Artificial intelligence is guiding plant breeding — helping to accelerate the development of crops that scientists hope will be better able to weather devastating drought and heat.
Why it matters: Droughts in China, Europe, East Africa and North America are damaging crops and contributing to food insecurity and hunger crises around the world.
- Parts of the American corn belt are experiencing extreme or exceptional drought. In Nebraska, 35% of the corn crop is considered to be in poor or very poor condition.
- Some of these prolonged droughts are being caused by human-caused climate change, while others are being exacerbated by it – but all together they are a window into the drier and hotter future forecast in some regions.
- These climate changes and growing global food insecurity are putting pressure on growers to develop more resilient crops faster.
What’s happening: Machine learning algorithms and other AI tools have been used by some companies for about a decade, but they are becoming more and more available to growers.
- Growers use them to analyze data that reflects what is known about plant biology — for example, how tall or fast a plant grows and whether it can withstand hot or dry conditions in a region.
- This data can help AI predict the combinations of genes — and the genes that regulate them — that can improve a plant’s tolerance without reducing yield.
- Instead of crossing plants over generations to find the most suitable ones, breeders can use AI to more quickly predict which genetics will produce the desired traits.
There are some compromises between how much water a plant uses and how much grain, corn or other produce a plant can produce – and discuss how far growers can go with each.
- AI can “help breeders navigate this complex maze,” says Charlie Messina, a professor of predictive breeding at the University of Florida.
Details: In a recent study, Messina and his colleagues examined how drought-tolerant corn hybrids bred using AI grew under different water conditions.
- Contrary to previous research, they report that the hybrids bred for better drought tolerance had better yields. (The hybrid is commercially available from Corteva, and company scientists participated in the study. Messina previously worked for the company.)
- The scientists also found that the hybrid plants showed less difference in yield under normal and dry conditions, meaning they produced a more reliable amount of corn under different conditions. One of the challenges of climate change is hydrological extremes, which amplify both droughts and heavy rains.
But, but, but… A study published earlier this year found that increases in corn yields are largely due to climate and improved soil and crop management, not crop genetics.
- “This is an important debate because it can influence public and private investment in technologies to address drought and climate change,” says Messina.
- “If we don’t find the root cause of the problem, we as a society may be investing in the wrong solutions,” he says.
Potatoes are another staple all over the world – and the plants are very sensitive to heat.
- AlphaFold, a deep learning system developed by DeepMind that can predict the structure of proteins, was used along with other tools to study the genes and proteins involved in how potatoes respond to elevated temperatures. (The founders of AlphaFold today won the Breakthrough Prize in Life Sciences.)
The big picture: Genetics is only one factor in a crop’s yield and resilience.
- There is also the environment of a field and how the soil and water are managed and possibly tailored to a crop.
- Farmers are under their own pressure to produce a certain amount of crop and may be strained for resources.
Messina tells his destination is to integrate information about the genetics of a plant, the environment of a field and the management of a crop.
- Ultimately, he wants to “move from thinking about drought tolerance in a crop to thinking about crops as systems to combat climate change and improve nutrition and food security.”