Overuse of fertilizers is one of the biggest environmental problems produced by modern agriculture. All kinds of solutions have been proposed, from cover crops and no-till systems to buffer zones between crops and streams. New technology from Imperial College London aims to reduce the amount of fertilizer runoff by reducing the amount of fertilizer that farmers actually use.
Farmers don’t want to abuse fertilizers; it costs money, after all. But figuring out exactly how much fertilizer a given crop needs is complex and sometimes impenetrable. Fertilizer can be lost through erosion and rain. It can also be washed away before it reaches the bacteria in the soil which transform it into food for plants. It is therefore generally assumed that a certain amount of fertilizer will be lost and must be compensated for by volume, resulting in runoff, something disastrous for rivers, fish, birds, insects and habitats. native.
The study of Imperial College London, Posted in Natural food, involves creating a small sensor that detects ammonia, the chemical in fertilizer that is transformed by soil bacteria into plant food. The sensor itself is made of paper, which isn’t as odd as you might think; sensors on paper used for a few years, due to their qualities of lightness, flexibility, low cost and biodegradability.
To keep costs down, this particular sensor does not do much on its own, measuring only ammonium. But any kind of prediction of how much fertilizer will be needed requires a lot more information than that. So this system uses machine learning, a form of artificial intelligence, to incorporate ammonium levels with all kinds of other data, including temperature, humidity, rainfall forecast, soil pH, and time since the last fertilizer was applied.
By combining all of this, the system is able to provide figures that tell the farmer how much nitrogen is in the soil and how much there will be for the next 12 days. This allows him to predict exactly when, where and how much fertilizer is needed in order to minimize the amount of excess fertilizer applied.
Unfortunately, the researchers say they are about three to five years away from commercial availability. But provided the cost is low enough, this system could be an affordable way to monitor fertilizer use.