Data cooperatives in agriculture: why farmers should share their data
Last month, I spent two days at Agritechnica in Hanover, the world’s leading agricultrual technology fair. Walking around the fair gave me some insights into the current trends in agriculture. The key theme at this year’s show was connectivity and how internet connected sensors on new agricultural machines can give farmers better insights into their business, allowing them to improve their operating efficiency.
Sensors currently available on agricultural machines can gather a large amount of data relating to the machine and field conditions. Machine operating parameters such as GPS location, engine load and fuel consumption can be measured to determine how efficiently a machine is operating. Sensors are also equipped to machines to measure the condition of the crop. For example, cameras are being used to assess the nutritonal state of plants and to identify weeds. The video below shows a smart spraying system, developed by Amazone, which uses a camera to identify a weed so it can be individually sprayed. This system allows a significant reduction in the volume of chemical required to spray a field when compared to conventional spraying systems which spray with a constant flow rate.
Many systems are available that display this sensor data on a dashboard within a mobile app or web browser, giving the farmer a complete overview of their farm. These current systems provide a wealth of information to the farmer and the system provider, and no doubt these systems will significantly increase the efficiency of farming operations, however I believe that the full potential of this information lies within cooperative data sharing programs. Such programs would encourage farmers to share their data, so that insights and comparisons could be made on a regional, national and global scale.
One use for this data could be to compare equipment settings and correlate these with machine running efficiency, crop yield and even weather conditions to determine optimal settings for different machines, regions and weather conditions. For example, the inflation pressure of different tractor tyres could be correlated with wheel slip and weather conditions to determine which tyre setup is most effective in different weather conditions. This allows the farmer to make better informed decisions when setting up and renewing their equipment. This would also push tyre manufacturers to be more innovative as real world comparisons could be made between their product and their competitor’s.
Additionally, this shared data would allow farmers to determine how competitve they are at growing different crops compared to other farmers, and such insights would enable them to adjust their business plan to ensure they are utilising their land to its full potential. For example, data may show that in a particular region of a country crop X grows incredibly well, whereas crop Y does not grow so well. This insight will allow farmers to make better decisions as to what crops should be grown on their farm.
On a national and global scale, the data could help policy makers identify which regions are best suited to producing different crops, allowing them to make better informed decisions when creating policies to futher optimise their region’s output and the global food supply chain.
I believe that this concept does not just apply to agriculture, and could be used in a multitude of other sectors and industries. Another use case for this concept is energy usage data in homes. A shared pool of energy usage data would allow home owners to see how much energy they are using compared to similar sized homes. This would allow them to determine whether they could make changes to their home to reduce their energy bill. It could even be coupled with a government incentive scheme to encourage people to increase the energy efficiency of their home, and reduce overall energy consumption.