ArticlePDF Available

Digital revolution and Big Data: A new revolution in agriculture

Abstract and Figures

This review considers the role of Big Data (BD), the digital revolution, the application of Internet of Things (IoTs) and sensor technologies in the agriculture sector. The introduction is focussed on the ongoing research efforts on BD within agriculture sector, basic features of BD and latest development in BD analytics tools. In subsequent sections, the importance of BD applications in the agriculture sector and examples of their success stories in increasing farm productivity, current scenario on BD and digital agriculture, the future prospects of BD and bottlenecks in its implementation in agriculture sector are discussed. Agriculture sector is undergoing a new revolution and transformation, driven by IoT, sensor technologies, BD and cloud computing. This digital revolution in agriculture is very promising and will enable the agriculture sector to move to the next level of farm productivity and profitability. This transformation process looks irreversible and poised to revolutionize not only agriculture but the entire farm-to-food sector.
Content may be subject to copyright.
Digital revolution and Big Data: a new revolution in agriculture
S. Himesh, E.V.S. Prakasa Rao, K.C. Gouda, K.V. Ramesh, V. Rakesh, G.N. Mohapatra, B. Kantha Rao,
S.K. Sahoo and P. Ajilesh
Address: CSIR Fourth Paradigm Institute, Bangalore 560037, India.
*Correspondence: S. Himesh. Email: himesh@csir4pi.in
Received: 19 September 2017
Accepted: 22 June 2018
doi: 10.1079/PAVSNNR201813021
The electronic version of this article is the definitive one. It is located here: http://www.cabi.org/cabreviews
© CAB International 2016 (Online ISSN 1749-8848)
Abstract
This review considers the role of Big Data (BD), the digital revolution, the application of Internet
of Things (IoTs) and sensor technologies in the agriculture sector. The introduction is focussed
on the ongoing research efforts on BD within agriculture sector, basic features of BD and latest
development in BD analytics tools. In subsequent sections, the importance of BD applications in
the agriculture sector and examples of their success stories in increasing farm productivity,
current scenario on BD and digital agriculture, the future prospects of BD and bottlenecks in its
implementation in agriculture sector are discussed. Agriculture sector is undergoing a new
revolution and transformation, driven by IoT, sensor technologies, BD and cloud computing. This
digital revolution in agriculture is very promising and will enable the agriculture sector to move to
the next level of farm productivity and profitability. This transformation process looks irreversible
and poised to revolutionize not only agriculture but the entire farm-to-food sector.
Keywords: Agriculture, Big Data, Weather, Digital agriculture, Data analytics, IoT
Review Methodology: This article is not about in-depth review of either Big Data or Digital Revolution, rather focused on the application
of these tools in enhancing the overall productivity of agriculture sector. This Review also highlighted on how; Big Data and digital
revolution complementing each other in driving a new revolution in agriculture, which is a paradigm shift. This article also looked at how
digital revolution and IoT are driving research and application on Big Data in Agriculture sector. Except some original conceptual
contribution, most of the review materials are sourced from online resources; Journals, abstracts, conference papers, technical and
scientific reports, webpages of leading organization working in related areas.
Introduction
Ongoing research efforts
Traditional skill-based agriculture is rapidly transforming
into digital and knowledge-driven agriculture with Big Data
(BD) playing a critical role in enhancing farm productivity.
BD in agriculture is being generated rapidly with the advent
of GPS and sensor technologies combined with Internet
of Things (IoTs). GPS-enabled farm equipment fitted with
sensors are generating diverse (soil, crop, weather, etc.)
on-field data, which can be transferred to centralized
servers in real time. Digital information on soil, weather,
climate, crop, etc., is fundamental to digital agriculture and
predictive data analytics. The explosive growth of IoTs and
mobile data penetration are further fuelling the
transformation of traditional agriculture into digital agri-
culture. Some companies are now developing optimum
crop planning prescription based on historical agriculture
data (crop yield, weather, soil, seed and fertilizer) to
enhance farm productivity and profitability. Valuable
Decision Support System (DSS) tools can be developed
using data analytics and IoT to enhance farm productivity.
The DSS tools developed based on objective information
helps precision farming that reduces input cost and
maximize benefits (Research Report 2016, Australian
Farm Institute).
According to Bronson and Knezevic [1], Farming is
undergoing Digital Revolution. New information and
communication technologies (ICT) and IoT innovations
are taking place at rapid pace in the collection, communi-
cation, archival, analyses of data and decision-making
CAB Reviews 2018 13, No. 021
http://www.cabi.org/cabreviews
in agriculture-food sector. Tractors are now fitted with
sensors to collect farm-level data (crop and soil data). The
data can be accessed by farmers to make informed decision
(crop choice, irrigation, etc.). The Integrated Field System,
for example, is designed for on-site data collection (soil,
weed and weather) and help farmers to make risk-free
or low-risk decisions. The Agro-climate Impact Reporter
(AIR) developed by National Agriculture Information
Services (NAIS) of Canada provides climate and weather
data on a range of scales: local, regional and national. Food
companies use analytics to understand consumer pre-
ference for food which in turn influence farm activities,
such as the Heartbeat tool developed by Sysmos.
