=Paper=
{{Paper
|id=Vol-2790/paper12
|storemode=property
|title=
Formation of the Digital Platform for Precision Farming with Mathematical Modeling
|pdfUrl=https://ceur-ws.org/Vol-2790/paper12.pdf
|volume=Vol-2790
|authors=Victor Medennikov,Alexander N. Raikov
|dblpUrl=https://dblp.org/rec/conf/rcdl/MedennikovR20
}}
==
Formation of the Digital Platform for Precision Farming with Mathematical Modeling
==
https://ceur-ws.org/Vol-2790/paper12.pdf
Formation of the Digital Platform for Precision
Farming with Mathematical Modeling
Victor Medennikov[0000-0002-4485-7132], Alexander Raikov 1[0000-002-6726-9619]
1 Federal Research Center ”Informatics and Control” of the Russian Academy of Sciences,
Vavilova 44-2, 119333, Moscow, Russia
2 V.A. Trapeznikov Institute of Control Sciences of the Russian Academy of Sciences
65 Profsoyuznaya street, 117997, Moscow, Russia
dommed@mail.ru, alexander.n.raikov@gmail.com
Abstract. The paper addresses the issue of development trends of precision
farming technologies (PFT) in the world. PFT's rapid development's main mo-
tive is the improvement of geoinformation technologies, artificial intelligence,
and other cutting-edge digital technologies. It is shown that these technologies
are currently evolving from the digitalization of individual operations to the
digitalization of an interconnected set of operations in crop production and re-
lated industries. The approach makes PFT available for small and large farms.
The paper analyzes the problems of PFT implementation such as following: the
lack of a clear strategy in this area, weakening of scientific researches, the dom-
inance of the “task-based” approach of the development and implementation of
digitalization systems, significant underutilization of traditional factors of in-
creasing production efficiency in the industry, limited financial, labor, material
and technical resources, poverty of most households. The paper discusses the
scientific basis for designing an optimal digital platform for precision farming
based on mathematical and ontological modeling. An analysis is made of the
constituent modules of a promising digital platform of precision farming inte-
grated into unified geographic information space. To demonstrate the possibil-
ity of forming a cloud service of the value chain, the concept of the single cloud
Internet space for digital interaction of the logistic activities of agricultural pro-
duction, processing, and marketing of its products is presented.
Keywords: Digital Platform, Precision Farming, Mathematical Modeling, Geo-
graphic Information System.
1 Introduction
An increasing number of countries are currently giving strategic priority to the digital-
ization factor of developing an effective interaction between the state, business, and
population. Based on the acquired positive experience of countries' digital transfor-
mation, this process is becoming increasingly large-scale and dynamic. The digitaliza-
tion of the economy has significantly affected agriculture, turning it into industrial
production. For example, in 2018, in the UK, for the first time in the world, winter
Copyright © 2020 for this paper by its authors. Use permitted under Creative
Commons License Attribution 4.0 International (CC BY 4.0).
121
wheat has been grown in one hectare area without people's direct participation. A
good harvest was obtained. Robotic agricultural machines and units carried out all
technological operations from processing the soil to threshing the grain.
The upcoming digital era of agricultural industrialization in industrialized countries
requires introducing the most modern information and communication technologies
(ICT) in management and agricultural machinery in almost all production and auxilia-
ry technologies. In digital technologies, countries see the main means of increasing
the efficiency and quality of industrial products in the world against the background
of exhaustion of other factors of its growth, which include: obtaining more productive
varieties of cultivated plants, an invention of more energy-efficient agricultural mech-
anisms, the formation of optimal agricultural technology systems, the emergence of
effective remedies and feeding plantations. Goldman Sachs Bank believes that digital
technologies can increase industry productivity in the world by 70% by 2050.
