“This summer, India’s Ministry of Agriculture oversaw an impressive real world trial of AI-powered weather forecasts. The project sent weekly monsoon predictions to 38 million farmers using an AI model. During the trial, this new AI system accurately predicted an unusual 20-day dry spell weeks before it happened—something none of the conventional systems managed to do,” reports The Doomslayer.
A sustainability website explains:
One of the most promising prospects for artificial intelligence (AI) is in weather forecasting…a key barrier for low-income countries is a lack of funds….Weather forecasts are important to almost everyone, but they can make a huge difference to farmers (which is the majority in low-income countries) as they guide them on when and what to plant. A good forecast could be the difference between a great harvest and none at all.
[AI] has the potential to not only improve the accuracy of forecasts but also to run them more quickly and efficiently. That then makes them better and cheaper….a huge trial in India this year has taken a huge step forward. The Indian Ministry of Agriculture partnered with teams of scientists…They sent weekly AI-powered forecasts about the monsoon to 38 million farmers across 13 states in India. These AI forecasts predicted changes in the monsoon that all other ones missed. The forecasts of the timing of the monsoon were sent up to four weeks in advance of its arrival; conventional physics-based modelling usually can’t do it more than five days in advance.
This year’s monsoon was a weird one. It hit Southern India in early June (which the AI model predicted), but then stopped temporarily for 20 days. No conventional model predicted this stall, but the AI-based one did…This information can make a huge difference to farmers. Knowing that the monsoon would stall for three weeks meant that farmers could delay their planting to take advantage of the rain or choose to plant a different crop. In a self-reported survey, around one-quarter of the 38 million farmers adjusted their plans in response to the forecast.
Artificial intelligence is also helping African farmers. Kenyan farmers have substantially increased their harvests and reduced fertilizer costs, by using a chatbot with artificial intelligence to advise them about things like how much fertilizer to use. This artificial intelligence tool yields much more accurate information than advice from government agricultural extension offices. It also yields faster, cheaper results than sending soil samples to distant private soil labs. Kenyan soil labs can take months to provide farmers with test results, leaving farmers in the dark as they make critical decisions about planting and fertilizer use.
The impoverished African nation of Zambia has used artificial intelligence to find new mineral wealth.
Artificial intelligence is also greatly improving the detection of many different diseases. Artificial intelligence has discovered a new material that could reduce lithium use in batteries and thus reduce our dependence on China. Artificial intelligence is outperforming radiologists in detecting prostate cancer. Artificial intelligence is also being used to generate highly-effective antibodies to fight disease. Doctors overseas are using artificial intelligence to detect cases of breast cancer more effectively.
Robots with artificial intelligence are spreading on Japanese farms. In the U.S., farming robots now use artificial intelligence to kill 100,000 weeds per hour. Drones with artificial intelligence will make farming easier.
