Where Is Imagery in Digital Farming?

I was recently asked, “Where is imagery in digital farming?” Imagery, especially from satellites and increasingly from drones, is often proposed or inferred as the core functionality of digital farming. Why else would almost every digital farming discussion center on it and every platform lead with it as its centerpiece functionality?

Digital farming is about two key objectives. The first objective is getting inside the decision loops of the cultivation and making decisions before they become a risk. The second objective is enabling digital farming, the digital twin, to use its data to anticipate, assess, and explore alternative courses of action.

The user must first understand the agricultural decision cycle, and then the user must separate the variable data from the invariable data. The agricultural process will contain continuous decision loops throughout the cultivation, and the invariable data will provide the foundation for decision analysis. On the other hand, the variable data will enable the development of decision information.

The agricultural decision process looks like a decision loop developed in the 1960s for the military. It was called the OODA loop. From Wikipedia: “The OODA loop is the decision cycle of observe, orient, decide, and act, developed by military strategist and USAF Colonel John Boyd.“

For agriculture, digital farming might employ a modified OODA Loop for its decision loop. The modified OODA Loop is: Indication, Detection, Identification, Localization, Mitigation, and Validation. The Observe step is Indication. The Orient steps are Detection, Identification and Localization. The Decide step is deciding upon mitigation based upon analysis from the digital twin. The Act Step is Mitigation and Validation.

Imaging is used at the Detection, Identification, Localization, and Validation steps. Imaging exists inside of the decision loops for each of these steps and only exists to develop the decision information required for each loop. Each imaging technology has its optimum OODA use case.

Imaging provides both variable and invariable data. The best known of the imaging technologies measures the amount of the incident energy that is reflected by vegetation, soil, and other artifacts in the cultivation. These imaging sensors have varying spatial, spectral, radiometric, and temporal resolutions, and each has an optimum utility in the decision process. Other sensors that that might be used include Light Detection and Ranging (LIDAR), Synthetic Aperture Radar (SAR), and earth penetrating radars. These sensors transmit a pulse of incident energy and then measure the reflected energy, including the time and intensity of the return. This data tends to be invariable.

File sizes for imaging environments are massive and are often measured in multiple gigabytes. Generating, collecting, managing, and analyzing this data is expensive. The size of the files demands that they are optimally used and managed before sensing starts. It also demands application automation and integration. Automation and integration can only be accomplished when Imaging is aligned with its specific decision loop.

To date much of the imaging has generated information about the cultivation that does not support a decision, is not automated, and has already happened. Imaging today often has limited contribution to the overall decision process. This might be because it was the wrong sensor, the wrong resolution, or analyzed too late to do any good. Imaging’s contribution to the decision process is where it establishes its value.

When does imaging technology get used, how often, and what is its objective? The following is a sample of where imaging is in a digital farming sequence. There are potentially many different decision cycles that could be synthesized; each decision cycle will be crop and objective dependent.

As a functional starting point there are some key takeaways that were stated in the previous article about a digital farming system. Many of these factors represent invariant data. First, soil is the productive asset. There needs to be a digital soil model in this ecosystem, i.e., a digital twin that models the soil and its productive capability. Soil is the common denominator; one cultivation to the next. Next, seed production generates a wealth of information about that crop and the metrics for that production are available to the next cultivation. This includes crop and variety information like time to first emergence, timing of vegetative states, root growth profiles, nutrient and moisture utilization, and fruit size and maturation. Finally, the stresses that impact the cultivation are persistent. The geo-location and persistence of these stresses applies to weeds, fungi, insects, and biologicals. Early indications of these stresses are locked in the memory of the soil, and the digital twin will remember exactly where.

These data and their metrics can be statistically described, and these results can be used to digitally predict, specify, and schedule when imaging events in the next cultivation should be happening. This “memory” can be used to develop the indication, and like seed production their occurrence can be predicted and used to develop the various OODA loops.

Some examples of imagery used in digital farming include:

  1. Using LIDAR to establish and determine the topography of the field. Topography is the height of each soil asset relative to the soil assets around it. LIDAR systems on airborne systems can develop topographic or elevation maps of a field in a very short time, and LIDAR can provide resolutions in centimeters/ inches. This map with Electrical Conductivity maps will assist in determining where to take soil samples. Its value will be reinforced over and over as it gives insight to the soil horizons and soil contents at depth.
  2. The next area might be crop emergence. We know what the planting plan was and when it was implemented, and we can geo locate every seed. The computer can anticipate emergence, and with imagery it can count each seed with unitary precision. With emergence the digital twin can predict time to vegetative states, crop moisture and nutrient usage and requirements, potential fruit sizes, and production yields. It can execute this process for every seed if required. Each of these predicted steps gives rise to a new OODA loop.
  3. The digital twin will provide indications from memory or from environmental inputs that indicate the presence of these stresses, and properly used imaging will note the possible first detection of these stresses. The digital twin will predict when to start the next OODA Loop. Each stress will have its own signature, its sensible profile, and its temporal offset. This data in a digital twin defines the imaging technology and when and where to look beyond indication to achieve detection, identification, and localization.