At the same time, the leading technology is precision farming technology (PFT),
which increases productivity to the degree that cannot compare with the appearance
of tractors, chemical fertilizers, pesticides, herbicides, and genetically modified seeds
and plants. Precision farming (PF) is the approach that utilizes cutting edge infor-
mation technology to achieve the greatest improvement and efficiency in agricultural
systems. This approach exploits modern information technology tools such as Global
Positioning System (GPS), Geographical Information System (GIS), and Remote
Sensing to improve farm management [1].
The essence of PFT is the integration of new agricultural technologies with the
high-precision positioning based on remote sensing technologies (Earth remote sens-
ing) and differentiated highly effective and environmentally friendly agricultural prac-
tices in the fields based on detailed information on the chemical and physical charac-
teristics of each site. As a result of this integration, by creating optimal conditions for
the growth and development of crops within environmental safety boundaries, digital
PFT makes it possible to obtain the maximum number of products with requirements
for quality, price, and safety.
This shows that agriculture has to combine a huge amount of heterogeneous, mul-
tidimensional, diversified information with appropriate technologies for its pro-
cessing. As a result, PFT has evolved from the digitalization of individual operations
to a complex of operations in crop production and the integration of operations in
related industries. A significant reduction in the cost of digital technologies has pro-
pelled them to such a level that it has become possible to receive information about
each operation with any agro-industrial facility and its surroundings with an accurate
analysis of all actions' consequences. Accounting and monitoring the maximum pos-
sible number of agricultural processes become the main goal in developing a digitali-
zation strategy for the world's largest agricultural and engineering companies.
Russian agriculture lags far behind the pace of the digitalization of developed
countries. One of the reasons is the absence of a clear national strategy in the agricul-
ture area. There are a lot of factors affecting both the industry itself and its digitaliza-
tion. A scientifically integrated approach to the industry's digital transformation based
on mathematical modeling, taking into account financial, labor material, and technical
122
resources, is required. This concerns the PFT, an integrator of a significant number of
agricultural technologies, remote sensing, and geographic information systems.
Authors' papers [2, 3] represent results of the analysis of the experience of creating
information systems in the agro-industrial complex of Russia within the framework of
the Comprehensive Program of Scientific and Technological Progress of the Member
States of the Council for Mutual Economic Assistance. In these papers, the conceptual
approach to the digital transformation of agriculture using the necessary conditions
for applying this approach is suggested. To develop this approach in this paper, a
more detailed scientific elaboration of the PFT's dominant digital technology is given;
the upper-level of the architecture of the unified digital agricultural platform created
in the context of international standards is presented.
2 Review and Trends
The main motivator for the rapid development of PFT in recent years was the im-
provement of ICT, electron-optical surveying equipment, the formation of global
positioning systems that can simultaneously determine the coordinates of a significant
number of objects with high accuracy anywhere in the world. There are a lot of papers
devoted to this issue.
For example, the paper [4] highlights that the PFT tools are gaining ground in sus-
tainable agriculture policies. The authors suggest a model that describes different
farms with different propensity to adopt precision farming tools. The paper marks two
main limitations. The first one concerns the representativeness of the sample: farmers
were selected during fairies devoted to PFTs. Secondly, the adoption rates vary wide-
ly among different kinds of PFT [5]. In this context, the authors considered precision
farming tools as unique.
The paper [6] addresses the issue of influencing the trend of precision livestock
farming on human-animal relationships. It is shown that introduction of this approach
does not always depredate human-animal relationships. Farmers spend more time in
front of the computer each day looking at digital data about the animals. But the paper
does not describe the details of working with digital technology.
The paper [7] devoted the idea that sensory signals help make animal production
decisions more effective and achieve significant animal husbandry and farming gains.
Sensing technology can make animal farming more holistic, humane, environmentally
friendly, centralized, large scale, and efficient. There are many types of machine
learning algorithms. For getting the desired outcome of the animal welfare evaluation,
the choice of features for data analysis has to be done. For example, from a set of 44
features, perhaps only five to seven features may be needed to yield highly accurate
classification results. In real-time systems, large feature sets could be problematic due
to computational complexity. The paper shows that the machine learning algorithm
has to take into account the behavior of animals in different environments because it
can show discrepancies in classification results, which can be due to differences in the
animals or environmental characteristics.