BD and IoT are set to revolutionize farming practices
and operations of agro-food sector. The BD has now
been used in the agriculture sector in a big way, covering
the entire lifecycle of agriculture and related practices,
including post-harvest processing to food processing, and
its marketing. BD with appropriate analytics can be used
for target intervention to achieve farm productivity and
its sustainability in the face of climate change and market
vulnerabilities. BD utilities have been used by scientists
at International Centre for Tropical Agriculture (CIAT)
to devise customized farming strategies under changing
climate for small-scale farmers (https://ccafs.cgiar.org).
Applied BD analytics was used to investigate the role of
climate variability on rice yields; to unearth reason for
shrinking rice yield, identification of productive varieties
and ideal planting time for specific sites in Colombia. These
targeted intervention are expected to increase rice yield by
13 tons per hectare. Similar data analytics can be used
elsewhere to address similar problems, provided, relevant
data are available (historical climate and crop-yield data,
farming practices, etc.). BD will be the key to dynamic and
successful management of agriculture-food sector in sus-
tainable manner under adverse impacts of changing climate
and its extremes. Scientists at CIAT are promoting revol-
ution in data-driven agronomy in a big way. Their efforts
won a UN Global Pulses Big Data Climate Challenge award
(https://ccafs.cgiar.org/bigdata#.WifOAYVOLvU).
BD applications can go long way in addressing global
issues such as food security, sustainability, farm productivity
and profit. The scope of BD applications extend far beyond
farming and covers the entire supply chain. The develop-
ment of IoTs, wireless connection of objects and devices in
farming and the supply chain produce many new data sets
that are accessible in real time. BD is set to cause major
changes in scope and operations of Smart Farming (SF).
Business analytics at a scale and speed that was never seen
before is now becoming a real game changer and con-
tinuously reinventing new business models [2].
The whole cycle of farm-to-food operations and
research is interdisciplinary in nature cutting across boun-
daries of different scientists: agronomists, geneticists
environmental engineers, meteorologists, climate and eco-
nomic. BD and IoT together opened up new possibilities
for agriculture and food industry [3]. However, not much
emphasis was given to this emerging field in developing
countries, owing to many bottlenecks such as limited
Internet penetration [4], bandwidth, etc. However, the
rapid penetration of mobile phones and mobile-broadband
connections are now opening up new opportunities for
data-driven smart agriculture in developing countries
too [5].
The BD-driven applications in the developed world
are primarily focused on enhancing the productivity and
efficiency of large-scale commercial agriculture, while in
developing countries, these have been largely focused
around systemic problems such as agri-market and supply-
chain management. Unlike in the developed countries,
where BD-driven agriculture activities are driven by private
players, publicprivate and NGOs are major players in
developing countries [6]. According to FAO (World
Agriculture), by 2100, climate change could endanger
global and local food security (http://www.fao.org/3/
a-y4252e.pdf). BD analytics can play an important role in
understanding and mitigating those climate-related risks.
Basic features of BD
Existing and emerging data analytics and IoT technologies
offer immense potential for BD application in farm-to-food
sector. BD in general is characterized by three main fea-
tures or dimensions: volume,velocity and variety. The volume
dimension of BD is not necessarily about size, as the size of
data is growing rapidly with IoT and sensors, and qualifying
size of BD is also increasing. The volume dimension of BD is
rather described subjectively as those data sets whose size
is beyond the ability of conventional database tools to
process them. Also, the concept of BD is not same across
sectors. The size of BD can vary from multiple of terabytes
to multiple of petabytes. The velocity dimension refers
to the capability to acquire, process, understand and
interpret data in real time, basically the speed of data
processing. The variety dimension is novel and intriguing [7],
but in simple terms it refers to number of data types
(image, text, numbers, etc.). Big corporate farms use
sophisticated unmanned aerial vehicles fitted with sensors
to collect variety of agricultural data (growth, weed,
disease). Individual and marginal farmers, however, can
collect useful data using devices like tablets and smart
phones, moisture sensors and so on.
Some tools of BD analytics
Data analytics is aimed at deriving knowledge and wisdom
from data, a bottom-up processes as shown in Figure 1.
BD analytics refers to the processes of collecting, organiz-
ing, curing, analysing and modelling to discover patterns and
trends. There are many industry-standard BD analytics
tools: Hadoop, MapReduce, HDFS, HIVE, HBase. Hadoop is
an open-source multi-task software for data storage and
2 CAB Reviews
http://www.cabi.org/cabreviews
running analytics. MapReduce is a programming model for
BD processing with parallel and distributed algorithm on
cluster. HDFS is a Java-based file system which is modular,
scalable and reliable. This can store up to 200PB of data on
a single cluster of 4500 servers, handling close to billion files
and blocks. The HIVE too is capable of analysing large data
sets stored in Hadoops HDFS. The HBase is a distributed
database designed to handle large tables with billions of
rows and millions of columns, and can provide real-time
read-write access to BD [8]. Agricultural landscape rightly
fits BD landscape in terms of volume (350 million farm
acres in the USA alone!), velocity (tractors alone are now
recording 100 s of data points at 5 Hz on every operation),
variety (crop types, soil-health data, weather, disease, data
formats).
