How AI Will Help Feed the World
If the predictions of the UN’s Food and Agricultural Organization (FAO) are to be believed, the population of our blue planet is set to reach 9.2 billion by the year 2050.
Currently, we are already touching the limits of available acreage for planting crops and breeding cattle. Estimates indicate that we only have as little as 4% available land for agriculture to potentially expand into. So, obviously, we will not be able to feed more mouths by adding more farmland.
Instead, we need to process the land we have more efficiently in order to achieve higher yields. In a field trial in 2017 run by the organization ICRISAT, AI was selected as a means to help farmers work more productively.
Typically, farmers plant their crop of groundnut during the first week of June, following traditional agricultural wisdom. However, variations in the weather conditions in recent years have led to unpredictable monsoons – the key source of irrigation for the crop. In this trial, while AI crunched the numbers in the cloud, various data sources were simultaneously drawn upon which included for instance historical rainfall patterns. Further innovations were monitoring real-time weather conditions to advise the farmers on the risk of pest attacks. All these AI calculated results and recommendations were sent to the farmers through a simple automated voice call to their mobile phones or via a sms.
The outcome was incredible! In total, the farmers participating averaged yields some 30% higher than those not on the scheme.
Here’s another example: A high-tech solution for improving the yield of tomatoes has been trialed on six farms in the United States and Mexico. The Israeli farming company Prospera has been testing out their camera-based AI solution in the greenhouses of NatureSweet. The cameras are designed to detect insect infestations or even dying plants. Typically, such work was undertaken by employees, but it was difficult to accurately identify struggling plants.
While the employees could only manage to undertake a full analysis of their greenhouses once per week, the camera system operates 24 hours a day, seven days a week. The cameras are also being trialed to detect the optimal harvest time for the crop. Since its introduction, weekly harvests have grown by 2% – 4%.
Regardless of whether it is integrated into greenhouses or running in the cloud sending text and voice messages to mobile phones, AI does seem capable of helping us farm smarter rather than just harder.