Sadly, today’s agricultural research is often disseminated in a way that makes reviewing it a time-consuming process. This obviously slows down innovation. However, it has even more dire consequences for those suffering from malnutrition and hunger.
With the help of artificial intelligence (AI) and machine learning, researchers were able to comb through more than 500,000 studies. They found that there are several ways to make huge strides in this decade to combat the hunger crisis. However, the process wasn’t perfect and left out some important factors.
Nonetheless, the use of AI in this instance shows that technology has a far-reaching impact on the world—especially when it comes to problem-solving.
The research team for this project consisted of 70 scientists. Together, they published eight studies across the journals Nature Food, Nature Plants, and Nature Sustainability.
Reviewing the mountains of scientific literature emerging today is a monumental task. Doing so manually takes months or even years. In fact, the pace of today’s research is so staggering that humans are struggling to translate new discoveries into true knowledge and real-world applications.
The use of AI helped researchers cut down on the amount of time a literature review takes so that they can focus on applying the findings. They trained several unspecialized algorithms to examine 500,000 documents regarding agriculture and development. It took the systems one week to compile datasets that were actually useful. The analysis helps clarify which areas stand to benefit the most from financial aid.
Maximo Torero is the chief economist at the UN’s Food and Agriculture Organization. He says, “The world produces enough food to feed everyone. So it’s unacceptable that 690 million people are undernourished, 2 billion don’t have regular access to sufficient amounts of safe, nutritious food, and 3 billion people cannot afford healthy diets.”
“If rich countries double their aid commitments and help poor countries to prioritize, properly target and scale up cost-effective interventions on agricultural R&D, technology, innovation, education, social protection and on trade facilitation, we can end hunger by 2030,” Torero adds.
That’s a powerful statement considering that the UN hasn’t made much progress on its goal of ending world hunger. In fact, the number of people experiencing hunger has increased by 60 million in the past five years.
Although the AI-driven analysis that researchers carried out shows ways that world hunger can be addressed, it isn’t foolproof. A human-led review process found that the algorithms didn’t look at factors like gender and income. Those are obviously key metrics that affect the world’s hunger problem.
Moreover, few of the studies in the pool account for nutrition and instead look at crop yield. Although yield is certainly important, it means nothing if the food being grown isn’t nutritious. In some cases, less food is necessary if it provides more nutrition than a crop with little value.
It will be important to take these things into account when analyzing the data of these machine learning studies. Perhaps researchers can train new algorithms that consider things like gender, income, and nutrition. If so, AI could become an even more powerful tool in the fight against hunger.
If the world aims to eliminate hunger by 2030, as Torero suggests, those innovations will need to happen quickly.