Importance of BD in Agriculture
BD proponents promise a level of precision, information
storage, processing and analysis that were previously
impossible due to technological limitations [9]. The
adoption of ICT, mobile-broadband connection, in particu-
lar, is growing at a remarkably rapid rate in developing
countries. The combination of the above factors provide
unprecedented opportunity for BD application in develop-
ing countries. The increased availability of high-resolution
environmental, climate and economic data, coupled with
the availability of affordable computing power, has triggered
enormous interest in the potential uses of BD on a large
scale in many fields such as agricultural economics, climate
change and agricultural policy research. The computational
tools and data necessary to tackle many outstanding
new problems in agriculture sector are now becoming
more readily available, and this has the potential to unlock
access to an incredible set of possibilities in the field of
agriculture, from productivity to risk management [10].
Agriculture is an important sector for the economies of
many developing countries such as India, which employs a
large proportion (<50%) of workforce. Improved infor-
mation on weather and climate could make the sector more
productive. Rain-fed farming remains a risky business as
80% of the variability in agricultural production is the result
of the variability in rainfall. In many developing countries
where rain-fed agriculture is the norm, a good rainy season
means good crop production, enhanced food security and a
healthy economy. Failure of rains and occurrence of natural
disasters such as floods and droughts could lead to crop
failures, food insecurity, famine, loss of life. Climate
variability and the severe weather events are responsible
for agricultural disasters. BD analytics can complement
conventional weather forecasts and climate projections in
reducing the risk to the farming community in a big way.
Sensing huge opportunities, many big tech companies
(Google, IBM) and start-ups are taking a lot of interest and
are investing in a big way to harness the power of BD in
agriculture and allied sectors [2]. The emerging landscape
of BD and agriculture companies is shown in Figure 2.
Agriculture companies such as Monsanto and John Deere
made huge investments in developing tools based on BD
(soil, weather and seed) to help farmers to increase their
yield and profitability. Monsanto, in particular, is emerging
as a big leader in this space by working on BD analytics
across the chain of its agri-business, from climate projec-
tion, customized field scripts to genetic engineering.
Digital Agriculture and BD: Current Scenario
The use of ICT and BD in SF is still in an early development
stage. SF is leveraged on ICT and BD and can be visualized
as cyber-physical farm management cycle including post-
harvest and food-supply chain operations. SF is a system that
emphasizes the use of ICT in the cyber-physical farm
management cycle. New technologies such as the IoT and
cloud computing are expected to leverage this system
and introduce more robots and artificial intelligence in
farming. Digital agriculture is driven by the phenomenon of
BD wherein massive volumes of data with a wide variety
can be captured, analysed and used for decision-making.
With the advent of smart sensors, IoT, cloud computing
and real-time data generation, traditional farming is set
to transform into a modern data-driven and data-enabled
SF [11].
Unlike precision agriculture, which is just taking
on-field variability into account, SF goes beyond by
including the whole cycle of farm-to-food, enhanced by
context and situation awareness, triggered by real-time
events. The conceptual cyber-physical system for SF is
shown in Figure 3. The entire system is driven by IoT, smart
devises and sensors. SF driven by BD analytics holds the key
to sustainable agriculture and food security [12].
The IoTs fuel the next level of intensive, high-yield,
high-quality, efficient and ecologically sustainable agricul-
ture. The Facility Agriculture based on IoT technologies is
new and an emerging trend in modern data-driven SF. The
Facility Agriculturetypically consists of perception layer
(data-aware acquisition), transport layer (data transmission)
Figure 1 Data to wisdom (https://en.wikipedia.org/wiki/
DIKW_pyramid).
S. Himesh et al.3
http://www.cabi.org/cabreviews
and application layer. The application layer is mainly
responsible for data analysis, early warning, automatic
control and scientific decision-making. The Facility
Agriculture consists of RFIDS, sensors (light, temperature,
humidity, pressure, CO
2
, plant growth), wireless data
transmission with GPRS, intelligent information processing
and cloud computing. A typical Facility Agriculture [13] is
shown in Figure 4.
Some tools of digital agriculture
Advent of IT, IoT, sensors and cloud computing are fuelling
the development of new generation of smart devises that
can help: smart management of agricultural practices,
generate real-time on-field data, increase farm productivity
and profitability. Few such digital tools are discussed
below. The e-Kisaan tablets are loaded with information
on IT-enabled agriculture, education and health, and
have been distributed to farmers in southern province
(Karnataka) of India. The tablet works as a catalyst to
share best practices among farmers and facilitate higher
level of interaction. The tool provides an array of infor-
mation on weather, food processing, fertilizers, pesticides,
seeds, crop combinations, etc. Apart from agriculture-
related contents, the tablet also provides other information
such as education, e-governance, rainwater harvesting and
basic healthcare. The farmers can interact through dedi-
cated call centre created for the purpose. The Android
version of the tool is under development. (http://www.
thehindu.com/news/national/karnataka/farmers-get-ekisaan-
tablets/article6819570.ece) http://indianexpress.com/article/
cities/bangalore/indias-first-e-kisaan-tablet-for-farmers-
launched/
The Plantix is the pest and disease management tool.
