EDITOR’S PICKS ▶▶▶
Farm-level predictability for post-farm players
NORTH AMERICA BY MATT MCINTOSH
C
ould more accurate yield predictions help secondary and tertiary agricul- tural industry players better asses business risk? The founders of a
Agrograph, a Wisconsin ag-software company, certainly think so.
Prediction at field level The start-up recently raised $ 500,000 to fund the expansion of its yield prediction software. It combines high-resolution satellite imagery and field data with machine learning algorithms to predict crop yields at the individual-field level. This, they say, results in more granular and accu- rate bushel per acre predictions. The company sells to three main customer groups: crop insur- ers and lenders to better assess their risk portfo- lio, grain distributors to improve their supply chain logistics, and agricultural tech providers
Nvidia and Yamaha team up ASIA
Chip manufacturer Nvidia and Yamaha Motor have signed an agreement to develop a line- up of autonomous machines to accelerate the automation of driverless agricultural vehicles and low-speed vehicles with AI. Yamaha Motor will include Nvidia’s Jetson AGX Xavier plat- form as the development system for autono- mous machines. According to Yamaha, Jetson AGX Xavier is the world’s first computer created for AI, robotics and edge computing, that will enable automa- tion of a wide range of Yamaha’s products by making them more intelligent. Target products include unmanned ground vehicles which sup- port automation of agricultural processes such as fruit picking; low-speed vehicles based on golf carts, used for “last mile” transportation of people and logistics; and industrial robots and drones. The company expects to begin testing
6
to enhance their precision solutions. Mutlu Ozdogan, co-founder and CEO of Agro- graph, states the the agricultural industry is de- fined by “volatility and variability.” In a drought year, one field might produce great results, while another just a handful of miles away won’t. Agrograph is turning data into solutions at the individual field level, which is a level of in- sight the agricultural industry hasn’t had, Jim O’Brien, another of Agrograph’s co-found- ers, describes the software as bundling satellite imagery along with soil, weather and cropping models to create a crop type identification map and derivative products for both historical and in-season yield predictions. This builds greater accuracy into the company’s models. Predictive yield data has value for the individual farmer, he says, from in-season crop assessment to grain marketing and damage assessment (in the case of hail or wind, for example). “Our focus on the field scale is the same reason a farmer’s focus is on the field scale – because that is their
benchmark for the smallest unit of measure- ment. Yes, precision ag allows you to ‘see’ varia- bility to the square meter, but operational deci- sions are still decided on a field-scale.”
Data for machine learning algo- rithms “From our standpoint, our technology utilises data for machine learning algorithms and it’s not a direct source back to the contributor. Just like Google uses your cell phone location in their traffic algorithm, they are not pin-point- ing and sharing your location to the wider community, unless you want to share it.” Agrograph’s software is purported to have a pre- diction error rate between 5 and 15%. “We see billion-dollar decisions being made with anecdo- tal data across these sectors. It’s not that these companies are make poor decisions today”, O’Brien says. “It’s that they have limited informa- tion and a short timeline to make billionn-dollar decisions. And getting it wrong is very expensive.”
these devices next year, with the goal of a pub- lic launch in 2020.
Farmtrac presents robot tractor
ASIA Escorts Limited, the parent company of tractor manufacturer Farmtrac, presented its ‘Autono- mous Farmtrac’ robot tractor at the Esclusive 2018 event in India. At the moment the Autono- mous Farmtrac is still a concept; it does not yet have a type or serial number. Parent company Escorts says it has developed the autonomous tractor in cooperation with companies such as Microsoft, Trimble, Wabco and Bosch. The trac- tor was presented to hundreds of visitors during a spectacular show at the Esclusive-event in In- dia. It’s no coincidence that Farmtrac displays its autonomous technology on a relatively small tractor. In India, one of the largest for tractor markets in the world, tractors up to 80 hp make up the majority of the market.
▶ FUTURE FARMING | 1 November 2018
Noticeably a number of other oriental manu- facturers preceded Farmtrac showing their au- tonomous tractors to the public, particularly in the segment of small tractors. Recently Yanmar did so, and Kubota unveiled one at the Ag- ritechnica in Germany, late 2017.
Can AI outperform human growers?
EUROPE 14 August marked the start of the Autono- mous Greenhouses Challenge as five interna- tional teams try to grow cucumbers with the
PHOTO: BAS VAN HATTUM PHOTO: BRENDAN SMIALOWSKI
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
