conceptual modeling allows designing
a model, which is a tool for structuring data and at
the same time, it is software-independent. A con-
ceptual model provides an integration of system
dynamics, as well as shows interactions and con-
nections between the crop characteristics.
In implementing monitoring systems, the
starting point should be developing a conceptual
model of a system. The process of designing a
conceptual model expresses the origin of a prob-
lem as well as peculiarities of an object or a study
area. Because agricultural crops have spatial and
temporal characteristics, the conceptual model
would be expected to possess the spatial and tem-
poral schemes [Leroux et al. 2019].
Multi-source spatial datasets are mainly used
in agricultural practices in order to provide the
crop growth monitoring. Remote sensing data,
being the source of actual spatial information
both for farming and precision agriculture, re-
quires dierent pre-processing and thematic pro-
cessing techniques to be used in order to obtain
comparable information that would be integrated
into the crop monitoring systems [Rekha et al.
2018, Habibie et al. 2018, Weiss et al. 2020].
Satellite and air-born remote sensing can
signicantly contribute to providing repeatable
information with dierent spatial, spectral and
Journal of Ecological Engineering Received: 2020.07.15
Revised: 2020.07.30
Accepted: 2020.08.15
Available online: 2020.08.25
Volume 21, Issue 7, October 2020, pages 108–114
https://doi.org/10.12911/22998993/125442
Improved Approach to the Development of the Crop Monitoring
System Based on the Use of Multi-Source Spatial Data
Svitlana Kokhan1*, Oleksandr Dorozhynskyy2, Khrystyna Burshtynska3,
Anatoliy Vostokov1, Oleg Drozdivskyi1
1 Department of Geoinformatics and Aerospace Research of the Earth, National University of Life and
Environmental Sciences of Ukraine, 17 Vasylkivska St., Kyiv, Ukraine
2 Department of Environmental Engineering and Geodesy, University of Life Sciences in Lublin, Leszczyńskiego
St. 7, 20-069 Lublin, Poland
3 Department of Photogrammetry and Geoinformatics, Institute of Geodesy, Lviv Polytechnic National
University, Lviv, Ukraine
* Corresponding author’s e-mail: kokhan_s@nubip.edu.ua
ABSTRACT
The study describes the stages of conceptual modeling to provide a crop monitoring system based on the multi-
source spatial data to assess the state of agricultural crops. The process of developing geodatabase models, which
is the basis of the crop monitoring system, considered the construction of a set of diagrams of the Unied Model-
ing Language (UML). The UML Sequence diagrams were developed to describe the specic properties of crop
monitoring system components and their behavior. The developed data ow diagram showed the data ow in the
crop monitoring system and described the processes involved in the system for the transfer of data from the source
les to the geodatabase. The approach presented in the study can be suggested as a methodology that is suitable for
a wide range of developers of monitoring systems.
Keywords: geodatabase, spatial data, remote sensing, crop monitoring system

109
Journal of Ecological Engineering Vol. 21(7), 2020
temporal resolutions over a large area. The fol-
lowing applications of remote sensing data in
agriculture are mainly reported: crop state moni-
toring, drought/water stress monitoring; yield es-
timation; crop acreage determination; cropland
mapping; mapping of land use/land cover chang-
es; precision agriculture and irrigation manage-
ment [Atzberger 2013]. Satellite remote sensing
and application of multicriteria analysis for maize
cultivation were described in [Habibie et al.
2018]. An overview of remote sensing and proxi-
mal sensing data in agriculture was presented by
M. Weiss [Weiss et al. 2020] for various scales
and a large range of stakeholders.
Satellite monitoring is applicable for the eval-
uation of the vegetation dynamics based on the
relevant vegetation indices for a certain period
and providing the access to the crop rotation data
of the eld and of the given crop. The relevant
information on the current stage of crop growth
and development is also widely monitored.
Remote sensing based on Unmanned Aerial
Vehicle (UAV) data has also been proven to be
an efcient tool and it is widely applied in rapid
and non-destructive estimation of crop status,
leaf N content and LAI evaluation [Hyun et al.
2013, Quemada et al. 2020]. The study of Gon-
zalo Cucho-Padin et al. [Cucho-Padin et al. 2019]
showed the developing Open-Software tools for
the analysis of the vegetation parameters based
on the UAV images.