This modern digital tool allows farmers to identify pests
and diseases using their mobile phones and provides
remedial measures. A key feature of the mobile App
Plantixis an automated disease diagnosis. Farmers can
upload a photo of their infected crop and the App will
provide a diagnosis. Besides giving a diagnosis and steps
Figure 2 Different stake holders of Big Data in agriculture and its allied sectors (source: [2]).
Figure 3 The cyber-physical management cycle of Smart
Farming enhanced by cloud-based event and data manage-
ment (source: [12]). In such a system, intelligent decision
can be made by combining on-site field data and weather
data to minimize the risk to farmers.
4 CAB Reviews
http://www.cabi.org/cabreviews
to mitigate the disease, the App also provides information
on preventing the disease in the next cropping season.
Farmers are also presented biological treatment options
for pest and disease control. Given the overuse of chemical
pesticides in India, the App also helps disseminate best
practice methods to reduce pesticides. The App also
features a library of diseases which farmers can refer to
in case there is no connectivity. Currently, the database
has over 60,000 photographs and covers 30 crops in India,
60 crops worldwide and has prescriptions for over
200 crop diseases. Every time a farmer uploads a
photograph for diagnosis, it will be time-marked and
georeferenced. Hence, the database also facilitates pest
and disease outbreak monitoring, and can send early-
warning messages for specific locations. The App can be
downloaded on any Android-based mobile device. To
overcome connectivity issues, photographs can be taken
and later uploaded when Internet connectivity is available.
This is part of a pilot project being implemented in the
southern province of India (Telangana). Details can be
referred at: http://www.icrisat.org/mobile-app-for-pest-
and-disease-management-of.
Figure 4 The Facility Agriculture-based on IoT technologies [13].
S. Himesh et al.5
http://www.cabi.org/cabreviews
The AgDNA (http://agdna.com) is one of the most
popular cloud-web-platform-based application designed
to empower farmers to maximize their profit. This tool
is designed to help farmers across the gamut of their
activities, from soil-to-silo: farm planning, inventory man-
agement, agronomic insights, equipment optimization,
financial records and e-market. Again, this will enable
data-driven SF based on IoT. The AgDNA is revolutionizing
the future of farming by helping farmers maximize their
profit and productivity. It is an enterprise-level precision
farming platform that combines data science and the IoT
to help farming community to reduce input costs and
maximize farm productivity and profitability. AgDNA is
considered as one of the worlds most intelligent farming
platforms.
The Monsanto field scripts can be used for spatially
variable application of water, fertilizer and seeding, etc. This
field script can be iteratively improved through feedback
information from farmers. In general, at least 5 years of data
(yield, fertilizer, seed) are required to develop predictive
analytical tools (Research Report, 2016, Australian Farm
Institute). http://www.crdc.com.au/sites/default/files/pdf/
Big_Data_Report_web.pdf.
The IntelliSense IoT will be an important tool for efficient
and ecologically sustainable agriculture. It has an important
significance in raising the level of agricultural development,
improving the overall efficiency of agriculture and its
transformation [13].
Future of BD in Agriculture and Bottlenecks
The BD is tipped to be the fourth revolution in agriculture.
According to the CEO of AgDNA, the agriculture sector is
poised to witness massive disruption fuelled by BD (www.
linkedin.com/pulse/data/fourth-revolution-agriculture-paul-
turne). Advent of GPS and georeferenced site-specific data
laid the foundation for digital transformation of agriculture
as early as 1980, when the University of Minnesota used
soil sample data to vary lime application. Many AgTech
companies like AgDNA are developing powerful analytical
tools and software to make sense of data and help farming
community to make informed decision with reduced risk.
Future of farm-to-food processes; crop-planning, irrigation,
fertilizer application, disease control, harvesting and
post-harvest processing, transport, food supply chain to
end-user, will be driven by data analytics. Combination
of technologies and tools, simulation, modelling, BD,
Remote Sensing data, Geographical Information System
(GIS), Automatic Weather Stations (AWS) and IoTs, can be
used to develop integrated agriculture management
and DSS as shown in Figure 5. In countries like India,
agriculture is an important component of economy with
15% of GDP and 50% of employment. However, with
only 3060% yield, there is a huge potential to improve
the performance and productivity of Indian agricultural
sector [14].
In developing countries, fragmented pattern of land
holding (25 acres) by marginal farmers, restricted access
to resources and markets faced by them are often cited as
main barriers for adopting new technologies and develop-
ing new capabilities that are necessary for the successful
implementation of BD-based solutions [15]. Relatively,
limited attention is given to the potential of BD-based
solutions in the agri-food value chains in developing
economies [4]. There are still many concerns on data
security, data ownership, and quality of data.
Summary
The agriculture sector is undergoing a new revolution
driven by BD, IoT, cloud and sensor technologies. Benefits
of green revolution seem to have reached their limits.