123
Some innovative examples show the trend of using GIS in PFT for collecting, stor-
ing, processing, and displaying spatial data of a certain object or event on a map. The
research work [8] presents a GIS approach for assessing the biogas production poten-
tial's spatial distribution by taking into account the seasonal variation of this produc-
tion. The results proved that seasonal variations of the potential of non-lignocellulosic
agricultural residues and municipal bio-waste could be neglected since the generated
feedstocks have near-continuous generation during the whole year.
Different applications can extend GIS systems. For example, the article [9] pre-
sents the r.landslide system. This is a free and open-source add-on to the open-source
GIS for landslide susceptibility mapping, written in Python. Land-use planning organs
can use it as a support tool very agile and effective. This system could be intended to
support early-warning systems for events that are triggered by rainfall.
The GIS using in various industries has led to the fact that such data currently oc-
cupy a predominant share of all stored data—over 80%, the bulk of Earth remote
sensing data. Due to such properties, remote sensing and GIS technologies immedi-
ately found their widespread use in technologies of remote sensing throughout the
world due to the obvious spatio-temporal nature of the agricultural activity.
Modern electron-optical equipment installed on various mobile (space, air, sea,
transport, agricultural) and stationary devices has such a resolution that allows solving
a significant range of problems in the field of agricultural production - from mapping
the boundaries of individual land plots to the analysis of using intended to land and
plant conditions over large areas. Thanks to special means of deciphering the vegeta-
tion cover's spectral characteristics, it became possible to calculate various vegetation
indices that reflect the dynamics of crops' development, their biomass. The use of the
dynamic data series of remote sensing data makes it possible to monitor the imple-
mentation of agricultural measures to identify the fields infected by pests and diseases
in the dynamics and the damage caused to them due to natural disasters. Every year,
the list of tasks to be solved is significantly replenished.
J'son & Partners Consulting presents the research results devoted to the world mar-
ket of cloud platforms of the Internet of Things (IoT) for agriculture in Russia [10].
This company believes that two specialized platforms are gradually formed in agricul-
ture: agrarian data aggregator platforms; otherwise, platforms for primary data collec-
tion and accumulation (information resources) and application platforms. These two
platforms must be integrated with the intensive mutual exchange of data. At the same
time, data analysis is carried out in both platforms, and applications in the form of
automation of production management using information resources are solved only in
application platforms. It is also argued that such symbiosis is possible only through
the development of appropriate cloud platforms and services since only such cloud
technology makes them available for enterprises of all sizes and not just for some of
the largest farms. The appearance of these services, including those available for
small farms, will significantly increase the industry's efficiency and reduce the risks
of activity for all participants in the value chain: suppliers of resources, consumers of
products, and transport companies. This chain's main element is cloud platforms and
applications for crop production and universal logistics platforms and applications
124
that form 86% of the total amount of information consumed. The massive use of such
a cloud service in the agricultural business is only planned.
This company also believes that using the two types of technologies of the above-
mentioned cloud platforms in the supply chain (wholesale companies, logistics, retail
chains) will provide an opportunity to switch to direct sales, in which the manufactur-
er traces the final consumer, the volume and structure of his demand, and through the
use of mathematical models, in particular, artificial intelligence and predictive analyt-
ics, it produces exactly the products that the consumer needs and at the right time, and
delivery control is realized by automatic exchange of information between partici-
pants in the supply chain and minimizes the use of warehouse and logistics infrastruc-
ture resellers. Such an approach makes it possible to exclude any unnecessary inter-
mediaries from the chain, which now account for up to 80% of the cost in the retail
price of goods. It is believed that in total, these two factors can increase the volume of
agricultural products consumption in Russia by 1.5 times in monetary terms. Simulta-
neously, the decrease in retail prices will be compensated by an increase in the vol-
ume of consumption of goods. AS a result, the margin of agricultural producers' busi-
ness even grows with a decrease in risks. Due to this, the fleet of tractors in the indus-
try may increase by 300 thousand units, combines will increase by 200 thousand
units, and the use of fertilizers can grow nine times.
