AI cracks the code for faster, better crops

In the vast, sun-drenched fields of Yazhou Bay in Sanya, Hainan province, a quiet but monumental shift is taking place. Here, the practice of crop breeding is being rewritten not with a hoe, but with computer algorithms.

For generations, developing a superior seed variety was often an inexact science — a decade-long pursuit often relying heavily on a breeder's hunch. Now, a new initiative powered by artificial intelligence promises to slash that timeline in half, aiming to deliver resilient, high-yield crops in just three to four years.

Officially known as the Future Agriculture Nexus, or Fan, the project is a joint creation of the Yazhou Bay National Laboratory and Chinese tech company Huawei Technologies Co. The hub aims to transform breeding into a precise, predictive science — a critical move for a nation safeguarding its food security in an era of climate uncertainty.

The goal is in line with China's strategic needs, with seeds seen as the "chips" of global agriculture.

During an inspection of the Yazhou Bay laboratory in April 2022,President Xi Jinping stressed the importance of pursuing agricultural technological breakthroughs to achieve self-dependence in the seed sector. "We should rely on Chinese seeds to ensure China's food security," he said.

Yuan Xiaohui, a senior scientist at the Yazhou Bay National Laboratory, said that "as the only national-level laboratory in China's agricultural sector, our lab's mission is to develop major strategic crop varieties to meet real demand".

"We are fully aware that AI holds immense potential to empower agricultural science, but data remains the core bottleneck hindering its practical application," Yuan said.

"There is an urgent need for us to build a system capable of integrating global field and laboratory data while providing intelligent analytical capabilities."

Chen Fan, deputy director of the laboratory, outlined the fundamental shift required.

"Traditional breeding work relies heavily on experience. Moving from traditional to precision breeding requires analyzing correlations between massive amounts of data on crop traits and genotypes," Chen said.