There are evidence of declining productivity in many parts
of the world, especially in developing countries, with
abysmally low yield 3060%. As evident in the literature,
the developed world is harnessing the power of IoT and BD
to transform traditional skill-based agriculture into
knowledge-based and technology-driven digital agriculture
akin to state-of-the art industrial sector, covering entire
cycle of farm sector, farm-to-food. New generation of
GPS-enabled and sensors-fitted farm equipment, e-tablets,
Android-based tools capable of measuring and monitoring
crop and soil health are all contributing to the growth of
digital agriculture and precision farming. Companies like
Monsanto are already capable of providing end products of
BD analytics such as plot-specific field prescription to
farmers to increase their productivity and profitability. In
developed countries, digital agriculture revolution is mainly
driven by private players, whereas in developing countries,
these are mainly government and initiatives from NGOs.
There are some major bottlenecks in developing world to
fully exploit digital agriculture driven by BD: digital literacy,
Internet access and its speed, small land holding pattern,
lack of participation from private corporate and industries.
Figure 5 Conceptual diagram of agriculture management
and decision support system.
6 CAB Reviews
http://www.cabi.org/cabreviews
One thing is certain, digital revolution in agriculture,
driven by BD, is set in motion which is irreversible, and
farm-to-food sector is witnessing a paradigm shift.
Acknowledgements
I thankfully acknowledge the support of Head CSIR Fourth
Paradigm Institute, Bangalore, and all my Co-authors. I also
thank editors and reviewers for their insightful comments
and suggestion. This work received no financial support
from any organization or individuals.
References
1. Bronson K, Knezevic I. Big Data in food and agriculture. Big
Data & Society 2016;3(1):15: DOI: 10.1177/
2053951716648174.
2. Wolfert S, Ge L, Verdouw C, Boggardt M-J. Big Data
in Smart Farming a review. Agricultural Systems
2017;153:6980.
3. Woodard JD. Data science and management for large scale
empirical applications in agricultural and applied economics
research. Applied Economic Perspectives and Policy
2016;38(3):37388.
4. Kshetri N. The emerging role of Big Data in key development
issues: opportunities, challenges, and concerns. Big Data
and Society 2014;1(2):120. DOI: 10.1177/
2053951714564227.
5. Salami A, Kamara AB, Brixiova Z. Smallholder Agriculture in
East Africa: Trends, Constraints, and Opportunities. Working
Paper Series 2010 #105. African Development Bank. Available
from: URL: http:/www.afdb.org/ (last accessed 5 July 2015).
6. Protopop L, Shanoyan A. Big Data and smallholder farmers: Big
Data applications in the agri-food supply chain in developing
countries. International Food and Agribusiness Management
Review 2016:19.A:17390.
7. Steve S. Big Data and the Ag sector: more than lots of numbers.
International Food and Agribusiness Management Review
2014;17(1):120.
8. Surya P, Laurence P, Ashok K. The role of Big Data analytics in
agriculture sector. International Journal Advanced Research in
Biology, Engineering, Science and Technology (IJARBEST)
2016;10(2):8308.
9. Datafloq (2015) John Deere is revolutionizing farming with
Big Data. Available from: URL: https://datafloq.com/read/
johndeere-revolutionizing-farming-big-data/511 (last accessed
15 July 2015 ). Available from: URL: https:// datafloq.com/read/
john-deere-revolutionizing-farming-big-data/511.
10. Woodard JD. Big Data and Ag-Analytics: an open source, open
data platform for agricultural and environmental finance,
insurance, and risk. Agricultural Finance Review
2016;76(1):1526. https://doi.org/10.1108/AFR-03-2016-0018.
11. Sundmaeker H, Verdouw C, Wolfert S, Pérez Freire L.
Internet of food and farm 2020. In Vermesan O, Friess P, editors.
Digitising the Industry Internet of Things Connecting Physical,
Digital and Virtual Worlds. River Publishers, Gistrup/Delft; 2016.
pp. 12951.
12. Wolfert J, Sørensen CG, Goense D. A Future Internet
Collaboration Platform for Safe and Healthy Food from Farm
to Fork, Global Conference (SRII), 2014 Annual SRII. IEEE,
San Jose, CA, USA, pp. 26673.
13. Zhou L, Song L, Xie C, Zhang J. Applications of Internet of
Things in the facility agriculture. 6th Computer and Computing
Technologies in Agriculture (CCTA) 2012;6:297303.
DOI:10.1007/978-3-642-36124-1_36.
14. Yadav R, Rathod J, Nair V. Big Data meets small sensors in
precision agriculture. International Journal of Computer
Applications (0975 8887), Applications of Computers and
Electronics for the Welfare of Rural Masses (ACEWRM)
2015;14.
15. Jack BK. Constraints on the Adoption of Agricultural
Technologies in Developing Countries. White paper, Agricultural
Technology Adoption Initiative 2011: J-PAL (MIT) and CEGA
(UC Berkeley):255.
S. Himesh et al.7
http://www.cabi.org/cabreviews
... It is pertinent to note that researchers study a group of digital infrastructures that share the same features. See for example: virtual or cloud computing (Gill et al., 2017;Molin et al., 2021), global positioning system (GPS), geographic information system (GIS) and Unmanned Aerial Vehicle (UAV) (Himesh et al., 2018;Lajoie-O'Malley et al., 2020;Potgieter et al., 2021). ...