Indeed, imagery is a part of digital farming, and, potentially, it is useful at many steps in the decision process. The image requires a level of precision that enables the required decision. It should be appropriate to the action required and no more, but its value is as a complement to the decision process to provide the valuable inputs that support detection, identification, localization and validation. It should seek to inform the process before an event so that it is inside the decision loop and there is time to take the appropriate action.


Leave a Reply

4 comments on “Where Is Imagery in Digital Farming?

  1. Appreciation, is the right world to thank you for such excellent article Michael. I could not stop underlining all the key points of your narrative. Translating your ideas into validations that will make business sense — specially for new Agtech companies emerging everywhere — is no easy task, needless to say from an investment perspective. Business model for many Agtechs addresses decision cycles poorly. Decision cycles evokes critical processes and these are often overlooked, that’s why I think your article is so helpful in seen through these from a real and practical viewpoint. I love when you said that “… image requires a level of precision that enables the required decision ….to provide the valuable inputs to support detection, identification, localization, and validation” which, for me translates into the last delivered mile of real value. From a business/investment point of view, this is absolutely critical. The impact of imagery in supporting real management decisions which, in turn, will deliver and have direct impact on production outputs is, perhaps, the single most important asset for sustaining growth for the emerging Agtech companies (startups especially). Again, thanks for this clear and educational article.

    1. Paulo, Thank you for the comment. I have spent a lot of time in the subject of imagery. Satellite, airborne, and drone. The key is the sensor and what it is you need to “see”. It is about spectral, spatial, radiometric, and temporal resolution. It is about the analytics needed to process and the decision that must be made. What I have seen is that there is a focus on NDVI and multi-spectral… when all you have is a hammer everything is a nail. I see need for high spatial resolution monochrome, hyperspectral in 1-2 nanometer wide measures, and even occasional LIDAR. The crop, the cultivation cycle and the decision loop will help specify the need. I would suggest that for every situation there is a standard Statement of Work and a templated task specification that would capture this need for each decision. This could be easily evaluated for its contribution to the business. At the end of the day it is about profit. I would apply this same measure to IoT and the infrastructure that it requires. I am building a couple of more articles that hopefully will bring all of this together. I have had a couple of excellent conversations about the economics of imagery and the state of technology. Again, thank you for the comments. Michael Collins

    1. Cory, Thank you for your reply. I did mean topography and I do know how difficult that it is. I built a couple using QGIS and participated in others with ARCGIS. I do mean topography and this can be used throughout the imaging process to determine a number of cultivation factors like crop height, etc. It is useful for soil and other factors. I did not mention elevation. On a macro scale of geological constructs I can see the need for elevation but in the immediacy of the Digital Farming initiative I am interested in topography including buried artifacts, boundaries, and geological artifacts that impact hydration, nutrients, and soil horizons. I have written a couple of follow on articles and in those I also specify topology. I also say that the user should not be burdened with manipulating this data to get it. Again, thank you. Would you like to discuss this further? Michael Collins

