The discussion of sustainability and climate change at events such as COP28 often focuses on fossil fuels and the energy transition. Meanwhile, agriculture accounts for one-third of all global emissions but receives far less attention.
A case in point is the World Agri-Tech Innovation Summit, held in San Francisco in March, where attendees explored solutions for climate-resilient agricultural practices. In the four weeks since, the media coverage for this event has been almost nonexistent.
Why? One factor may be that the industry has an ambitious agenda not for the faint of heart: feed the world, adapt to climate change, and drastically reduce its greenhouse gas (GHG) emissions. At a time when addressing food scarcity is a top priority in parts of the world, it may seem like an intractable dilemma: reducing emissions by cutting yields would, it seems, increase food insecurity.
In truth, decarbonization and sustainability can coexist. This topic was a major focus of the event. And the conversations were set against a tense backdrop in the US—the House’s farm bill, which has been delayed by a handful of factors, including climate-related funding, is set to be unveiled by Memorial Day, May 27.
Our research shows that during the conference, many participants expressed optimism that mitigating agriculture-based emissions was doable.
“With regenerative ag practices, you can both increase productivity and restore more of the environment,” said Jeremy Williams, head of Climate LLC, digital farming, and commercial ecosystems for the crop science division of Bayer.
The traditional approach of the agrifood industry is set to be disrupted in the coming years with the boom of new technology. The challenges of producing enough food to feed the growing world in a way that reduces waste and energy consumption continue to accelerate as fast as the human population grows.
According to one analysis, using sustainable artificial intelligence (AI) solutions such as precision farming, machine learning algorithms, and other AI technologies to replace conventional farming methods can cut GHG emissions by up to 25 percent. With the help of AI, farmers can improve their crop yields, make adjustments ahead of the growing season thanks to early identification of weather patterns, reduce waste, and, ultimately, increase the profitability of their yields.
As such, the conference featured much discussion of trends in innovation in agriculture, including the potential use of gene editing to develop new crops.
In our view, three agriculture AI innovations stood out:
Expert systems
Programs falling under an “expert system” represent “if–then” rules. The program can capture the knowledge of skilled human experts in the form of specific rules. For example, if the moisture level of your soil is under a certain percentage, then turn on the water pump. Expert systems help in selection of crop or variety; diagnosis or identification of pests, diseases, and disorders; and making valuable decisions about the crop’s management. This technology addresses the problem of transferring knowledge and expertise from highly qualified specialists to less knowledgeable personnel. Ninety-eight percent of the world’s agricultural workers are employed in developing countries, according to the International Labour Organization. Technology is key in supporting the agricultural industry in developing countries, where expertise about the ever-changing climate is scarce. It is important when thinking about our global food supply chain to provide farmers in lower-income countries with the tools needed to predict weather patterns and make informed decisions about their crop yields.
Computer vision
Computer vision and sensing enables vehicles such as tractors, combines, and sprayers to collect data across fields, while AI can process the data “on the backend so we can provide the right data science and insights to our farmers so that they can actually drive profitability on the farm,” said Marc Kermisch, global chief digital and information officer of CNH Industrial.
Machine learning
Imitating the human learning process of “learning by example,” machine learning trains computers or machines by exposing them to sample data repetitively to find patterns using algorithms. For example, farms could use machine learning to understand price fluctuations when selling crops and manage risks from variables such as demand and climate change.
But there’s no one technology that will address all the decarbonization and sustainability issues facing agriculture, USDA under secretary Robert Bonnie pointed out during the conference. “This isn’t going to be a silver bullet—it’s going to be silver buckshot. We need innovations on the methane side to reduce methane emissions in livestock, on the nitrous oxide side, on the fertilizer front. We need new biologics to think about soil carbon. We’re going to need them all,” he said.
Agriculture embodies an apparent contradiction: it is undoubtedly one of the industries most vulnerable to the effects of climate change while being one of the biggest contributors to global emissions. Information presented at the World Agri-Tech Summit is cause for optimism: technology may hold the key to solving the climate crisis and food insecurity simultaneously.
Now the challenge is to mobilize elected officials, policymakers, and industry leaders to ensure solutions get implemented on the ground. We at LEFF are committed doing our part to promote these advances through communications and storytelling.