... By employing digital technology such as GIS, remote sensing and digital camera, farmers will be able to enhance food production by determining the features and texture of soil for planting as well as observing urban encroachment that may hinder soil fertility. In similar fashion, (Gill et al., 2017;Himesh et al., 2018) develop a model to delivery of service quality for agriculture business using the IoT, sensor technologies and big data analytical system with information store in the cloud-a cloud based automatic information system. Small (2017) noted that the emergence of digital technologies has revolutionized agribusiness sector by providing efficient service through computer-based technologies, and this will impact positively on the agribusiness value chain, most importantly to rural enterprises and SMEs. ...
... The analysis of Digital Agriculture (DA) articles reviewed for this study revealed that 42% (22 articles) discusses the precision agriculture as model of agribusiness to improve productivity, efficiency, increase food sustainability and reduce world hunger (Carolan, 2020). Digital technologies are tools adopted by enterprises to help in precise management of agribusiness information in order to reduce cost of production and maximize benefits (Cook et al., 2021;Himesh et al., 2018;KP, 2019;Ravis & Notkin, 2020). Klerkx et al. (2019) reviewed literatures on digital technologiessuch as Iot, big data, sensors, robotic, artificial intelligence (AI) employed in precision farming or precision agriculture as regard food productivity, food systems and its value chain. ...
Article
Full-text available
Purpose: Digital agriculture has been noted to have far reaching prospects in the transformation of agribusiness. Digital technologies are been applied to improve food production, processing, security and packaging. As most of the least developed and developing economies are strategizing to reduce poverty and hunger, digital agriculture presents opportunities to reverse the trends. Thus, this paper presents a systematic literature review with aim to collect all related research and identify gaps in digital agriculture, as well as to understand the benefits of digital technology in agriculture in other to chart new proposition for future studies. Design/methodology/approach: A systematic literature review was carried, and we have extracted 67 journals published within the last two decades (2002-2022). Findings: Findings suggests that digital agriculture is important drivers of food sustainability, with improve production yield and increase household income. Also, 42% of the studies on digital agriculture are dominated by precision agriculture model. This SLR recognizes knowledge gaps in relation to the context, theory and content for future research. Originality/value: This paper is original Paper type: a Research Paper
... Traditional skill-based agriculture is undergoing a major transformation into digital and knowledge-driven agriculture and Big Data is playing a crucial role in enhancing farm productivity with optimal use of resources as well as expenditure (Himesh et al., 2018). Big Data in agriculture is being generated rapidly with GPS-enabled farm equipment that is fitted with sensors that are generating diverse (soil, crop, weather, etc.) on-field data, which then further can be shared to centralized servers in real-time (Paul et al., 2019a). ...
Article
Smart sensors are useful in professional farming approach by which one can use the digital technology to monitor, visualize, generate digital data, to control the application of resources, to improve quality and productivity of agriculture produce. Novel sensors add value in soil-less farming through automation and IoT (Internet of Things) based operation management digital tools. Data-driven technologies by using smart sensors can find a solution to many glitches in agriculture practices and it could improve new efficiencies. The principles of smart sensors as well as the most viable sensors that are used for monitoring soil and plant physicochemical parameters in field cultivation processes, greenhouse and indoor hydroponics are being discussed. Digital technologies in precision farming, automation in agro machinery, Precision Livestock Farming (PLF), TV White Spaces (TVWS) remote connectivity, Unmanned Aerial Vehicles (UAVs) based imagery, application of IoTs can help farming communities to use resources accurately based on real-time farm data acquired and improve crop yield without any wastage. Smart sensors helps the entire food value chain, the precision to productivity quest of growers and could enable new business models. This article provides a wide understanding of novel smart sensors, wireless sensor network architectures, and applications of these sensors to inculcate sustainable farming practices, value chain traceability and create secured income.
... Novel technologies have transformed the agriculture division, permitting it to undergo a revolution which favorably enabled the sector to experience a whole new increase in productivity and profitability [2]. The first and second waves of the modern agriculture revolution were mechanization and the green revolution, undergoing genetic modification. ...
Article
Full-text available
The use of Artificial Intelligence (AI) in agriculture has recently gained prominence. The fundamental notion of AI in agriculture is flexibility, high performance, accuracy, and cost prosperity. This article investigates the use of artificial intelligence (AI) to diagnose and control plant diseases. The application's benefits and limitations and the approach for utilizing expert systems for enhanced productivity are all highlighted. Present study overview the several application of AI,i.e, Neural Networks, Support Vector Machines, Hyper-spectral imaging, Alex net, Explanation block, and Fuzzy logic. These approaches have accuracy, pace, and affordability for sustainable safe food production.
Article
Smart farming is a trend in agriculture that involves incorporating information and communication technologies (ICT) into the production process. The study aims to get the factors that contribute to the current exposure to smart farming implementation on farmers from farmers’ perspectives in Alor Setar, Kedah, Malaysia. The study includes the determination of correlation between factors and exposure implementation of smart farming. About 116 farmers have been selected from the population to conduct the questionnaire. The results were obtained by analysing using Statistical Package for the Social Science (SPSS) software. It has been found that personal factors contribute the most to the exposure of smart farming implementation. A significant correlation between personal and environmental factors also has been discovered. Contrary, the security factors have no significant correlation with the exposure of smart farming implementation. Overall, the findings indicated that the implementation of smart farming exposure among farmers is emerging progressively.
