It’s been suggested that agriculture stands on the brink of another technological evolution, with drones and robots set to revolutionise field work, allowing for ‘ultra-precision’ agriculture.
The current focus for machine learning is on monitoring and forecasting - jobs that can be done every day to optimise crop growth. There is scope for roaming robots to tackle pests, diseases and weeds, and with much more precision and less environmental impact than current methods allow.
The process will involve sensors feeding crop information in real time to the machine, which will analyse and continually cross-check data with added information (the cost and availability of inputs, weather forecasts, disease stats and so on) and take the best action based on its knowledge.
These learning machines will require a huge amount of data from multiple sensors in the field and include moisture probes that can give us information on available moisture throughout the season, sensors that can look at weather in specific areas and cameras to identify signs of plant disease.
Limiting factors include power (charging and battery life) and the need to cope with wind, rain heat and dust.
However, groups are already working to overcome these obstacles, and promising solutions include the NH Drive, from the CNH Industrial group and the Bonirob, developed by Bosch.
Artificial intelligence software, that will take this next step, allowing machines to process data, make decisions, and learn, is under development, but there is still some way to go.
By combining hardier machines, better data collection techniques and highly developed software, the next level of computer learning doesn’t appear to be too far away, and it’s easy to imagine how useful it will be to tomorrow’s farmers, facing pressures from climate change and plateauing yields to chemical resistance in weeds and pests.
Adapted from an article by Pascal Cochelin, a digital business leader, which appeared on Terre-Net.