Since crops have diverse temporal character-
istics, the conceptual model should include the
spatial and temporal patterns. The heterogeneous
data obtained from dierent observations can-
not be directly compared because they have not
been collected under the same set of acquisition
conditions, e.g. within the same time period, with
consistent sensors or under similar management
practices [Leroux et al. 2019]. Thus, all input
data should be unied and it is known to be rather
complex task. It demands a wide range of scien-
tic approaches to be applied for the construct-
ing environmental modeling structures [Argent
2004]. Moreover, the development of domain-
specic software structures is a complex task,
in which it is necessary to take advantage of the
modern software development process. In addi-
tion, there is a need to take into account the fact
that the developers should be specialists in agri-
cultural production, data processing specialists in
remote sensing, GIS specialists and software en-
gineers [Argent 2004].
Thus, the conceptual model is the most expedi-
ent tool to develop a diagram based on UML. The
Unied Modeling Language (UML) is a software
standard modeling language for visualizing, spec-
ifying, constructing and documenting elements
of systems, and at that time software systems are
complex systems consisting of cooperating het-
erogeneous software, hardware and database sub-
systems, trading and distribution of agricultural
products. The UML is used for the documentation
and the describing the functionalities provided by
the system and their associated interactions.
Designing models of systems based on UML
diagrams was considered in papers [Khaiter
and Erechtchoukova 2019, de Kinderen and
Kaczmarek-Heβ 2019]. Khaiter and Erechtchou-
kova presented a formalized approach to the entire
process of software development and design in the
area of sustainable decision-making on the basis of
ecosystem services with using methodology on the
application of the UML. De Kinderen et al. dem-
onstrated the application of multi-level, integrated
modeling and programming to model organiza-
tional structures which allows overcoming some
limitations to modeling approaches situations.
Decision Support System which is able to as-
sist farmers to make proper decisions is presented
in the paper [Zhai et al. 2020]. It is described the
use of UML for modeling data in order to obtain
the desired information to increase the agricultur-
al productivity by receiving the weather informa-
tion through a decision support system.
UML sequence diagrams provide valuable
information for comprehension, debugging,
maintenance, and software archeology. In the
study [Alvin et al. 2019] presented a framework
for static generation of UML sequence diagrams
from object-oriented source code, which provides
a query renement system to guide the interac-
tions in the source code. The proposed technique
involves constructing a hypergraph representa-
tion of the source code, traversing the hypergraph
with respect to a user-dened query, and generat-
ing the corresponding set of sequence diagrams.
This technique implemented framework as a tool,
StaticGen (supporting software: StaticGen).
The study [Jetlund et al. 2019] aimed to im-
prove the implementation of geospatial mod-
els in Web Ontology Language (OWL). The

Journal of Ecological Engineering Vol. 21(7), 2020
110
methods and rules for the conversion of the
geospatial information from UML models to
implementation as OWL Ontologies were pre-
sented in the paper.
In the study [Sadowska and Huzar 2019] the
rules for conversion and verication of UML
class diagrams to their OWL 2 representation
were reviewed. The extent to which state-of-
the-art transformation rules cover the semantics
expressed in class diagrams was presented. New
transformation rules showing the semantics not
yet covered but expected from the point of view
of domain modeling pragmatics were determined.
The transformations proposed in the study can be
used for automatic validation of compliance of
UML class diagrams with respect to OWL 2 do-
main ontologies.
In the paper [Filipova and Nikiforova 2019]
dened more than 20 rules, which should be fol-
lowed while creating use case diagrams to make
them more ecient to visualize and understand.
The requirements of the use case diagrams and
placement criteria were also examined, which
served as a basis for the creation of an automatic
use case diagram layout algorithm.
STATEMENT OF PROBLEM
Many developed techniques usually take into
account one data source in order to provide crop
monitoring and evaluation of the crop state. These
are mainly the satellite remote sensing data and
ground-based data, or air-born data with ground-
based information. The problems of structuring
spatio-temporal multi-source data for assessing
the state of crops that provide a convenient and
user-friendly display of data being the basis of
the monitoring system, are not suciently con-
sidered in previous studies.
In order to increase the eciency of the crop
monitoring system and to provide the appropri-
ate information support of farmers, the presented
multi-level approach includes the stages of con-
ceptual modeling to develop the crop monitoring
system for assessing the state of crops, is given
in the paper.
The aim of the study was to describe the pro-
cess of the development of geodatabase models
in order to provide the crop monitoring sys-
tem. During the study, the following tasks were
solved: to develop the models of the crop geoin-
formation system based on UML and to describe
the structure of the geodatabase of the crop mon-
itoring system.