Article
Full-text available
Agri-food supply chains (AFSCs) are one of the significant building blocks of agricultural production, and their sustainability aims are advanced by big data analytics (BDA) and the circular economy (CE). As access to safe, healthy, and high-quality food has become increasingly difficult, AFSCs need to leverage their capabilities for CE-based BDA to overcome sustainability challenges. However, a significant gap exists in the relevant literature on how to identify such capabilities to achieve sustainability goals. To build CE-based BDA capabilities, organisations need to orchestrate their resources and competencies and align them well with specific sustainability targets. In consideration of these issues, this study was conducted to identify the aforementioned capabilities and their effects on the performance of circular AFSCs from the perspective of a developing country. To this end, a three-stage multi-criteria decision-making model was developed and used in the examination of circular AFSCs in Turkey. The findings revealed that supply chain management (SCM) was the most important capability, followed by organizational, technical, environmental, economic, and social capabilities. Furthermore, big data infrastructure was the most important sub-capability ahead of financial benefits, top management support, sustainability and resilience, and food waste reduction. Finally, productivity improvement was determined as the most significant impact of CE-based BDA capabilities on circular AFSCs. This study can serve as a reference for managers and policy-makers on what BDA capabilities should be developed for circular AFSCs. It also contributes to addressing the agricultural production issues encountered by developing countries.
Chapter
Agricultural economics deals with the methods of effective land usage, maximizing the crop yield while maintaining the good soil ecosystem. It is concerned with the application of economical theories to optimize the production and the distribution of the agricultural yield. We know that in India, more than 50% of the population is directly or indirectly dependent on the agriculture sector for living. The contribution of agriculture in the gross domestic product is mere 17%–18% which is much less compared to the number of people involved. This is primarily because of lack of scientific approach and the absence of new technologies in this field. In this chapter, we have focused on how we can reform the field of agriculture by inducting machine learning and artificial intelligence technologies. It will not only help to increase the production but also to make the agricultural sector more economical and profitable.
Chapter
Full-text available
Seven percent of world palm oil (PO) production comes from Latin America (LATAM), 15% certified as sustainable PO with the adoption of the Round Table model for Sustainable Palm Oil (RSPO), pointing to sustainable agriculture that contributes to hunger reduction and a reduction of dependence on hydrocarbons for energy. Colombia is the fourth global producer of PO and the first one in LATAM and expects to produce over two million tons in 161 municipalities and 21 departments in 2021. This document will focus on the Colombian PO industry. The contribution of this study is twofold: First, it provides a more comprehensive review of the PO industry technology literature based on Scopus and Clarivate Analytics, using the reporting checklist of preferred reporting items for systematic reviews and meta‐analyses (PRISMA). Second, as far as the authors know, this is one of the first studies to address the technological solutions applied by Colombia's PO producers and aims to help fill this research gap. Evidence for the use of Internet of Things (IoT), big data (BD), and cloud computing in the Colombian PO industry was found in the extraction plants, in crop and pest management, in the use of seeds with smart tags, and in biofuel generation from PO, positioning it as a country with multiple lessons to offer to the PO industry.
Chapter
Productiveness present in soil, productive weather conditions, plant growth information, rainfall in regional areas, and information on seed planting, among other things are significant parameters to consider for the development and improvement of Indian agriculture. All parameters can be gathered via IoT sensors and digital devices and stored in real-time database environments for sharing with digital machines. It aids farmers in obtaining information on all aspects of agriculture. Modern farming may be recorded using different sensors, smart digital cameras, and gadgets such as micro-chips thanks to the internet technology era. The automated technology provided by the internet of things (IoT) assists farmers in a variety of ways, including the most efficient use of resources (resources are finite) and agricultural problems.
Article
Full-text available
Smart Farming is a development that emphasizes the use of information and communication technology in the cyber-physical farm management cycle. New technologies such as the Internet of Things and Cloud Computing are expected to leverage this development and introduce more robots and artificial intelligence in farming. This is encompassed by the phenomenon of Big Data, massive volumes of data with a wide variety that can be captured, analysed and used for decision-making. This review aims to gain insight into the state-of-the-art of Big Data applications in Smart Farming and identify the related socio-economic challenges to be addressed. Following a structured approach, a conceptual framework for analysis was developed that can also be used for future studies on this topic. The review shows that the scope of Big Data applications in Smart Farming goes beyond primary production; it is influencing the entire food supply chain. Big data are being used to provide predictive insights in farming operations, drive real-time operational decisions, and redesign business processes for game-changing business models. Several authors therefore suggest that Big Data will cause major shifts in roles and power relations among different players in current food supply chain networks. The landscape of stakeholders exhibits an interesting game between powerful tech companies, venture capitalists and often small start-ups and new entrants. At the same time there are several public institutions that publish open data, under the condition that the privacy of persons must be guaranteed. The future of Smart Farming may unravel in a continuum of two extreme scenarios: 1) closed, proprietary systems in which the farmer is part of a highly integrated food supply chain or 2) open, collaborative systems in which the farmer and every other stakeholder in the chain network is flexible in choosing business partners as well for the technology as for the food production side. The further development of data and application infrastructures (platforms and standards) and their institutional embedment will play a crucial role in the battle between these scenarios. From a socio-economic perspective, the authors propose to give research priority to organizational issues concerning governance issues and suitable business models for data sharing in different supply chain scenarios.
