Harvesting data – but how to use it? Precision agriculture has been around for quite some time. But questions remain, specifically on how data from precision ag tools are used, and how that benefits farmers and ranchers.
Chris Paterson, formerly North America Lead for Xarvio (a division of BASF), says digital agriculture can support farmers worldwide by monitoring soil and crop conditions, assisting with disease and pest recognition, and providing recommended treatments based on in-field conditions. Paterson outlines here for New AG International how data is used and why that is a good thing.
The “digitization” of farming and agronomy is viewed as one of the most exciting opportunities in one of the world’s oldest, largest, and most essential industries. Really?
It was exactly 15 years ago when I was comparing an HP IPAQ and a Palm Pilot in front of me, debating which one would most likely become the best pocket-size mobile device for conveniently entering crop scouting data right from the field into the cloud, no laptop needed. Little did I know that very soon a company called Blackberry would soon eliminate both of those devices, and then stubbornly suffer the same fate themselves as the Google and Apple devices became everyone’s favourite (but that’s another story).
The thinking at that time was that if the data entry function was so convenient that a laptop was not even needed, and the pocket devices were so popular that everyone would carry one always, the inconvenience barrier would be removed and it would happen. We would be able to fine-tune the fertility program, avoid pesticide resistance, compare genetic performance, estimate crop yields and take advantage of marketing opportunities. And yet the entry of field data remained a challenge, except for a small percentage of meticulously organized farms, or farms that hire an agronomist to manage their agronomy program.
Some have speculated the barrier to entry might be more related to scepticism around data ownership, privacy and accountability. Many times, I have given presentations to farm groups and events, stressing the importance of making sure the company behind the program is reputable and long-term viable, and that it is known how they make their revenue. Farmers need to make sure it is understood exactly how the data will be used and what new value will be provided back, whether there are rights to sell the data to third parties, whether there are rights to use the data in anonymized aggregated pools of data to come up with area averages or other forms of big data. And what precautions have been taken to ensure security and backup.
There is definitely a wide mix of company types offering data management products for farms and agribusinesses, and in this mix there are definitely some very good choices that offer long-term viability, integrity and good value. In fact, the risk of proprietary data ending up in the wrong hands is actually very low compared to the consumer apps we use in our devices to take photos, check the weather, stream some music, participate in social media or read the news. So that has likely not been the biggest barrier to better field data entry.
My speculation is the bigger reason has simply been that the hassle for busy people in busy moments was still larger than the perceived value; that the promise of improved decision support was too vague, and it was too easy to just use the muscle memory on how decisions were made previously.
And yet, despite seemingly slow progress in any given year over the past 15 years, at least compared to that hockey stick chart we all expected, the adoption has consistently expanded, and the rate of adoption is really accelerating at this time. Why?
My impression is the effort has been reduced or even eliminated, and a wide range of higher value outputs are appearing. We are transitioning from decision support tools to decision making tools that can also deliver the output.
Sensors have reduced in size, improved in reliability and longevity, and the cost has dropped impressively. Instead of typing, data is now automatically appearing in templates from the field equipment: from weather stations, from soil moisture probes, from satellites, or from drones and airplanes. Over time, as large volumes of data begin appearing, “machine learning” can be used to study the patterns and spot the anomalies, clean the data sets up, eliminate the bad data or populate the missing data, and then look for the correlations.
The output now, with almost no typing involved, could show up as an alert that risk has evolved and timing is critical so something needs to happen; it could be a variable rate prescription that wirelessly lands in your sprayer controller and sets up the right rates for different areas of the field; or it could be an automatic appraisal of what weeds are present and from that what the options are for controlling them – and when that should ideally happen, given the growth stage and the predicted weather conditions. And soon, a fully autonomous implement that just does everything right.
Beyond optimizing the timing and dosage of the right crop inputs, choosing the right genetics, and becoming more efficient with the logistics and task coordination, there are even bigger value opportunities emerging through digitization in the areas of qualifying for finance and insurance, demonstrating contract or regulatory compliance, new income streams related to sustainability and carbon initiatives, and selling to buyers who want to be able to tell the story of food to the consumer.
In summary, the “digitization” of farming and agronomy is definitely one of the most exciting opportunities in one of the world’s oldest, largest and most essential industries.
This article was first published in New AG International September 2020, here. Chris Paterson can be found at Tall Grass Ventures. He is also a board member of Soilgenic – featured here in New Ag International.