Agriculture, in terms of the production process, looks and is usually described as a
system of its interrelated elements in the form of production resources. To produce a
certain type of product with required qualitative and quantitative characteristics, strict
proportions between the system's elements (resources) must be observed due to the
general and specific requirements of the planned products' production technologies.
Deviations from technological requirements for the quality and quantity of one of the
resources entail certain changes in using other resources, which ultimately leads to the
products' quantitative and qualitative consequences. With the awareness of the im-
portance of the digital economy, as one of the resources, along with the material, hu-
man and financial ones, most affecting the economy, their rational use becomes very
obvious in conditions of their limited number. Therefore, depending on the resource
base, the state of agricultural machinery, and personnel's education, each country
chooses its own approach to the industry's digitalization, choosing individual digital
technologies. So, in the USA, already 40-50% of farms use PFT technologies, which
is about 40% of the world's market. Monitoring of US farms has shown that the fol-
lowing PFT services are most popular: rapid soil analysis (90% of farms); yield moni-
toring and mapping, space navigation technology (80%); dosed fertilizer application
based on technological maps (60%); images from spacecraft, vegetative indices of
cultures (30%) [11].
In the European Union, almost all countries are beginning to use PFT, while Ger-
many is the PFT leader. Significant experiments are planned with PFT in Asia: China
and India. In Germany, the Atfarm digital service is currently being tested. The At-
farm is a cloud-based service in the field of PFT developed by the Norwegian compa-
ny Yara for dosed plant nutrition based on plant health data collected using Yara N-
Sensor equipment [12]. This service helps farmers to apply nitrogen fertilizers using
satellite remote sensing data at each specific site. The Yara N-Sensor is equipment
125
allowing to determine the requirements of plants for nitrogen. It moves during the
fields with dosing of fertilizer application on a plot of 20x20m in size. Although the
Yara N-Sensor costs about 25,000 euros, which is extremely expensive for Russia, it
gives the most accurate recommendations of all methods and does not depend on the
weather. Most technologies based on satellites and Unmanned Aerial Vehicles (UAV)
depend on the region's cloudiness.
3 Problems of Introducing PFT in Russia
Precision farming is defined as a system consisting of interconnected subsystems:
differentiated production technologies in crop production, a software and hardware
complex for high-precision positioning of technological operations of the production
process, a set of technical and agro-chemical means meeting the quality and quantity
requirements. Therefore, the use of PFT should occur using an integrated approach. It
requires the appropriate integration of information systems and information resources.
However, today in Russia’s agriculture, a task-oriented approach to the design and
development of information systems (it is also called patchwork, island informatiza-
tion) prevails, when they either order independently or purchase individual software
systems that are ready from various manufacturers and are neither connected ontolog-
ically, nor functionally, nor informational. It was still possible to put up with this
situation before the digital age due. But now, in the era of total digitalization of the
economy, the low level of penetration of informatization into the enterprise manage-
ment system, the haphazard introduction of ICT leads to huge losses.
This is also true concerning the PFT. So, the first experiments of their use in Rus-
sia's agrarian production show their non-integrated, fragmentary use of individual
technologies with filling heterogeneous information that differs in a structure during
sending from one farm to another. In connection with the mass introduction of infor-
mation systems and individual technologies of PFT, only in the last two years, the
heads of information departments of agricultural companies began to pay keen atten-
tion to the weak unification of primary accounting, patchwork computerization of
business, the introduction of software systems, databases, the absence of a unified
system of reference information.