Article
Full-text available
At the present time, we are facing an emerging problem which will become even more urgent and critical in the coming decades: the Food and Agricultural Organization of the United Nations (FAO) estimates an increase of the world population from the current 6 billion people to 9-11 billion people by 2050 leading to a doubling of world-wide food demand. It is generally believed that that smart, data-rich ICT-services and applications, in combination with advanced hardware, can provide the much needed breakthroughs to producing enough good quality food in a safe and environmental-sound way. Therefore, the EU?s Future Internet Public-Private Partnership (FI-PPP) program (www.fi-ppp.eu) aims to make service infrastructures and business processes more intelligent, more efficient and more sustainable through tighter integration with Future Internet (FI) technologies.
Article
Full-text available
Farming is undergoing a digital revolution. Our existing review of current Big Data applications in the agri-food sector has revealed several collection and analytics tools that may have implications for relationships of power between players in the food system (e.g. between farmers and large corporations). For example, Who retains ownership of the data generated by applications like Monsanto Corproation's Weed I.D. “app”? Are there privacy implications with the data gathered by John Deere's precision agricultural equipment? Systematically tracing the digital revolution in agriculture, and charting the affordances as well as the limitations of Big Data applied to food and agriculture, should be a broad research goal for Big Data scholarship. Such a goal brings data scholarship into conversation with food studies and it allows for a focus on the material consequences of big data in society.
Article
Full-text available
This paper presents a review of academic literature, policy documents from government organizations and international agencies, and reports from industries and popular media on the trends in Big Data utilization in key development issues and its worthwhileness, usefulness, and relevance. By looking at Big Data deployment in a number of key economic sectors, it seeks to provide a better understanding of the opportunities and challenges of using it for addressing key issues facing the developing world. It reviews the uses of Big Data in agriculture and farming activities in developing countries to assess the capabilities required at various levels to benefit from Big Data. It also provides insights into how the current digital divide is associated with and facilitated by the pattern of Big Data diffusion and its effective use in key development areas. It also discusses the lessons that developing countries can learn from the utilization of Big Data in big corporations as well as in other activities in industrialized countries.
Article
Purpose – The purpose of this paper is to provide a brief and necessarily partial overview of the design, motivation, and use of the Ag-Analytics platform (ag-analytics.org), focussing on integration and warehousing of publicly available research data for broad communities of researchers, including those in the area of agricultural finance. Design/methodology/approach – The paper walks the reader through an overview of the layout and utilization of the Ag-Analytics platform, including a few example applications of some of the tools and web API’s. Findings – Much of the data researchers routinely use in agricultural and environmental finance and related fields are often – strictly speaking – publicly available; however the form in which they are distributed leads to great inefficiencies in data sourcing and processing which can be greatly improved. The goal of the Ag-Analytics open data/open source platform is to help researchers centralize and share in such efforts. Development of systems for disseminating, documenting, and automating the processing of such data can lead to more transparency in research, better routes for validation, and a more robust research community. Practical implications – Some of the tools and methods are discussed, as well as practical issues in data sourcing and automation for research. A few high level introductory examples and applications are illustrated. Originality/value – Development and adoption of such systems and data resources remains seriously lacking in social science research, particularly in the economics, natural resource, environmental, and agricultural finance spheres. This brief provides an overview of one such system which should be of value to researchers in this field and many others.
Article
The increased availability of high resolution data and computing power has spurred enormous interest in “Big Data”. While analysts typically source data from a wide variety of agencies, even within the USDA no comprehensive data warehouse exists with which researchers can interact. This leads to massive duplication in efforts, inefficient data sourcing, and great potential for error. The purpose of this article is to provide a brief overview of this state of affairs within the community. An overview of a prototype warehouse is also provided, as are thoughts on future directions.
Conference Paper
It is a trend to use information technology to lead the development of modern agriculture. The IntelliSense Internet of Things will be an important support for intensive, high-yield, high-quality, efficient, ecological security agriculture. In this paper, we give solutions and key technologies of facilities agriculture based on the Internet of Things technology. On this basis it designs and implements facility cultivation greenhouses. Practice has proved that the Internet of Things is the development of modern agriculture productivity. It has an important significance in raising the level of agricultural development, improving the overall efficiency of agriculture, promoting the upgrade of modern agricultural transformation. © 2013 IFIP International Federation for Information Processing.
Big Data and smallholder farmers: Big Data applications in the agri-food supply chain in developing countries. International Food and Agribusiness Management Review
  • L Protopop
  • A Shanoyan
Protopop L, Shanoyan A. Big Data and smallholder farmers: Big Data applications in the agri-food supply chain in developing countries. International Food and Agribusiness Management Review 2016:19.A:173-90.
Big Data and the Ag sector: more than lots of numbers. International Food and
Steve S. Big Data and the Ag sector: more than lots of numbers. International Food and Agribusiness Management Review 2014;17(1):1-20.