The following is part of an ongoing Smart Rural CommunitySM series on ag tech. In our first installment, published May 11, we shared an overview of U.S. farm markets. In the following section, we will explore examples of ag tech on crop and animal farms. Please join us on June 15 for a Smart Rural Community ag tech webinar; please register here.
III. OVERVIEW AND EXAMPLES OF AG TECH
A. CROPS
Precision agriculture (PA) has been defined as:
using technology to improve input efficiency and collect output data to facilitate future production decisions. . . . It allows farmers to apply the optimal amount of nutrients, seed, and pesticides in the right location, at the right time, using the right product and right amount to maximize crop yield and save on labor and time.1
The value of precision ag is clarified when agriculture is viewed as a business of logistics. Row and specialty crops are particularly suited to tech-enabled efficiencies during planting and cultivation that enable farmers to harvest and deliver produce to market at peak product times.
The first major iteration of precision ag was the incorporation of global positioning systems (GPS) and guidance systems in the late 1990s.2 These include guided steering systems on tractors as well as sprayers and other implements that adjust output based upon GPS coordinates. Even seemingly rudimentary efficiencies can yield substantial benefit. GPS-enabled autosteering enables tractors to travel in straight lines. This can enable efficiencies by ensuring uniform rows that maximize acreage and ensuring that rows do not encroach upon each other; one study predicts overall efficiency gains of 20% on small farms.3 In this context, “efficiencies” refers to measures such as reducing gaps or overlaps among rows.4 GPS systems can enable drivers to maintain a constant distance of 18” between rows when manipulating a 100-foot boom while travelling 15-25 mph. Farmers can also rely on autosteer while monitoring other systems:
If I have to stare down the hood of a tractor to drive it, I pay less attention to sensors that are bringing information into the cab. I could miss a problem with ground (seed-to-soil) contact or a plugged row nozzle because I am steering instead of looking at cab monitors.5
Autosteer and GPS-guided travel also helps maintain soil density by reducing soil compaction, while guidance systems can lay fertilizer within five inches of a targeted zone, avoiding drifting, wasted fertilizer and unnecessary fuel consumption. “See and treat” systems feature sensors at the front of a tractor that can determine the color of a plant (plants lacking nitrogen are pale green or yellow) and trigger an implement at the back of the tractor to dispense fertilizer.6 It is estimated that fertilizer placement has improved 7% with PA and can improve an additional 14% with further ag tech adoption.7 Irrigation, as well, is aided by PA, which can map fields and curve rows so that rainwater can be directed for natural irrigation. A study found current PA adoption has decreased water usage in agriculture by 4%, and that an additional 21% reduction could be realized at full PA adoption.8
These systems rely upon the analysis of data gathered in the field. In earlier years of PA, farmers would download this data on thumb drives and process the data at their office using the “sneaker net” (literally, walking data back to the office). Newer technology, by contrast, including robust wireless broadband, cloud computing, and artificial intelligence (AI), enables “crop scouting,” specifically, “continuous monitoring to acquire information about plant status, disease incidence, and infestations affecting crop growth.”9 Sensors can collect and transmit data rapidly; robots can execute on-the-go responses including pest control and weed removal.
PA also facilitates better future planning. Visual inspection of crop development (either by surface imaging or drones) combined with sensors that assess soil condition can help farmers create a forward-looking plan of action.10 Data gathered during harvest can contribute to strategic future planting. For example, sensors can measure the mass-flow in a combine’s grain elevator and mark that data with GPS coordinates. This enables farmers to compare yield to sensor-informed soil maps that disclose soil types, nitrate levels, and pH levels. Geolocated data from these maps can direct variable rate technology (VRT) in subsequent seasons to tailor seeding, fertilizer, and pesticides; VRT systems use data from sensors or GPS coordinates to vary the application rates. This enables users to plant “different types of hybrid corn seeds . . . at different locations in a farmer’s field with a single pass of the tractor.”11
The replacement of the “sneaker net” with PA relies on advanced fiber and mobile wireless networks – fiber to support office and backhaul needs and wireless deployments to support mobile systems. For example, drones with 5G components can rely on cloud computing rather than drone-mounted processing equipment that would add weight and increase power demands.12 These capabilities, however, would require fiber deep into the local broadband network, with precise distances to be determined based on actual data needs.13 But once a robust network of complementary platforms is achieved (the Federal Communications Commission notes that users subscribe to mobile and fixed services concurrently and “treat them as complements,”)14 a combination of fiber and wireless networks can support cloud-based deep learning analytics. Enabled by machine learning, implements can execute on-the-go decisions that can assess field conditions and respond immediately. Imaging and sensors can discern plant status, soil texture and water holding capabilities, and can inform AI systems to control pesticide and fertilizer application as weeds are identified within or beside crops. Drone-mounted sensors can “us[e] reflectance information from the visible and near infrared bands from either bare soil (to discern patterns of soil moisture, organic matter, etc.) and from crop canopies (to estimate crop health/biomass, nutrient deficiencies, crop damage, etc.).”15 GPS-guided auto-steering can leverage digital records of planting, irrigation and feeding, in turn enabling automatic control of implements (namely, any instrument that is attached to and follows a tractor) and improved crop yields.16
