Encyclopedia of Big Data

Living Edition
| Editors: Laurie A. Schintler, Connie L. McNeely

AgInformatics

  • Andrea De MontisEmail author
  • Giuseppe Modica
  • Claudia Arcidiacono
Living reference work entry
DOI: https://doi.org/10.1007/978-3-319-32001-4_218-1

Synonyms

Definition

The term stems from the blending of the two words agriculture and informatics and refers to the application of informatics to the analysis, design and development of agricultural activities. It overarches expressions such as Precision Agriculture (PA), Precision Livestock Farming (PLF), and Agricultural landscape analysis and planning. The adoption of AgInformatics can accelerate agricultural development by providing farmers and decision makers with more accessible, complete, timely, and accurate information. However, it is still hindered by a number of important yet unresolved issues including big data handling, multiple data sources and limited standardization, data protection, and lack of optimization models. Development of knowledge-based systems in the farming sector would require key components, supported by Internet of things (IoT), data acquisition systems, ubiquitous computing and networking, machine-to-machine (M2M) communications, effective management of geospatial and temporal data, and ICT-supported cooperation among stakeholders.

Generalities

This relatively new expression derives from a combination of the two terms agriculture and informatics, hence alluding to the application of informatics to the analysis, design, and development of agricultural activities. It broadly involves the study and practice of creating, collecting, storing and retrieving, manipulating, classifying, and sharing information concerning both natural and engineered agricultural systems. The domains of application are mainly agri-food and environmental sciences and technologies, while sectors include biosystems engineering, farm management, crop production, and environmental monitoring. In this respect, it encompasses the management of the information coming from applications and advances of information and communication technologies (ICTs) in agriculture (e.g., global navigation satellite system, GNSS; remote sensing, RS; wireless sensor networks, WSN; and radio-frequency identification, RFID) and performed through specific agriculture information systems, models, and methodologies (e.g., farm management information systems, FMIS; GIScience analyses; Data Mining; decision support systems, DSS).

AgInformatics is an umbrella concept that includes and overlaps issues covered in precision agriculture (PA), precision livestock farming (PLF), and agricultural landscape analysis and planning, as follows.

Precision Agriculture (PA)

PA was coined in 1929 and later defined as “a management strategy that uses information technologies to bring data from multiple sources to bear on decisions associated with crop production” (Li and Chung 2015). The concept evolved since the late 1980s due to new fertilization equipment, dynamic sensing, crop yield monitoring technologies, and GNSS technology for automated machinery guidance.

Therefore, PA technology has provided farmers with the tools (e.g., built-in sensors in farming machinery, GIS tools for yield monitoring and mapping, WSNs, satellite and low-altitude RS by means of unmanned aerial systems (UAS), and recently robots) and information (e.g., weather, environment, soil, crop, and production data) needed to optimize and customize the timing, amount, and placement of inputs including seeds, fertilizers, pesticides, and irrigation, activities that were later applied also inside closed environments, buildings, and facilities, such as for protected cultivation.

To accomplish the operational functions of a complex farm, FMISs for PA are designed to manage information about processes, resources (materials, information, and services), procedures and standards, and characteristics of the final products (Sørensen et al. 2010). Nowadays dedicated FMISs operate on networked online frameworks and are able to process a huge amount of data. The execution of their functions implies the adoption of various management systems, databases, software architectures, and decision models. Relevant examples of information management between different actors are supply chain information systems (SCIS) including those specifically designed for traceability and supply chain planning.

Recently, PA has evolved to predictive and prescriptive agriculture. Predictive agriculture regards the activity of combining and using a large amount of data to improve knowledge and predict trends, whereas prescriptive agriculture involves the use of detailed, site-specific recommendations for a farm field. Today PA embraces new terms such as precision citrus farming, precision horticulture, precision viticulture, precision livestock farming, and precision aquaculture (Li and Chung 2015).

Precision Livestock Farming (PLF)

The increase in activities related to livestock farming triggered the definition of the new term precision livestock farming (PLF), namely, the real-time monitoring technologies aimed at managing the smallest manageable production unit’s temporal variability, known as “the per animal approach” (Berckmans 2004). PLF consists in the real-time gathering of data related to livestock animals and their close environment, applying knowledge-based computer models, and extracting useful information for automatic monitoring and control purposes. It implies monitoring animal health, welfare, behavior, and performance and the early detection of illness or a specific physiological status and unfolds in several activities including real-time analysis of sounds, images, and accelerometer data, live weight assessment, condition scoring, and online milk analysis. In PLF, continuous measurements and a reliable prediction of variation in animal data or animal response to environmental changes are integrated in the definition of models and algorithms that allow for taking control actions (e.g., climate control, feeding strategies, and therapeutic decisions).