At the end of 2019, a draft concept of the national platform “Digital Agriculture of
Russia” was developed. It provides a list of sub-platforms, the composition of which
is determined from a task-based approach. The sub-platforms included: a sub-
platform for collecting agricultural statistics, a sub-platform for providing information
support and services, a sub-platform for digital land use and land devices, a sub-
platform for storing and disseminating information materials, a sub-platform for
traceability of agricultural products, a sub-platform for agro-meteorological forecast-
ing, a multi-factor service operational monitoring, diagnostics and proactive modeling
of the development of crop diseases. Such an approach to the digital platform (CPU)
of agriculture, such as combining these sub-platforms, excludes their integration on a
truly integrated unified CPU agribusiness.
126
However, the concept says almost nothing about the transformation of national ag-
ricultural management technology. The problems of forming a unified educational
environment, which should play a tripartite role, are almost not addressed: support for
scientific research, raising the level of education, an effective system of transfer of
scientific and educational knowledge to the economy due to unlimited access to
knowledge not only to traditional users in the person of scientists, students, and teach-
ers but also to prospective applicants and employers, government agencies, producers,
business, management, other categories of the population. Such a unified information
space of scientific and educational resources should remove the contradictions be-
tween the volumes of accumulated knowledge and their effective use, as well as a tool
to improve the quality of human capital, its assessment, and the impact on the socio-
economic situation in the industry.
The number of companies offering various individual solutions in precision farm-
ing based on GIS technologies is growing. Since these technologies are implemented
in fragmented form, GIS is also capturing only individual aspects of the processes.
Moreover, the logical database structures are incomplete subsets of the ideal unified
informational scheme of plant growing [13], which poses a threat to the future inte-
gration of agricultural information resources into a promising digital platform for the
use of GIS. In this situation, following a task-oriented approach, the potential number
of information systems in crop production that may appear in the absence of their
integration may be assessed. We think that about 150 topical tasks are to be solved in
crop production for 20 crops, about 20 different technological operations are per-
formed with each crop, and the number of regions is 80. Then, we can potentially get
4,800,000 information systems. From an analysis of the calculation results based on a
mathematical model of scenarios of possible options for informatization of the agri-
cultural industry, it becomes clear that with this approach, without abandoning task-
oriented technologies for designing digital systems for standard and automated design
with state support, the maximum possible level of the digital transformation of the
industry will not exceed 17%, according to our estimates.
Also, there are a significant number of other problems in the implementation of
PFT technologies. Thus, the supply of expensive and high-tech machinery and
equipment will have a delayed effect due to, on the one hand, its high cost and lack of
sufficient financial resources for most households; on the other hand, a significant
amount of existing equipment, but unsuitable, for the most part, PFT. PFT's contain-
ment is affected by the almost complete absence of domestic manufacture of commu-
nication devices, sensors, and actuators necessary to install on agricultural machinery
for automatic control of PFT technological processes. For example, a Yara N-Sensor
device [12], mounted on a tractor to measure the culture requirement for nitrogen
when the tractor is moving across the field and varying the dose of fertilizing on a
20x20 m plot, costs about 25,000 euros, and the MTZ 80.1 tractor is almost three
times cheaper—from 800,000 rubles. Manufacturers of Kirovets tractors without
smart electronics currently have big problems with the sale due to the huge price for
farms of about 7 million rubles. Due to the much more difficult to master PFT tech-
nologies compared to existing technologies in the country, there is a big drawback
and trained staff.
127
4 The Approach to Design a Digital PFT
The most advanced approach to the design of digital systems is currently considered
an architectural approach. This approach determines the overall structure and organi-
zation of life cycles and the life history of the "enterprise" [14, 15]. An enterprise here
is understood in a broad sense; for example, an enterprise may be a system for manag-
ing the industry, the economic sector, or the state. So, the user of this approach has
found its application in the federal authorities of the United States, the construction of
the electronic government of India, and so on.
