“We create new crops five times faster”

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

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

Based in Idaho, the company sources wheat from farmers throughout the US Pacific Northwest.

As the weather becomes more unpredictable, Mr. Bunch says, “I need to have a plan B and a plan C in case plan A fails.”

To power these plans, Mr. Bunch’s company now uses an artificial intelligence software system called ClimateAi.

Using current and past data, such as satellite imagery and temperature and precipitation data, and combining it with future projections, ClimateAi aims to provide farmers with the most accurate, locally tailored weather forecasts one hour to six months ahead.

It then advises when exactly to plant and harvest specific crops and predicts their yields.

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

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

“Looking ahead to the weather helps our growers decide which crops to plant. The platform knows when to plant and when the crop will flower and produce seed.”

One of the biggest challenges facing the seed industry is how to get climate-resilient seeds to market faster and cheaper, says Himanshu Gupta, CEO of San Francisco-based ClimateAi.

“By the time some seed companies do that, say 10 to 15 years from now, the climate will have already changed,” says Mr Gupta. “We are running against time to bring new seed varieties to market.”

He says ClimateAi helps these firms see how specific test seeds performed in a specific region or location. “This can help seed companies figure out the optimal places to grow seeds.”

Last year, a study published in the scientific journal Nature warned of the potentially dire consequences of multiple crop failures occurring at the same time around the world due to the impact of climate change.

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

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

With increased pressure on crops and as the world’s population continues to grow, could artificial intelligence be the key to developing new varieties that can better cope with extremes of weather?

In Arusha, Tanzania, David Guerena, an agricultural scientist at the International Center for Tropical Agriculture, leads a project called Artemis.

Funded by the Bill and Melinda Gates Foundation, this uses artificial intelligence to breed more resistant crops. Specifically, AI helps speed up a job called phenotyping.

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

“Traditionally, it takes about 10 years to develop a new crop variety,” explains Mr. Guerena. “But given the pace of climate change, that time frame is no longer viable.”

He adds that phenotyping work has traditionally relied on the human eye. “However, people do not do this consistently, with the high level of precision necessary to make subtle but important plant selections,” says Mr Guerena.

“It can be over 30°C in the field. It’s just tiring, and tiring affects data quality.”

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

“Computers can count every flower or pod, from every plant, every day without getting tired,” says Mr. Guerena. “This is really important because the number of flowers in beans correlates with the number of pods, which directly affects yield.

“Data can be so complicated to understand what’s going on, but AI can be used to make sense of complex data and get patterns, show where we need resources, show recommendations.

“Our breeders estimate that with better AI computer vision data, they may be able to shorten the breeding cycle to just a few years.”

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

“Our process starts with genomic data about crops, such as the sequences of different varieties,” says Rebecca White, Avalo’s COO.

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

Using their technology, they were able to create broccoli that matures in the greenhouse in 37 days instead of the standard 45 to 60 days, Ms. White says.

Broccoli produced in this time frame can get additional growth cycles and saves the carbon footprint and improves the environmental impact.

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

“Our core technologies can identify the genetic basis of complex traits with minimal training and use sequencing and predictive analytics to quickly and cheaply assess and model new plant varieties,” says Ms White.

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

But while AI can help mitigate the impact of climate-related weather and increase crop resilience, there are a number of challenges when it comes to using AI in agriculture, says Kate E Jones, professor of ecology and biodiversity at University College London.

“The effectiveness of AI in ensuring food security also depends on addressing issues such as data quality, technology availability… while recognizing that AI is one of many tools in a comprehensive strategy for sustainable and resilient agriculture.”