Imagery/Sensing Stories
Imagery/SensingIntelinAir, TerrAvion Partner on Ultra High Resolution Imagery with Automated Analysis
June 21, 2018
IntelinAir has partnered with TerrAvion to deliver what it is calling a “best in class imagery solution” to joint customers Read More
Imagery/SensingImagery in Agriculture: Time for a Reality Check
June 4, 2018
Where do I begin….I’ve been dealing with imagery in agriculture since I was 10 when my dad started Satshot. At Read More
Imagery/SensingIsraeli Imagery Provider Acquires Mavrx
May 17, 2018
Taranis, an Israel-based provider of high-resolution agriculture aerial imagery and deep learning, today announced the acquisition of all Mavrx assets, one Read More
Imagery/SensingSatellite Imagery Added to Paramount Reports
May 3, 2018
Paramount Reports, a reporting platform developed by Ag Developer, was built to display data collected on the agX Platform in Read More
Trending Articles
EventsHighlights from the 14th International Conference on Precision Agriculture
July 9, 2018
The 14th International Conference on Precision Agriculture (ICPA) presented by the International Society of Precision Agriculture (ISPA) was held in Montreal, Read More
Topcon X30 Console in cab
EventsAssociation Seeks Definitive Definition of “Precision Agriculture” — What’s Your Vote?
July 2, 2018
More than two-dozen definitions of precision agriculture have been identified through the years — but which is the best and Read More
AmericasRaven Name to Grace New South Dakota State University Facility
June 27, 2018
According to a press release issued by the company, Raven Industries was recognized today in the naming of South Dakota Read More
DronesNew York Apple Orchard Claims World First in Pollination by Drone
June 18, 2018
Beak & Skiff Apple Orchard in LaFayette, NY, is the first orchard in the world to use drones to pollinate Read More
Sensors/IoTJohn Deere, Pessl Instruments Team Up to Create Opportunities
June 18, 2018
John Deere is best known for its line of tractors, combines, sprayers, and implements. However, in an effort to help Read More
Decision Support SoftwareSST’s Matt Waits: Innovative Data Solutions Key to Transforming Global Agriculture
May 31, 2018
Proagrica, part of RELX Group, earlier this year acquired U.S.-based precision agriculture solutions company, SST Software, in a move set Read More
Latest News
Industry NewsFarmobile Acquires Prime Meridian, Taps Cubbage as New …
July 13, 2018
Farmobile today announced an agreement to acquire the assets of Prime Meridian, a precision agriculture data management company based in Read More
DronesPrecision Agriculture Takes Flight at North Carolina St…
July 13, 2018
Take a walk into the Suggs Laboratory for Precision Agriculture and Machine Systems and it’s hard not to be impressed, Read More
DronesAutomated Weeders Have Arrived in Vegetable Fields
July 12, 2018
The vegetable production areas of the Central Coast of California have lifted vegetable cultivation to a high art, writes Richard Read More
AgJunction, InfoAg 2014, Autosteer, GPS
Industry NewsAgJunction Settles with Raven in Patent Infringement Su…
July 12, 2018
AgJunction Inc., a leader in advanced guidance and autosteering, has settled a patent infringement lawsuit it filed against Raven Industries, Read More
Business ManagementTaking Measure of the Precision Agriculture Program: 6 …
July 12, 2018
In the overall agriculture market, the rhetoric surrounding emerging technology over the past half-decade has been nothing short of breathless. Read More
Industry NewsNew Raven Slingshot Advancements Will Help Save Time, R…
July 11, 2018
Raven Industries, Inc. has announced several new services available on the Slingshot and Viper 4 platforms: Job Generator and Job Read More
Industry NewsAgIntegrated Acquires Exclusive Licence to Satshot’s Im…
July 11, 2018
AgIntegrated, Inc. (AGI), a leader in precision ag data integration and software development, and Satshot, a leader and pioneer in Read More
Australian Harvest
Australia/New ZealandAustralian Agritech Plants Blockchain for Efficiency
July 11, 2018
“Agritech” at one time would have meant new equipment such as tractors and combine harvesters, but today it refers to Read More
AsiaIndia: Using Artificial Intelligence for the Good of Fa…
July 11, 2018
After graduating from IIT-Madras, the first thing that Vivek Rajkumar did was to buy four acres near Thiruvananthapuram and start Read More
Industry NewsForbes List of Innovative Ag-Tech Companies Includes Gr…
July 9, 2018
Forbes magazine recently posted a list of the 25 most innovative ag-tech startups in 2018, which includes a few companies Read More
AmericasNutrien Ag Solutions Brand, New Digital Platform Launch…
July 9, 2018
Nutrien (formerly Crop Production Services) has officially rebranded its retail business to Nutrien Ag Solutions, aligning the company’s retail operations Read More
EventsHighlights from the 14th International Conference on Pr…
July 9, 2018
The 14th International Conference on Precision Agriculture (ICPA) presented by the International Society of Precision Agriculture (ISPA) was held in Montreal, Read More
Industry NewsTerrAvion Integrates Aerial Imagery with John Deere Ope…
July 6, 2018
TerrAvion, Inc., a large volume provider of aerial imagery to agriculture, has announced an integration to allow TerrAvion’s aerial imagery Read More
Data ManagementAgriculture’s Next Breakthrough: New Technologies…
July 3, 2018
We live in an exciting time in agriculture. Not only is technology advancing rapidly, but the understanding and comprehension of Read More
Precision IrrigationNotes from the Field: A Look at Irrigation Management P…
July 2, 2018
One of the things I love most about my work is making periodic treks into the field – more often Read More
Topcon X30 Console in cab
EventsAssociation Seeks Definitive Definition of “Preci…
July 2, 2018
More than two-dozen definitions of precision agriculture have been identified through the years — but which is the best and Read More
Industry NewsAg Equipment Manufacturers: 3 Trends to Shape Farming G…
July 2, 2018
Bottom line instead of brand loyalty. Tractors and harvesters will look more like computers. Data will drive productivity. These are Read More
Ag Retailer and Growers with tablet WinField United
Service ProvidersPrecision Ag Technology: Act Like You’ve Been There Bef…
July 2, 2018
One of my dad’s favorite, albeit borrowed, sayings was, “Act like you’ve been there before.” He was mostly referring to Read More