The architectural approach began to take shape a long time ago. Back in the 60-80s
of the last century, CODASYL (COnference on DAta SYstems Language) made a
significant contribution abroad. We can recall the ANSI-SPARC 1975 standards. In
domestic practice, A.I. Kitov and V.M. Glushkov made a great scientific contribution
to solve this issue when creating a nationwide automated system to collect and pro-
cess information. The 100th anniversary of the former is celebrated this year [16]. In
Russia, the conceptual issues of designing a unified digital agricultural platform, in-
cluding the PFT sub-platform strategy creating (Fig. 1), were worked out due to the
optimal integration of information systems [17, 18]. So, an economic-mathematical
model was developed for the formation of a digital platform for economic manage-
ment, which allows calculating the optimal digital platform in agriculture.
Fig. 1. The upper-level of the architecture of the unified digital agricultural platform
128
A digital platform is a business model for providing the possibility of an algorith-
mized exchange of information and values between a huge number of market partici-
pants by conducting transactions in a single information environment, leading to low-
er costs due to digital technologies and changes in the division of labor. It includes a
collection of ordered digital data based on ontological modeling; mathematical algo-
rithms, methods and models of their processing, and software and hardware tools for
collecting, storing, processing, and transmitting data and knowledge optimally inte-
grated into a unified information management system designed to manage the target
subject area with the organization of rational digital interaction of stakeholders.
The model constructed by the authors made it possible to distinguish many digital
sub-platforms, one of which is a cloud service for collecting and storing operational
primary accounting information of all enterprises in the Unified Database of Primary
Information (UDPI) in the following form: type and object of operation, place of im-
plementation, subject of implementation, date and time interval conducting, means of
production involved, the volume and type of resource consumed. The second is also a
cloud service of a Unified Database of Technological Accounting of all enterprises
(UDTA). The ontological information model of crop production, based on them, is
common for all agricultural enterprises in Russia (a standard for information re-
sources) with 240 functional management tasks with a single description of algo-
rithms for most agricultural organizations (a standard for applications). Similar work
was done for all sectors of agricultural production and 19 types of processing enter-
prises.
Thus, a digital platform is simulated, integrating primary accounting information
and technology databases in a single cloud environment. It is formed based on a uni-
fied system for collecting, storing, and analyzing primary accounting, technological,
and statistical information, interfaced both with each other and with a unified system
of classifiers, reference books, standards, representing registers of almost all material,
intellectual and human resources of the agro-industrial complex.
The presented digital platform is acquiring special significance when remote sens-
ing and GIS technologies begin to be actively introduced in such a relatively young
agricultural production field as precision farming, which requires a combination of a
large amount of data and technologies. Fig. 2 presents the working schema of a prom-
ising digital sub-platform of PFT in agriculture, which uses the possibility of Unified
Geographically Distributed Information System of Earth Re-mote Sensing from space
(UGDIS ERS).
129
Fig. 2. The working schema of the digital sub-platform of PFT in agriculture
Consider the individual elements of this digital sub-platform PFT. All remote sensing
data are currently in the heterogeneous databases collected and stored in various
ground-based departmental complexes and centers. Data is often transmitted to cus-
tomers in the form of images, which need to be independently and labor-intensively
decrypted. The most effective way to get ready-made images for commodity produc-
ers would be forming a unified cloud GIS remote sensing with a special unified body
for their decryption in the industry with free transfer of ready-made solutions to users.
Now, there are hopes for this—UGDIS ERS is being created with the integration of
all remote sensing information into a unified geographic information space of the
country with an expiration date of 2025. The work is carried out following plans of
the development concept of the UGDIS ERS. Of course, it would be desirable to cre-
ate the same center for decrypting images both from drones that are gaining populari-
ty, as well as from stationary remote sensing masts, which would lead to a decrease in
the cost of introducing PFT and increasing the efficiency of using these devices.
Remote sensing information after decryption in the created centers should be col-
lected in a cloud GIS (CGIS), which also collects information on technological and
primary accounting, data on all material, intellectual and human resources of the in-
dustry. An example of this approach is the European Union Unified Administrative
Management System (UAMS), which receives and stores information about lands and
their users. Further, information obtained from sources other than those indicated
above and from gadgets, ground-based sensors, and sensors installed on agricultural
machinery are collected in a CGIS. At the same time, part of it is transmitted directly
130
to communication equipment back to the equipment. Thus, the CGIS will collect all
data on all employees' technological and accounting operations at each site throughout
the year. It will be possible to track all movements of products, materials, and any
equipment.