Agricultural Landscape Analysis and Planning

Agricultural landscape analysis and planning is increasingly based on the development of interoperable spatial data infrastructures (SDIs) that integrate heterogeneous multi-temporal spatial datasets and time-series information.

Nearly all agricultural data has some form of spatial component, and GISs allow to visualize information that might otherwise be difficult to interpret (Pierce and Clay 2007).

Land use/land cover (LU/LC) change detection methods are widespread in several research fields and represent an important issue dealing with the modification analysis of agricultural uses. In this framework, RS imagery plays a key role and involves several steps dealing with the classification of continuous radiometric information remotely surveyed into tangible information, often exposed as thematic maps in GIS environments, and that can be utilized in conjunction with other data sets. Among classification techniques, object-based image analysis (OBIA) is one of the most powerful techniques and gained popularity since the early 2000s in extracting meaningful objects from high-resolution RS imagery.

Proprietary data sources are integrated with social data created by citizens, i.e., volunteered geographic information (VGI). VGI includes crowdsourced geotagged information from social networks (often provided by means of smart applications) and geospatial information on the Web (GeoWeb). Spatial decision support systems (SDSSs) are computer-based systems that help decision makers in the solution of complex problems, such as in agriculture, land use allocation, and management. SDSSs implement diverse forms of multi-criteria decision analysis (MCDA). GIS-based MCDA can be considered as a class of SDSS. Implementing GIS-MCDA within the World Wide Web environment can help to bridge the gap between the public and experts and favor public participation.

Conclusion

Technologies have the potential to change modes of producing agri-food and livestock. ICTs can accelerate agricultural development by providing more accessible, complete, timely, or accurate information at the appropriate moment to decision makers. Concurrently, management concepts, such as PA and PLF, may play an important role in driving and accelerating adoption of ICT technologies. However, the application of PA solutions has been slow due to a number of important yet unresolved issues including big data handling, limited standardization, data protection, and lack of optimization models and depends as well on infrastructural conditions such as availability of broadband internet in rural areas. The adoption of FMISs in agriculture is hindered by barriers connected to poor interfacing, interoperability and standardized formats, and dissimilar technological equipment adoption. Development of knowledge-based systems in the farming sector would require key components, supported by IoT, data acquisition systems, ubiquitous computing and networking, M2M communications, effective management of geospatial and temporal data, traceability systems along the supply chain, and ICT-supported cooperation among stakeholders. Recent designs and prototypes using cloud computing and the future Internet generic enablers for inclusion in FMIS have recently been proposed and lay the groundwork for future applications. A modification, which is underway, from proprietary tools to Internet-based open systems supported by cloud hosting services will enable a more effective cooperation between actors of the supply chain. One of the limiting factors in the adoption of SCIS is a lack of interoperability, which would require implementation of virtual supply chains based on the virtualization of physical objects such as containers, products, and trucks. Recent and promising developments of the spatial decision-making deal with the interaction and the proactive involvement of the final users, implementing the so-called collaborative or participative Web-based GIS-MCDA systems. Computers science and IT evolvements affect the developments of RS in agriculture, leading to the need for new methods and solutions to the challenges of big data in a cloud computing environment.

Cross-References

Further Readings

  1. Berckmans, D. (2004). Automatic on-line monitoring of animals by precision livestock farming. In Proceedings of the ISAH conference on animal production in Europe: The Way Forward in a Changing World. Saint-Malo, pp. 27–31.Google Scholar
  2. Li, M., & Chung, S. (2015). Special issue on precision agriculture. Computers and Electronics in Agriculture, 112, 1.CrossRefGoogle Scholar
  3. Pierce, F. J., & Clay, D. (Eds.). (2007). GIS applications in agriculture. Boca Raton: CRC Press Taylor and Francis Group.Google Scholar
  4. Sørensen, C. G., Fountas, S., Nash, E., Pesonen, L., Bochtis, D., Pedersen, S. M., Basso, B., & Blackmore, S. B. (2010). Conceptual model of a future farm management information system. Computers and Electronics in Agriculture, 72(1), 37–47.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Andrea De Montis
    • 1
    Email author
  • Giuseppe Modica
    • 2
  • Claudia Arcidiacono
    • 3
  1. 1.Dipartimento di AgrariaUniversity of SassariSassariItaly
  2. 2.Dipartimento di AgrariaUniversità degli Studi Mediterranea di Reggio CalabriaReggio CalabriaItaly
  3. 3.Dipartimento di Agricoltura, Alimentazione e AmbienteUniversity of CataniaCataniaItaly