“We are creating new cultures five times faster” – BBC News

Like the bosses of many agri-food companies, Jeremy Bunch is worried about the impact of climate change on his business.

“Weather and climate are perhaps the number one risk for our business,” says the boss of the American flour company Shepherd’s Grain.

Based in Idaho, the company sources its wheat from farmers in the U.S. Pacific Northwest.

As weather conditions become more and more unpredictable, Mr. Bunch says, “I need a plan B and a plan C, in case plan A fails.” »

To help bolster these plans, Mr. Bunch’s company is now using an AI-based software system called ClimateAi.

Using current and past data, such as satellite images and temperature and precipitation records, and combining them with future projections, ClimateAi aims to provide farmers with the most accurate weather forecasts possible, tailored to local conditions, from one hour to six months in advance.

It then tells exactly when to plant and harvest certain crops, and predicts their yields.

Shepherd’s Grain only started using ClimateAi last year, but most of its more than 40 farmers are now guided by the app.

“They are starting to look to ClimateAi to help them plan management decisions for wheat, the main crop grown in the region,” says Bunch.

“A forward-looking view of the weather helps our growers decide which crops to plant. The platform knows when to plant and when the crop will start flowering and producing seeds.

One of the biggest problems facing the seed industry is how to bring climate-resilient seeds to market more quickly and affordably, says Himanshu Gupta, chief executive of San Francisco-based ClimateAi.

“By the time some seed companies do this, say in 10 to 15 years, the climate has already changed,” says Gupta. “We are racing against time to launch new seed varieties. »

He says ClimateAi helps these companies see how specific tested seeds perform in a particular region or locality. “This can help seed companies determine optimal locations for growing seeds.”

Last year, a study published in the scientific journal Nature warned of the potentially disastrous consequences of numerous crop failures occurring simultaneously around the world, due to the impact of climate change.

“Simultaneous harvest failures in major crop-producing regions pose a threat to global food security,” says the report, led by climate scientist Kai Kornhuber of Columbia University’s Lamont-Doherty Earth Observatory.

This warning comes as the world’s population is expected to reach 10 billion people by 2050, up from eight billion currently, according to the United Nations.

With increased pressure on crops, even as the world’s population continues to grow, could AI be the key to developing new varieties that can better cope with extreme weather conditions?

In the city of Arusha in Tanzania, David Guerena, an agronomist at the International Center for Tropical Agriculture, leads a project called Artemis.

Funded by the Bill and Melinda Gates Foundation, this project uses AI to help produce more resilient cultures. Specifically, AI helps speed up work called phenotyping.

It is the visual study of new crop varieties based on observation of their characteristics, such as the number of flowers, pods or leaves on a plant.

“Traditionally, it takes about 10 years to develop a new plant variety,” explains Mr. Guerena. “But given the pace of climate change, this timeline is no longer sustainable.”

He adds that phenotyping work has traditionally relied on the human eye. “But humans simply don’t do it consistently, with the high levels of precision needed, to make subtle, but important, plant selections,” says Guerena.

“It can be over 30°C on the pitch. It’s just tiring, and fatigue affects data quality.

Instead, growers involved in the project take photos of their crops via a smartphone app. The trained AI can then quickly analyze, record and report what it sees.

“Computers can count every flower or pod, every plant, every day without getting tired,” explains Mr. Guerena. “This is really important because the number of flowers in bean plants correlates with the number of pods which directly influences yields.

“The data can be very complex to understand what’s going on, but AI can be used to make sense of this complex data and detect patterns, show where we need resources and make recommendations.

“Our plant breeders believe that with the best data from AI computer vision, they might be able to shorten the breeding cycle to just a few years.”

In North Carolina, Avalo is an agricultural technology or “agri-tech” company that also works to create climate-resilient crops. It does this by using AI to study the genetics of a crop.

“Our process starts with crop genomic data, such as the sequences of various varieties,” explains Rebecca White, Avalo’s director of operations.

“For example, with different tomatoes, there are small differences in the genomes that give them different characteristics, for example different flavors, pesticide resistance profiles. Our machine learning program is able to take into account these small differences between a number of varieties and see which genomes are important for which traits.

Using their technology, they were able to create broccoli that matured in a greenhouse in 37 days instead of the usual 45 to 60 days, White said.

“Broccoli produced on this time scale can benefit from additional growing cycles, resulting in a reduced carbon footprint and improved environmental impact.”

Avalo, which works with companies in Asia and North America, is also working to make rice frost-resistant and potatoes more drought-tolerant.

“Our core technologies can identify the genetic basis of complex traits with minimal training and, through sequencing and predictive analytics, quickly and cost-effectively evaluate and model new plant varieties,” says White.

“We are creating new varieties for diverse crops that grow five times faster and at a fraction of the cost compared to traditional breeding. »

However, while AI can help mitigate the impact of climate-related weather and improve crop resilience, its use in agriculture poses a number of challenges, says ecology professor Kate E Jones and biodiversity at University College London.

“The effectiveness of AI in ensuring food security also depends on the need to address challenges such as data quality, technology accessibility… while recognizing that AI is one tool among many in a global strategy for sustainable and resilient agriculture. »