Input Stories

The world’s leading agricultural companies are turning to artificial intelligence to help them in the war against weeds (The Wall Street Journal, subscription).

What’s going on: With many invasive plants now resistant to go-to chemical sprays, “[f]armers are turning to mixology to find the most potent weedkiller formula, and pesticide makers want to speed up what can be a yearslong process of identifying new herbicides. … [firms such as] Syngenta say new AI systems are helping speed up the lengthy, complicated and costly process of bringing new chemicals to market.”

• Syngenta—which is using machine-learning models to help it find new active pesticide ingredients—estimates that AI will slash the average discovery-to-commercialization time by one-third, or to 10 years from 15, and reduce the number of lab and field tests by 30%.
• Another large company is using an AI system that swiftly matches the protein structure of a weed to a chemical molecule that targets the structure.

Why it’s important: “Companies say an advantage of molecules selected with AI is that they can be screened during the process for toxicity to humans—a critical point for pesticides sprayed on crops people will eat—as well as environmental safety and cost.”

• Weeds have evolved in the past few decades, leaving farmers with fewer options for killing them to ensure healthy harvests.

The AI advantage: “As recently as five years ago, companies could spend a year screening hundreds of thousands of chemical compounds. … Leaning on AI to help analyze and screen chemical molecules can help shrink the process down to about two to three months and predict possible toxicity problems earlier in the development process.”

• AI “helps to address all of the challenges our industry has when it comes to chemical innovation,” said Camilla Corsi, the head of crop protection research for Syngenta.