Artificial intelligence advances to make farming smarter
More artificial intelligence, cheaper sensors and longer flying drones are only some of the technological advances that Kiwi farmers can look forward to on "data-driven" farms over the next 10 years.
Microsoft Research principal researcher Ranveer Chandra has been in New Zealand for a week offering insights into precision agriculture and advances the United States technology company is working on to improve farming and food production.
He said Kiwi farmers and their innovations could help lead world farming, but they would see more advances themselves over the next decade.
Farmers faced doubling food production to feed a growing population by 2050 and this would require more technological advances world-wide, he said..
" New Zealand is quite advanced as far as technology and agri-practices go and I think this is where New Zealand can lead the world because there is more work to be done."
Chandra was a keynote speaker at the eResearch NZ conference in Queenstown before travelling to Christchurch and Palmerston North to meet with AgResearch and other leaders and leaving for the United States on Monday.
The Indian-born researcher went to the US 18 years ago to complete post-graduate studies and has led Microsoft projects including in longer lasting batteries and TV white space networking.
Chandra said using technology to provide more food for the world was close to his heart as India had much to do to lift its food production.
"I think the one change that will absolutely happen is a move forward to data driven farming."
Farmers would rely less on intuition before taking actions on their farm as they gained more data and this was happening in the technological space and would increase in farming for "precision nutrition", better yields and profits, he said.
The focus on precision nutrition would have nutrients customised for every animal based on the evaluation of data showing, for example, their body condition score, phenotyping and other genetic research. However, this data had to be affordable for farmers to increase its uptake.
Data-driven farming required more sensors and unmanned aerial vehicles such as drones to capture information such as the location of an animal, soil and ambient temperature, humidity and soil nutrients.
The limitation with drones was that it remained difficult to send large amounts of data to the cloud, but this would be solved once faster data streaming was available.
Chandra's research included aerial imagery work with drones and tethered balloons above cattle farms in the US to plot cow movements in a pasture farm to see if they were grazing properly and pastures were being grazed at the right level.
A barrier to advancing farm technology was the cost of sensors, he said. Research for field crop farms in the US showed precision agriculture improved yields and returns on investment, but the sensors were expensive with five of them costing US$8000.
"That is not feasible for farmers when most farmers don't make much money and ... if we reduce the cost of sensors we could bring the benefit of precision agriculture to farmers worldwide."
Chandra's team found that to shorten rural gaps in wireless access they could use TV band white spaces – unused VHF and UHF TV channels - and because of their lower frequency they could increase the distance of coverage during US and India projects, so farmers could connect to the internet.
"This is how we would enable dense placing of sensors if we had $25-$30 sensors and if we could scale this up they would fall down .... because there is so much spectrum available we can get camera data and stream to the cloud."
Chandra said advances in artificial intelligence that had been initiated on farms would be more mainstream over the next 10 years. Artificial intelligence would guide farmers with data-driven predictions such as for the best time to sow seeds, apply fertiliser and provide the best nutrition for livestock.
Weather forecasts would be co-ordinated with available water storage for irrigating crops and pastures or applying fertiliser to them and farmers would take pictures of pests and use artificial intelligence to analyse the best pesticide to control them.
Other research was being carried out to prolong the life of batteries to extend drone flights and assist precision agriculture advances.