RESEARCH METHODOLOGY
The approach based on the Unied Mod-
eling Language (UML) was used when devel-
oping the models of the geoinformation crop
monitoring system. The UML approach pro-
vides the combination of static structure ele-
ments with dynamic properties [Khaiter and
Erechtchoukova 2019], expands the possible
applications of geodatabases.
The unied modeling language UML iden-
ties key stakeholders and considers their par-
ticipation goals. Using three groups of graphical
models (functional, object, and dynamic), UML
provides a description of various aspects of de-
velopment of the crop monitoring system.
The developed multi-level approach included
the stages of conceptual modeling in order to pro-
vide the crop monitoring system based on multi-
source spatial data for assessing the state of crops.
A conceptual modeling expresses the most
signicant features of the real processes and phe-
nomena providing the possibility to take into ac-
count the logical representation of the data struc-
ture and the support for all representations of us-
ers being the basis for the further design of the
developed system.
UML diagrams are the diagrams based on
the Unied Modeling Language with the pur-
pose of visually representing a system. The two
broadest categories of UML diagrams are Be-
havioral and Structural UML diagrams. Some
UML diagrams describe the structure of a sys-
tem, and other express the system’s behavior.
The crop monitoring system is described rstly
by the behavior of its building components,
which have dierent origin, spatial, temporal
and spectral properties. In order to properly
describe the crop monitoring system which in-
cludes multi-source data, a set of Sequence dia-
grams were used in the study.
The crop rotation, which is located at the Uni-
versity’s Experimental Station in northern Forest-
Steppe of Ukraine in Kyiv region, was used as
test site in the study (Figure 1).

111
Journal of Ecological Engineering Vol. 21(7), 2020
RESULTS AND DISCUSSION
The development of a conceptual model of
crop monitoring system is carried out by con-
structing a set of UML diagrams. Taking into ac-
count the specic features of the components of
crop monitoring system and in order to explain
interactions between them, the UML Sequence
diagrams were designed in the study.
The general sequence of obtaining data to
provide crop monitoring, including the spatial-
temporal characteristics of crops, the necessary
and sucient amount of remote sensing data,
ground-based and laboratory measurements, is
shown in Figure 2.
The spectral characteristics of crops, obtained
both in-situ and those based on satellite and air-
born imagery, biometric and biophysical param-
eters of vegetation measured under eld condi-
tions, are incorporated into geospatial database.
These data are used for modeling crop state. For
validation and verication of models, eld mea-
surements were conducted in crop rotation on
chernozem soils. Thus, the diagram reects the
general sequence of obtaining spatial and non-
spatial data for the crop monitoring system in a
compact form.
The next stage of modeling is the development
of sequence diagram, which describes the process
of obtaining remote sensing data, including satel-
lite data of medium and high spatial resolution,
air-born imagery, and determines the necessary
and sucient amount of remote sensing data to
provide crop monitoring. The metadata analysis
involves the application of free satellite imagery
sources. In order to request commercial satellite
imagery, the product level, period of image ac-
quisition, cloud cover (%), satellite viewing angle
are indicated as well as the area of interest.
The period of data acquisition, camera type,
ight altitude and image spatial resolution are
requested to order the air-born imagery. Quasi-
synchronous measurements in-situ based on
GreenSeeker active sensor are important compo-
nents of the system (Figure 3). The GreenSeeker
NDVI values were used for calibration and veri-
cation of satellite and air-born data. The NDVI
values were measured at a certain location with
known coordinates. The adjusted ground vegita-
tion index (VI) are applicable in modeling time
series data for crop monitoring. The next stage
includes the provider selection of remote sens-
ing data and the availability of software for pre-
processing of dierent data formats and their
thematic processing (Figure 4).
Advanced remote sensing technologies con-
tinue to broaden the capabilities of satellite
Figure 1. The University’s Experimental Station
Figure 2. The general sequence of obtaining spatial and non-spatial data

Journal of Ecological Engineering Vol. 21(7), 2020
112
imaging, providing more types of data at a dif-
ferent scale.
Space, air-born and ground segments are de-
signed to collect, process and provide informa-
tion in a proper time. The space segment ensures
the ability to collect data based on dierent spa-
tial, temporal, spectral and radiometric resolu-
tion. The air-born segment enables receiving data
within test sites and the ground segment ensures
data collection for calibration and verication of
remote sensing data.
