PHOTO: VERITAS FARM MANAGEMENT
PHOTO: VERITAS FARM MANAGEMENT
PHOTO: VERITAS FARM MANAGEMENT PHOTO: MATT MCINTOSH
MACHINE LEARNING ▶▶▶
Drone with higher education is more useful agronomic tool
I BY MATT MCINTOSH
t’s not just about real-time decision-mak- ing either. This combined technological approach is now being utilised to provide predictive insights on how field conditions
could change. “We need to advance how we farm, but it can’t just be flashy […] I don’t need to bigger my operation, I need to better my operation”, says Mike Wilson, affiliate pro- gramme lead for Veritas Farm Management – an agricultural service company based in Southwestern Ontario, and subsidiary of drone-focused North American data company Deveron UAS.
Real-time replanting decisions Wilson says drones measure fields at the milli- metre level, gathering a lot of data as a conse- quence. With this in mind, he and his col- leagues focus on transforming that data to information the farmer can use. How Veritas uses small drones – rather than larger fixed- wing aircraft – to quickly develop detailed plant population maps is a practical example. Doing so involves flying the drone 8 meters off the ground and identifying crops very early in the season (shortly after emergence) and at key checkpoints – which themselves are iden- tified on zone maps created by combining elevation and historical yield data with soil sampling information, as well as seeding rate
Agricultural service providers in Ontario, Canada, are combining artificial intelligence (AI) and machine learning with drone technology to find more useful – and accurate – agronomic insights for their customers.
variability. Photos taken at each checkpoint highlight any stand gaps present. The farmer can then replant those areas with variable rate seeding, or even manually. An entire field can be accurately covered in minutes, which Wil- son says makes it both more time efficient and thorough than physically walking the field. The same stand information could also be used to make more accurate crop insurance claims. Drones can and indeed are also used to devel- op variable rate maps for fertiliser and crop protection inputs. For Norm Lamothe – farmer, unmanned aerial vehicle (UAV) operator, and co-founder of De- veron UAS – building and layering data has been a key approach to improving profitabili- ty. “What I see on my farm and the decisions we made, there’s opportunity to extract an- other 200 to 300 dollars per acre. We don’t farm a lot of acres, so we have to farm really well. It’s farming to the acre now as opposed to farming the field.”
Predictive nutrient mapping In addition to emphasising the importance of real-time data, Wilson and his Veritas
colleagues – in partnership with Grain Farmers of Ontario, the provincial grain commodity or- ganisation – are currently researching how drones can be used to predict nutrient availa- bility in the next growing season. More specifically, they are looking at how bio- mass and crop colour (leaf data) in red clover – which in Ontario is commonly seeded into winter wheat – can indicate nitrogen availabil- ity for corn planted the following spring. Ac- cording to Lamothe, it is hoped better variable rate nutrient prescriptions can be devised based on the results. He adds it might be pos- sible to determine if biomass also drives heat scripts. “The question is, does the area that has a larg- er biomass of red clover, translate to better nu- trient release for the crop. Does 30, 60, and 90% coverage have different effects? They are going to look at a bunch of variables.” says Lamothe. The project is still in its initial stages. As of summer 2019, Lamothe says his col- leagues are identifying growers that have un- derseeded their current winter wheat crop to red clover, and will begin gathering image data later in the year.
An example of the software counting corn plants. Each purple square is a corn plant.
28
Planting zone map with population check- points.
▶ FUTURE FARMING | 27 August 2019
Drones can be used to see, and distinguish between very small details within the field.
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
