A major review published in the prestigious journal Nature in July highlights how artificial intelligence and biotechnology have the potential to revolutionize global crop production — strengthening food systems against climate change, pests, and growing populations.
An international team of researchers from China, the U.S., and Europe, including Aberystwyth University, has outlined a roadmap for combining AI with genome editing, protein design, high-throughput phenotyping, and omics technologies that analyze plants’ genetic and chemical profiles.
They argue that using these advanced methods could speed up the development of crops that are more productive, sustainable, and resilient to climate challenges — and might even enable the domestication of entirely new crops, according to a press release.
“Think of it like designing and building a bridge,” Professor John Doonan, Director of the National Plant Phenomics Centre at Aberystwyth University’s Institute of Biological, Environmental and Rural Sciences (IBERS), said. “We now have the tools to engineer crops with similar precision — combining biological insights with AI to build plants that can withstand drought, disease, and other stresses.”
The review highlights how AI can:
- predict the best combinations of genes for yield, nutrition and stress tolerance
- design novel proteins to enhance plant defences and performance
- integrate very complex datasets to guide smarter, faster breeding decisions
“This is about building resilience into our crops from the ground up,” Doonan said. “By uniting AI with cutting-edge biotechnology and sustainable farming practices, we can future-proof food production for generations to come.”
The work aligns with IBERS’ strategic focus on resilient crops and was supported by the Biotechnology and Biological Sciences Research Council (BBSRC) through its Resilient Crops programme, and by the Engineering and Physical Sciences Research Council (EPSRC) as part of its AI for Net Zero initiative.
The review is published in full in Nature : https://doi.org/10.1038/s41586-025-09122-8