Using the specic techniques of remote sens-
ing data pre-processing and thematic processing
is one of the important tasks of this stage. For sat-
ellite images, geometric correction is carried out
on a pixel-by-pixel basis. Atmospheric correction
is an obligatory process. On the basis of the UAV
data, orthophotos are created for each spectral
channel. Sub-pixel geometric correction of the
imagery obtained at a dierent date is performed
based on a certain orthophoto with maximal spa-
tial resolution [Stankevich et al. 2018]. The test
points for the GreenSeeker ground measurements
as well as the plant sampling for chemical analy-
sis are the same. The above-mentioned techniques
have been also applied in the study of the crop
state monitoring [Kokhan and Vostokov 2020].
The next important stage in creating a model
of the crop monitoring system is to develop a Data
Flow diagram (DFD). The DFD allows creating
a ow of data in an information system and de-
scribes the processes that are involved in a system
to transfer data from the source les to the stor-
age les and generation of reports. A DFD for the
crop monitoring system is presented in Figure 5.
UML is successfully used to develop complex
software and business project systems. It is also
applied in the modelling of the ISO 19100 series
Figure 4. Remote sensing data providers and data processing
Figure 3. Remote sensing data collection

113
Journal of Ecological Engineering Vol. 21(7), 2020
of International Standards in the geographic in-
formation (geoinformation/geomatics) domain
and INSPIRE data specication. However, de-
spite the obvious advantages, UML is not cur-
rently widely used in software development in the
area of information systems for crop monitoring.
As the example of the developed elements of
crop monitoring system, a fragment of test site is
presented in Figure 6. Dierent crop growth fac-
tors such as soil fertility, moisture content as well
as the presence of hydrocarbon deposits, signi-
cantly inuenced the state of winter rapeseed [Ly-
alko and Popov 2006].
The winter rapeseed state is based on the data
from the Parrot Sequoia multi-spectrum sensor
installed on UAV Disco Pro AG. Geometric cor-
rection, calibration of the outputs of the camera is
based on the sunshine sensor. The thematic pro-
cessing of data has been also done. Perpendicular
vegetation index PVI was derived from the pro-
cessed data to evaluate the healthy, diseased and
damaged vegetation (Figure 6).
CONCLUSIONS
The article presents a conceptual model as a
key component of the crop monitoring system,
which provides integration of heterogeneous
data between the yield indicators and remote
sensing data. In this study, the authors described
the process of developing geodatabase models
considering the construction of a set of diagrams
of the Unied Modeling Language (UML). UML
was used in the development of both a geoinfor-
mation crop monitoring system and the structure
of the geodatabase.
It was shown that the crop monitoring system
is described by the behavior of its components,
which have dierent spatial, temporal and spec-
tral characteristics. A set of Sequence diagrams
was developed to describe the crop monitoring
system. The created Data Flow diagram showed
the data ow in the crop monitoring system and
described the main processes involved in the
functioning of the system.
Acknowledgments
Publication is funded by the Polish National
Agency for Academic Exchange under the Inter-
national Academic Partnerships Programme from
the project „Organization of the 9th International
Scientic and Technical Conference entitled En-
vironmental Engineering, Photogrammetry, Geo-
informatics – Modern Technologies and Develop-
ment Perspectives”.
Figure 5. A Data Flow diagram for the crop monitoring system
Figure 6. Test area fragment with damaged plants

Journal of Ecological Engineering Vol. 21(7), 2020
114
REFERENCES
1.
Argent, R. 2004. An overview of model integra-
tion for environmental applications – components,
frameworks and semantics. Environmental Mod-
elling & Software. 19(3), 219–234. https://doi.
org/10.1016/S1364- 8152(03)00150–6
2. Atzberger, C. 2013. Advances in Remote Sensing
of Agriculture: Context Description, Existing Op-
erational Monitoring Systems and Major Informa-
tion Needs. Remote Sensing. 5(2), 949–981. http://
https://doi.org/10.3390/rs5020949
3.
Cucho-Padin, G., Loayza, H., Palacios, D., Balcazar,
M., Carbajal, M., Quiroz, R. 2019. Development of
low-cost remote sensing tools and methods for sup-
porting smallholder agriculture. Applied Geomat-
ics. https://doi.org/10.1007/s12518–019–00292–5
4.
Filipova, O., Nikiforova, O. 2019. Denition
of the Criteria for Layout of the UML Use Case
Diagrams. Applied Computer Systems 24(1),
75–81. ISSN 2255–8691. https://doi.org/10.2478/
acss-2019–0010
5.
Habibie, M., Noguchi, R., Shusuke, M., Ahamed, T.
2019. Land suitability analysis for maize production
in Indonesia using satellite remote sensing and GIS-
based multicriteria decision support system. Geo-
Journal ,32 DOI: 10.1007/s10708–019–10091–5
6.