As noted in Section 1, the improvement of PFT based on GIS and remote sensing
will allow the formation of a cloud service for all participants in the value chain,
which dramatically increases their activities' efficiency. Based on the results of calcu-
lations with the economic and mathematical model for the formation of the digital
platform of the agro-industrial complex in the form of the unified database of primary
accounting and the unified database of technological accounting, it can be obtained by
integrating them the Unified space for digital interaction (USDI) of logistics activity
(Fig. 3). The implementation of this scheme is based on a mathematical model for
optimizing all participants' logistics activities in the supply chain.
Fig. 3. Unified space for digital interaction
The digital platform, based on PFT, GIS, and remote sensing technologies, will
create the operational management system. It will be a tool for economic analysis
based on mathematical modeling, artificial intelligence, internet of thing, predictive
logic, and big data in various sections at any level of management from the site to the
federal center.
Since remote sensing and GIS technologies began to be actively applied in many
other sectors of the economy besides agriculture, such as cartography, ecology, forest-
ry, land management, geology, logistics, construction, oil and gas transportation sys-
tems, weather and climate, oceanology, etc. they will gradually acquire the status of
infrastructure technologies [19]. In this case, with their competent integration, these
technologies will soon have to play in the digital economy the same key role that
electric networks, railway infrastructure, telegraph and telephone communications,
etc. played in due time.
131
5 Conclusions
It has long been known that any innovation requires the fulfillment of three condi-
tions: a “social order” must be formed, an appropriate technical level must be
achieved for translating the innovation into practice, and the threshold of the socio-
educational level of potential performers and consumers of innovation must be ex-
ceeded. Since these conditions are not fully ensured in Russia, the solution seems to
be to use a proven approach, including the development of the most advanced remote
sensing technologies at several reference objects of different levels of management
(from the enterprise to the region), the supply of modern software and hardware for
remote sensing in combination with a variety of technological equipment and ma-
chines involved in the production process of industries, the mass introduction across
the country.
The consistent implementation of the promising PFT digital sub-platform based on
reference objects will create the conditions for turning it into a set of scientifically-
based infrastructure technologies for the entire agricultural sector. This integrated
approach will significantly reduce the costs of implementing PFT, remote sensing,
and GIS technologies with a significant increase in the efficiency of their use.
References
1. Kannan, B., Rajasekar, M., Jayalakshmi, K., Thiyagarajan, G., Selvakumar, S., and Rajen-
dran V. (eds): Protected cultivation and precision farming technologies, TNAU, India, 297
p. (2019).
2. Medennikov, V.I.: Ot konzepzii k praktitscheckoj realisazii edinoj zivrowoj platvormy ag-
ropromyschlennogo komplekca (From concept to practical implementation of a single
digital platform for the agro-industrial complex). Mezhdunarodnyj cel'cko-chosjajctwennyj
zhurnal, № 5(377), 77-81 (2020), https://doi.org/10.24411/2587-6740-2020-15099.
3. Medennikov V.I.: Zivrowaja platvorma uprawlenija cel'ckim chosjajctwom (Digital Agri-
culture Management Platform). Cbornik III nazional'noj (wceroccijckoj) nautschnoj kon-
verenzii c mezhdunarodnym utschactiem «Teorija i praktika cowremennoj agrarnoj
nauki». Nowocibirck, IZ NGAU «Solotoj koloc», 846-851 (2020).
4. Vecchio, Y., De Rosa, M., Adinolfi, F., Bartoli, L., Masi, M.: Adoption of precision farm-
ing tools: A context-related analysis, Land Use Policy, vol. 94, 104481 (2020),
https://doi.org/10.1016/j.landusepol.2020.104481.