Post-harvest, ag tech can support traceability and security. “Data from the farm play a vital role in the post-farm-gate-supply chain, including identifying and dealing with food safety issues, mitigating spoilage and food waste, and cold chain monitoring.”17 For example, without traceability, an outbreak of food poisoning associated with a particular type of produce (for example, romaine lettuce) could trigger the removal of that item from all store shelves across the country. Block chain, by contrast, can enable industry to identity the farm and field from which the tainted produce was harvested, and recall only inventories from the affected acreage, thereby avoiding vast food waste and associated costs. As observed by an agronomist, block chain tracing:
. . . plays a significant role in helping businesses be competitive in the domestic and global marketplace. The ability to trace a product through all stages of production on farm, processing, distribution, transport and retail to the end point, or consumer, is becoming a standard business practice for all involved in today's food supply chain. . . . Adopting traceability is not a choice. It’s a question of how do we do this in the best way possible, and how do we take advantage of the opportunities that are emerging.18
B. LIVESTOCK
Ag tech can play an important role in livestock and dairy production. The value of potential efficiencies and gains in these sectors is evidenced by the role these industries hold in the national economy. Cash receipts for livestock and poultry total about $100 billion annually.19 U.S. livestock and dairy exports exceeded $20 billion in 2019.20 Global demand for meat and animal products is anticipated to increase 70% by 2050.21 Similar to crops, livestock production commonly operates on small margins; data collection and analytics can be critical to maximize efficiencies and profits. Ag tech for livestock and dairy farming is commonly referred to as precision livestock farming (PLF). Applications enable feed efficiencies and the ability to recognize sick or distressed animals. These functions are especially important because, “the two major costs in animal farming are feed and disease management.”22 Ag tech can support livestock, dairy and poultry production by monitoring feed consumption, animal health, and milk and egg production. Image processing can determine animal weight, as well as “. . . detect their sweat constituents, measure body temperature, observe behavior, detect stress, analyze sound, detect pH, and record[] cows’ movements to aid in the detection [of] diseases and lameness in cattle.”23 Facial recognition technology can enable farmers to decipher animal health status.24 Microphones can detect and distinguish among types of coughs.25 These abilities are critical in an industry where, as noted above, the major cost factors are feed and disease.26 Contagious diseases in confined conditions can devastate herds.27 Cameras can help farmers with the critical task of identifying and isolating sick animals. On poultry farms, air sensors can detect concentrations that evidence the presence of avian intestinal disease.28 PLF can also enhance worker safety. Large, open production areas are features of dairy and beef farms. In contrast, hog and poultry facilities generally operate at high biohazard ratings and have limited access from humans due to biological and contamination threats. These scenarios increase the value of remote monitoring technology.
Research literature on PLF is not as abundant as that which exists for PA. Preliminary studies, however, indicate that similar to the efficiencies enjoyed in PA, PLF would enable gains. PLF includes, but is not limited to, robotic milking systems, livestock health monitoring, and associated hardware. One study focusing on dairy production found improved productivity among PLF adopters, but noted the relative lack of data in the field and concluded, “more empirical research[ is] needed to better understand the effects of PLF technologies adoption on the productivity of heterogenous farms . . . .”29 Another study is reported to estimate the U.S. PLF market to increase from $3.1 billion in 2020 to $4.8 billion in 2025.30 Despite the nascent state of PLF data, it can be anticipated that technological advances in PLF and other applications aimed at poultry and egg production will continue, increasing productivity and driving additional demand for increased broadband connectivity in agricultural spaces.
Coming soon:
What drive ag tech adoption? Join us as we explore the respective roles of farm size, farmer age and educational attainment on broadband and tech adoption.
_________________________________________________________________________________________
[1] “Threats to Precision Agriculture,” 2018 Public-Private Analytic Exchange Program, U.S. Department of Homeland Security, at 8 (https://www.dhs.gov/sites/default/files/publications/2018%20AEP_Threats_to_Precision_Agriculture.pdf) (visited Apr. 6, 2021) (DHS).
[2] Konstantinos, et al. at 3.
[3] Kharil, Tulsi P,; Ashworth, Amanda J; Shew, Aaron; Popp, Michael P.; Owens, Phillip R., “Tractor Guidance Improves Production Efficiencies by Reducing Overlaps and Gaps,” Agricultural & Environmental Letters, Vol. 5, Issue 1 (2020) (https://acsess.onlinelibrary.wiley.com/doi/full/10.1002/ael2.20012) (visited Apr. 8, 2021).
[4] See, “Benefits and Evolution of Precision Agriculture,” Agriculture Research Service, USDA (Aug. 12, 2020) (https://www.ars.usda.gov/oc/utm/benefits-and-evolution-of-precision-agriculture/) (visited Apr. 8, 2021).
[5] Gullickson, Gil, “How Automated Guidance Changed Farming,” Successful Farming (Dec. 2, 2019) (https://www.agriculture.com/crops/how-automated-guidance-changed-farming) (visited Apr. 5, 2021).