Hyun, C., Lee, J., Lee, I. 2013. Assessment of hydro-
gen uoride damage to vegetation using optical re-
mote sensing data. In: International Society for Pho-
togrammetry and Remote Sensing. Spatial Inf. Sci.,
XL-7/W2” proceedings. Antalya, Turkey. https://doi.
org/10.5194/isprsarchives-XL-7-W2–115–2013
7. Jetlund, K., Onstein, E., Huang, L. 2019. Adapted
Rules for UML Modelling of Geospatial Informa-
tion for Model-Driven Implementation as OWL On-
tologies. International Journal of Geo-Information.
8(9), 1–26. https://doi.org/10.3390/ijgi8090365
8.
Khaiter, P., Erechtchoukova, M. 2019. Concep-
tualizing an Environmental Software Modeling
Framework for Sustainable Management Using
UML. Journal of Environmental Informatics. 34(2).
123–138. https:// doi:10.3808/jei.201800400
9.
de Kinderen, S., Kaczmarek-Heβ, M. 2019. On
model-based analysis of organizational structures:
an assessment of current modeling approaches and
application of multi-level modeling in support of
design and analysis of organizational structures”.
Software and Systems Modeling, (19), 19. https://
doi.org/10.1007/s10270–019- 00767–4
10. Kokhan, S. and Vostokov, A. 2020. Using Vegeta-
tive Indices to Quantify Agricultural Crop Char-
acteristics. J. Ecol. Eng., 2020. 21(4):120–127.
DOI: https://doi.org/10.12911/22998993/119808
11. Leroux, C., Jones, H., Pichon, L., Taylor, J., Tissey-
re, B. 2019. Automatic harmonization of heteroge-
neous agronomic and environmental spatial data.
Precision Agriculture, 2019. 20. 1211–1230. https://
doi.org/10.1007/s11119–019–09650–0
12. Lyalko, V. and Popov, M. 2006. Multispectral Re-
mote Sensing in Nature Management. Naukova
Dumka. Kyiv., p. 43 – 62. ISBN 966–00–0403–1
(In Ukrainian)
13.
Purnamasari, R., Ahamed, T., Noguchi, R. 2018.
Land suitability assessment for cassava production
in Indonesia using GIS, remote sensing and multi-
criteria analysis. Asia-Pacic Journal of Regional
Science, Springer 3(1), 1–32. http://doi: 10.1007/
s41685–018–0079-z
14.
Quemada, M., Lassaletta, L., Leip, A., Jones, A.,
Lugato, E. 2020. Integrated management for sus-
tainable cropping systems: Looking beyond the
greenhouse balance at the eld scale. Global Change
Biology, https://doi.org/10.1111/gcb.14989
15.
Rekha, B., Ajawan, P., Desai, V. 2018. Remote
Sensing Technology and Applications in Agricul-
ture. In: International Conference on Computational
Techniques, Electronics and Mechanical Systems
(CTEMS): proceedings. 193–197. Karnataka, India.
http://doi. 10NN.1109/CTEMS.2018.8769124
16. Sadowska, M., Huzar, Z. 2019. Representation of
UML Class Diagrams in OWL 2 on the Background
of Domain Ontologies. e-Informatica Software En-
gineering Journal (EISEJ). 13(1), 63–103. https://
doi.10.5277/e-Inf190103
17.
Stankevich, S., Shklyar, S., Lisenko, A. 2018.
Prohramnyy modulʹ otsinky subpikselʹnoho zmish-
chennya znimkiv, otrymuvanykh z kvadrokopteru.
Ukrayinsʹkyy zhurnal dystantsiynoho zonduvan-
nya Zemli. (17). 10–13. http://nbuv.gov.ua/UJRN/
ukjdzz_2018_17_4 (in Ukrainian)
18. Weiss, X., Jacobb, F., Duveillerc, G. 2020. Remote
sensing for agricultural applications: A meta-review.
Remote Sensing of Environment (236). https://doi.
org/10.1016/j.rse.2019.111402
19.
Zhai, Z., Martínez, J., Beltran, V., Martínez N. 2020.
Decision support systems for agriculture 4.0: Sur-
vey and challenges”. Computers and Electronics
in Agriculture. 170, 16. https://doi.org/10.1016/j.
compag.2020.105256
20.
Zhai, C., Peterson, B., Mukhopadhyay, S. 2019.
Static generation of UML sequence diagrams.
International Journal on Software Tools for
Technology Transfer. 23. https://doi: 10.1007/
s10009–019–00545-z