AI is all the rage and might seem new, but the experts at Computomics have spent over a decade perfecting it for use in plant breeding.
AI is everywhere, and everyone is trying to understand where it fits into their world. AI might seem new, but it’s not. For more than a decade, Computomics has been a trusted partner for those who work within the plant breeding space, notes Managing Director Sebastian Schultheiss.
“Using AI for text and images is one thing, but implementing it in plant breeding is on an entirely different level,” he says.
“We know how to bring powerful, useful AI solutions to industry applications.”
The pace of AI tool development makes it nearly impossible for non-experts to stay informed or evaluate their effectiveness. Some plant breeders might be hesitant to implement AI because they believe they don’t have relevant data. Others could become overconfident and think that a tool like ChatGPT is going to do what a specially-designed AI platform can. Computomics has been gathering fundamental knowledge on using AI for plant breeding for over 10 years now.
“It’s easy to get started with us. With pre-trained models that understand crop growth and genetic datasets, our AI solutions are designed to seamlessly integrate with the germplasm pool that breeders have,” Schultheiss says.
Here are some key things to understand if you are trying to navigate your way through the world of AI and how it might benefit your breeding program.
- You do not need to start from scratch. Computomics delivers plant breeding-focused solutions — they’ve spent years working with breeders to hone their platforms. That’s a unique track record in this field.
- One of the biggest myths around AI tools? That technologies like ChatGPT are more advanced than previously developed technologies. “The reality is that ChatGPT is wonderful for interactions in the realm of natural language but not meant for tackling complex tables or genetic interactions,” Schultheiss says. “We have built AI models with new mathematical approaches for plant breeding that are tailored to phenotyping measurements, genetic information and gene-environment interactions.”
AI knows no borders, but in agriculture, there are special challenges, he notes.
“The biggest one, for modern breeding, is in front of us: how can we select field-ready genetic material when faced with enormous climate uncertainty? What effective, conventional breeding does best is predict how genetics behave in past conditions.”
With Computomics’AI technology, breeders can emulate future climate conditions and project plant performance in novel or untapped locations while identifying the best performers with specific genetic combinations.
“We allow breeders to make better decisions with data — both faster and from a larger pool, reducing trial-and-error and resulting in the development of crops that will actually thrive in a given set of environmental conditions. Every breeding company has their own specific germplasm pool that our models are attuned to; this is why it comes natural to us to respect our clients’ data ownership. Everyone’s data is only ever used for their own benefit.”
With Computomics’ unique AI technology, Schultheiss and his team help give plant breeders a leg up on unlocking new information concerning genotype-environment interactions (G×E), thus providing a more efficient means by which to produce climate-resilient high-yielding varieties.
“This level of precision is crucial as breeders face growing pressure to develop crops that thrive in environments, withstand extreme weather, and adapt to shifting rainfall patterns and soil conditions,” he adds.
“In the last decade, we have made big strides in our journey with AI. Early plant breeding relied heavily on statistics, often overlooking or actively ignoring environmental factors. The breakthrough came when we integrated climate data, and thus G×E, into AI models — suddenly, we could predict how different varieties would perform across specific environmental conditions.”
This opens new possibilities for breeders, allowing them to expand into previously untapped regions and maximize the potential of their germplasm pools.
“As AI continues to reshape agriculture, we want to ensure plant breeders have the right tools, technology, and knowledge to unlock its full potential,” Schultheiss says. “That’s why we’re taking the next step: harness the power of AI foundation models to boost plant breeding.”
AI foundation models are advanced AI trained on massive amounts of data, allowing them to be fine-tuned to data for specific agricultural challenges. For example, to capture intricate patterns in genetic sequences, predict plant trait performance, or to identify genetic markers linked to diseases.
Visit computomics.com/vision to learn more.
The post Beyond ChatGPT: Why AI for Plant Breeding Requires a Different Approach appeared first on Seed World.