5. Lowenberg-De Boer, J., Erickson, B.: Setting the record straight on precision agriculture
adoption. Agron. J. 111(4), 1552–1569 (2019), https://doi.org/10.2134/
agronj2018.12.0779.
6. Kling-Eveillarda, F., Allain, C., Boivin, X., Courboulay, V., Créach, P., Philibertf, A.,
Ramonet, Y., Hostiouh, N.: Farmers’ representations of the effects of precision livestock
farming on human-animal relationships, Livestock Science, vol. 238, 104057 (2020),
https://doi.org/10.1016/j.livsci.2020.104057.
7. Neethirajan, S.: The role of sensors, big data and machine learning in modern animal farm-
ing, Sensing and Bio-Sensing Research, vol. 29, 100367 (2020),
https://doi.org/10.1016/j.sbsr.2020.100367
132
8. Lovrak, A., Pukšec, T., Duić, N.: A Geographical Information System (GIS) based ap-
proach for assessing the spatial distribution and seasonal variation of biogas production
potential from agricultural residues and municipal bio waste, Applied Energy, vol. 267,
115010 (2020), https://doi.org/10.1016/j.apenergy.2020.115010.
9. Bragagnolo, L., Silva, R.V., Grzybowski, J.M.V.: Landslide susceptibility mapping with r.
landslide: A free open-source GIS-integrated tool based on Artificial Neural Networks.
Environmental Modelling & Software, vol. 123, 104565 (2020),
https://doi.org/10.1016/j.envsoft.2019.104565
10. Analysis of the market of cloud IoT platforms and applications for digital agriculture in the
world and prospects in Russia. J'son & Partners Consulting. URL:
https://json.tv/en/ict_telecom_analytics_view/analysis-of-the-market-of-cloud-iot-
platforms-and-applications-for-digital-agriculture-in-the-world-and-prospects-in-russia
(2018), last accessed 2020/05/04.
11. Kulba, V., Medennikov, V., Butrova, Е.: Methodical approaches to agricultural risk esti-
mate in forecasting the economic effect of applying data of the Earth’s remote sensing.
IEEE Xplore Digital Library. 12th International Conference "Management of large-scale
system development" (MLSD). Moscow, Russia (2019),
https://doi.org/10.1109/mlsd.2019.8911084
12. Atfarm. URL: www.at.farm. last accessed 2020/05/04.
13. Ereshko, F.I., Medennikov, V.I., Muratova, L.G.: Modeling of a digital platform in agri-
culture. IEEE Xplore Digital Library. 11th International Conference Management of
Large-Scale System Development (MLSD), Moscow, Russia (2018),
https://doi.org/10.1109/MLSD.2018.8551894.
14. The TOGAF Standard, Version 9.2 Overview: URL: https://www.opengroup.org/togaf,
last accessed 2020/05/04.
15. ArchiMate 3.1 Specification, a Standard of The Open Group: URL:
https://pubs.opengroup.org/architecture/archimate3-doc/, last accessed 2020/05/04.
16. Peters, B.: How not to network a nation: The Uneasy History of the Soviet Internet. The
MIT Press, 313 p. (2016).
17. Ereshko, F.I., Kulba, V.V., Medennikov, V.I.: Digital platforms clastering model // 12th
International Conference Management of Large-Scale System Development (MLSD),
Moscow, Russia (2019), https://doi.org/10.1109/MLSD.2019.8911012.
18. Raikov, A., Abrosimov, V.: Import countries ranking with econometric and artificial intel-
ligence methods. 3d International Conference Digital Transformation and Global Society,
DTGS, St. Petersburg, Russia, Revised Selected Papers, Part I. 402-414 (2018),
https://doi.org/10.1007/978-3-030-02843-5_32
19. David, P.A.: The dynamo and the computer: an historical perspective on the modern
productivity paradox, The American Economic Review, American Economic Association,
80(2):355-361 (1990).
133