Agroinformatics: Measuring Progress in Data, not Yield
The Evolution of Farm Tech
Throughout time, the greatest agricultural progress has been measured in lengths we like to refer to as revolutions. The first occurred as humans transitioned from scattered hunter-gatherers to the society of farmers we recognize today. The second, often called the mechanical or chemical revolution, coincided with the industrial revolution. During this time, labor-saving inventions such as the reaper and the combine freed farmers from the tribulations of field work. Synthesized fertilizers and pesticides also began to reach growers on the cutting edge. A third “Green Revolution” occurred as society took a special interest in the genetic potential of dwarfed grains and their response to synthesized nitrogen fertilizer (Three Great Farming Innovations of the Last Century 2014). Now, we find ourselves debatably in the midst of a fourth revolution dominated by technological innovation and progress in genetic engineering. This “Data” revolution is fueled by just that; data, or in a broader sense informatics.
Improving Farm Productivity
Agroinformatics could be defined as the science of computer information systems designed to function in tandem with agriculture. It can be broken down into three distinct phases: data collection, sharing, and analysis. Through these three steps, agroinformatics aims to accomplish a number of goals including, but not limited to; improving farm productivity, labor efficiency, decision making, planning, storing of secure data, simplifying intervention, and access to information for all vested parties (Moni 2012).
Automation in the Field
As stated, the first step in the process is data acquisition. Most growers currently rely on physically measuring, weighing, photographing, tissue/soil sampling, or collecting whatever records seem appropriate. With a large population of plants, this quickly becomes inefficient, tedious, and costly. Cutting edge agri-technology seeks to remedy this issue with a combination of sensing and automation directly in the field. These “smart sensors” vary depending on the data in question. Location sensors use GPS technology to triangulate and map geographical features for precision agriculture. Optical sensors can identify the presence of clay, organic matter, moisture content, plant features, weed/insect pressure, and detect disease-stricken plants. Electrochemical and mechanical sensors evaluate soils properties (Shriber, Steven). When used in conjunction, these units produce a dynamic portrait of wellness for cultivators that can be accessed remotely. This brings us to the second step.
Farm Data Interoperability
All this information means nothing unless it makes it to the appropriate platform or set of eyes. That’s where data sharing comes into play. Agroinformatics relies on the ability to send messages from production sites to distribution, consumption, and processing sites via cloud-based file sharing. From here it can be stored in public or private databases where users may query for relevant files. Theoretically, these databases are constantly growing as the data collection system in place should be logging files periodically (Yoshida 2018). As this breadth of information swells, it must be translated via a process called data interoperability. Interoperability is the process by which we, “standardize data from disparate sources through machine-assisted spell correction and ontology matching. Innovating in agriculture can involve decisions that span from molecules to markets.” (Data-Driven Agricultural Innovation 2018). The last piece of the data-sharing puzzle isn’t so much sharing as it is securing. Discrete file sharing and comprehensive digital security must be a top responsibility. Charts and figures may look like a bunch of nonsense to the untrained eye, but in the right hands it can be a very powerful derivative tool. This brings us to our third step.
Using Farm Data for Trend Analysis and Decision Making
Information is a powerful thing, especially when compiled. A single data point can be coupled up to become a vector. A number of vectors can combine to form a trajectory. With enough data we can eventually derive trends and use them to make educated, informed decisions. This is where agroinformatics has the potential to change agriculture as we know it. With proper data collection and file sharing in place, the analytical tools of the future will be able to draw information from thousands of locations across hundreds of seasons. Growers will be able to model and simulate potential scenarios backed by concrete information from cultivators in similar or widely different areas. Decision support systems backed by AI will relay the most optimal circumstances, conditions, and actions to take (Data-Driven Agricultural Innovation 2018). This level of analytics will give users confidence in their choices as the potential success, as well as the potential risks, will always be calculated.
Farm Technology to Increase Productivity
Ultimately, where there is risk, there is reward. Similarly, where there are benefits, there are often unforeseen detriments. Agroinformatics is no exception. Clearly there are pros to the concept. Comprehensively simplifying and automating integral steps in data acquisition, analysis, access, and storage has the potential to reduce human error, labor, and increase overall productivity in farm systems. Providing opportunities and a platform for exchanging knowledge, strategies, and experiences among researchers will promote and encourage interactions among agriculture scientists, IT professionals, and other stakeholders (Li 2013). On the other hand, these techniques are still in their infancy meaning there is great possibility for misuse. Initial costs may be high and it will take several years, if not decades, before there is sufficient reliable data to fully utilize the analytical capabilities. Lastly, there is the risk of agricultural systems losing their “human touch” as the focus on data and analytics increases (Goklany 2001). The future of agroinformatics will undoubtedly be shaped by both the goals and concerns of those affected.
Farm Management Programs are Entering the Market
In reality, it is a future that is not at all far off. Numerous agriculturally focused computational programs are in development or have already entered this juvenile market. One example is ADAK Farm System’s Farm Produce Manager. This cloud-based program can be used as a scheduling device, analytical tool, and recordkeeping platform that encompasses data from the pre-planting stage to the point of sale. This unique database is combined with regional weather outlook, educational materials, and customizable mapping and view functions to provide a well-rounded tool for large- and small-scale farmers alike. With an impending need to further enhance and improve agricultural efficiency, it is certain that pioneering efforts such as this will be on the forefront of agroinformatics.
“Data-Driven Agricultural Innovation.” Agro Informatics, G.E.M.S, 2018, agroinformatics.org/.
Goklany, Indur M. “The Pros and Cons of Modern Farming.” Fur Commission USA, 21 Mar. 2001, furcommission.com/the-pros-and-cons-of-modern-farming/.
Li, Daoliang. “Information Processing in Agriculture.” Highlighted Articles – Elsevier, China Agricultural University, 2013, www.journals.elsevier.com/information-processing-in-agriculture/.
“Three Great Farming Innovations of the Last Century.” BioResource International, Inc. (BRI), 2014, briworldwide.com/three-great-farming-innovations-of-the-last-century/.
Schriber, Steven. “Smart Agriculture Sensors: Helping Small Farmers and Positively Impacting Global Issues, Too.” Mouser Electronics – Electronic Components Distributor, Mouser Electronics, www.mouser.com/applications/smart-agriculture-sensors/.
Moni, M. “Centre for Agricultural Informatics and E-Governance Research Studies.” CENTRE FOR AGRICULTURAL INFORMATICS AND E-GOVERNANCE RESEARCH STUDIES, Mar. 2012, www.shobhituniversity.ac.in/caigers/index.php.
Yoshida, Tomokazu. “Institute of Agricultural Machinery, NARO.” IAM/NARO:Electronic Control Unit Certified by ISOBUS, National Agriculture and Food Research Organization, 2018, www.naro.affrc.go.jp/english/laboratory/iam/research/department_of_innovative_engineering_research/agro_informatics_unit/index.html.