[6] See, Lowenberg-DeBoer, Jess, “Yield of Dreams: How Precision Ag Will Help Feed the Planet,” Trend Magazine, Pew, (Jun. 12, 2017) (https://www.pewtrusts.org/en/trend/archive/summer-2017/yield-of-dreams-how-precision-agriculture-will-help-feed-the-planet) (visited Apr. 2, 2021).
[7] “The Environmental Benefits of Precision Agriculture in the United States,” AEM, ASA, CropLife America, National Corn Growers Association, at 15 (2021) (https://newsroom.aem.org/asset/977839/environmentalbenefitsofprecisionagriculture-2#.YBdQZR2Lc74.link) (visited Apr. 2, 2021) (AEM, et al.).
[8] AEM, et. al, at 18.
[9] Saiz-Rubio, Veronica, and Rovira-Mas, Francisco, “From Smart Farming Towards Agriculture 5.0: A Review on Crop Data Management,” Agricultural Robotics Laboratory, Universitat Politecnica de Valencia, Camino de Vera, at 7 (2020) (Saiz-Rubio, Rovira-Mas).
[10] See, Saiz-Rubio, Rovira-Mas, at 4.
[11] Schimmelpfennig, David, “Farm Profits and Adoption of Precision Agriculture,” Economic Research Service, USDA, at 4 Oct. 2016) (https://www.ers.usda.gov/webdocs/publications/80326/err-217.pdf?v=0) (visited Apr. 7, 2021) (Schimmelpfennig).
[12] Estes, Vonnie, “5G Made Waves at CES But has Long Road to Relevance on-Farm,” AgFunder Network (Jan 27, 2020) (https://agfundernews.com/) (visited Apr. 7, 2021) (Estes).
[13] Thompson, Larry D., and Vande Stadt, Warren H., “Evaluating 5G Wireless Technology as a Complement or Substitute for Wireline Broadband,” Vantage Point Solutions (Mitchell, SD) (2017) (https://www.vantagepnt.com/2017/07/10/white-paper-evaluating-5g-technology/) (visited Apr. 7, 2021).
[14] Inquiry Concerning the Deployment of Advanced Telecommunications Capability to All Americans in a Reasonable and Timely Fashion: 2020 Broadband Deployment Report, Docket No. 19-285, Federal Communications Commission, at para. 12 (Apr. 24, 2020) (“The record also provides substantial evidence, however, that fixed and mobile services often continue to be used in distinct ways, and that users tend to subscribe to both services concurrently and treat them as complements.”)
[15] DHS, at 12.
[16] See, i.e., Tyler, Mark B., and Griffin, Terry, “Defining the Barriers to Telematics for Precision Agriculture,” Kansas State University at 1, 2 (Southern Economic Association 2016 Annual Meeting, 2016) .
[17] Estes.
[18] Folnovic, Tanja, “Traceability – What’s It All About?,” Agrivi Blog (https://blog.agrivi.com/post/traceability-what-s-it-all-about) (visited Mar. 22, 2021).
[19] Animal Products, Economic Research Service, USDA (Aug. 21, 2019) (https://www.ers.usda.gov/topics/animal-products/) (visited Mar. 12, 2021).
[20] “2020 United States Agricultural Export Yearbook,” Foreign Agricultural Service, USDA, at 4 (2020) (https://www.fas.usda.gov/sites/default/files/2021-04/2020-ag-export-yearbook.pdf) (visited Apr. 7, 2021). This includes pork and pork products; beef and beef products; and dairy products.
[21] Neethirajan, Suresh, “The Role of Sensors, Big Data and Machine Learning and Modern Animal Farming,” Sensing and Bio-Sensing Research 29, at 1 (2020) (https://reader.elsevier.com/reader/sd/pii/S2214180420301343?token=B602564370C602815736ED0D3610E8F2B313404BAAA7EAFD25129E21B1D56472EE9F980CE1FECCC7CC0335148D82EEB4) (visited Mar. 12, 2021) (Neethirajan).
[22] Id.
[23] DHS at 14.
[24] Neethirajan at 4.
[25] DHS at 14.
[26] Neethirajan at 1.
[27] Neethirajan at 3.
[28] Id. Neethirajan explains as an example that sick pigs move up to 10% less during early stages of infection and describes how air sensors that measure the concentration of volatile organic compounds in the air can be used to identify the occurrence of intestinal infections in poultry.
[29] Carillo, Felicetta, and Abeni, Fabio, “An Estimate of the Effects from Precision Livestock Farming on a Productivity Index at Farm Level: Some Evidences from a Dairy Farms’ Sample of Lombardy,” Animals, MDPI, at 9 (2020) (Carillo and Abeni).
[30] “Precision Livestock Farming Market with COVID-19 Impact Analysis by System Type, Application, Offering, Farm Type, Farm Size and Geography – Global Forecast to 2025” (Nov. 2020) (https://www.reportlinker.com/p05812010/Precision-Livestock-Farming-Market-by-Functional-Process-Hardware-Application-And-Geography-Analysis-Forecast-to.html?utm_source=GNW) (visited Apr. 7, 2021).
