A new promising tool is helping to parse through thousands of images to predict the health and yield of crops, sparking optimism that less wasteful and more sustainable agricultural practices could be within reach.
As detailed by Anthropocene, researchers at the University of Bonn developed their data-cruncher with a machine-learning algorithm, or artificial intelligence.
The AI processed more than 100,000 images of crops at various stages of growth, and it learned how to identify crop traits associated with future yields as well as understand growth patterns over time.
The findings, published in the journal Plant Methods, could help support an agricultural industry impacted by the effects of changing global temperatures.
According to the U.S. Department of Agriculture, pests already account for 20% to 40% of crop production loss worldwide. However, warmer temperatures have contributed to increased infestations. Extreme weather events, like prolonged droughts and heavy rains, are also on the rise and have become more severe.
This leaves farmers searching for solutions to protect their livelihoods and support the global food supply. Oftentimes, that means expensive synthetic fertilizers (whose excess runoff can contribute to toxic algae blooms) and chemical pesticides (which contain toxins, the WHO states).
New technologies and scientific discoveries are expected to contribute to creating a more climate-resilient, food-secure future. Scientists have also been experimenting with plant-based alternatives (which can provide plenty of health benefits) to reduce planet-warming pollution and support a growing global population.
University of Bonn doctoral student Lukas Drees, the study's lead author, believes his team's AI tool can be another crucial piece of the puzzle. It could assist with the timing of harvests to ensure maximum yield for both the farmers' laborers and their crops.
"This makes it possible to negotiate fair prices and minimize food waste, both of which contribute to sustainability," Drees explained to Anthropocene.
The World Wildlife Fund estimates that around 1.4 billion tons of food is lost as waste every year in the U.S., and about 16% of that happens right on the farms. As it decomposes, food waste releases gases like methane, contributing to the overheating of the planet.
Drees also said that the algorithm could help farmers decipher the best areas to administer fertilizers, pesticides, and irrigation — nipping potential crop issues in the bud before they advance further and reducing the potential for harmful nutrient runoffs.
While the potential applications show promise, further research and investigation are now needed to refine and fill in gaps in the AI's modeling, according to the study.
Join our free newsletter for weekly updates on the latest innovations improving our lives and shaping our future, and don't miss this cool list of easy ways to help yourself while helping the planet.
Cool Picks
