A robot-enabled, data-driven machine vision tool for nitrogen diagnosis of arable soils
Increasing crop productivity with reduced inputs and lower impacts on the environment is a major challenge for global food production. Optimal nitrogen (N) fertilisation can increase crop production and enhance soil fertility. On the other hand, high N inputs are costly for farmers and result in reductions in plant biodiversity, pollution of natural ecosystems and increases in emissions of the potent greenhouse gas, nitrous oxide.
Current spend on fertilisers by UK farmers is £1.345bn. At present excessively high N fertiliser rates are used by farmers because they are not aware of the areas of land where N is excessive, optimal or deficient. Accurate detection of soil N is crucial for the economic and environmental sustainability of cropping systems. The current practices in determining soil N is costly, destructive, labour intensive and time consuming and so high N inputs are common.

Driven by the needs of the growers, in our previously funded feasibility project (N2Vision) we have successfully demonstrated the technical feasibility of a novel non-destructive robot enabled AI vision system for automated N diagnosis in plants and soil. Our initial cost-benefit analysis and farm survey shows our system has potential to cost reduction by 27% and farm profitability increase by 17%, with emission savings of 65%, comparing to current farm practices.
Building on our existing innovation, the goal of this collaboration between industry and academia is to create a commercial robot for automated soil nitrogen monitoring and application. We will showcase how to further improve our existing innovations by optional modular add-on sensors such as 3D mapping (360-degree), soil analysis, leading to automated cost-effective data collection and N monitoring at scale. We will also simulate robotic foliar nitrogen application in a field trial, which has the potential to greatly reduced N usage and costs.
More information: https://n2visionai.wordpress.com/
Paper: https://www.mdpi.com/2072-4292/14/6/1400