SDSU Builds AI Tool to Read Wheat Traits

South Dakota State University researchers are developing WheatAI, a free web application that analyzes wheat characteristics from photos.

Updated on Nov. 13, 2026 in Botany

Wide photograph of a mature wheat field under low golden sunlight on the South Dakota prairie, with long shadows and an open sky.
South Dakota State University researchers are developing WheatAI, a free web application that analyzes wheat traits from photos, with a planned 2028 public release. AI Illustration. Upload story photo >

Live Poll

Do you think AI tools for farming will mostly benefit everyday food buyers?

South Dakota State University researchers are developing WheatAI, an AI-powered web application for wheat phenotyping. The platform is planned for public release at wheatai.net in 2028 at no cost.

Why it matters

Manual wheat phenotyping is subjective and slow, limiting how many samples researchers can evaluate. The tool aims to reduce that subjectivity and help farmers make earlier, more accurate crop assessments.

The platform currently analyzes nine plant characteristics, with 10 to 12 more traits planned before release. Its accuracy for yield estimates and Fusarium detection has not been reported.

The players

South Dakota State University

A public land-grant university in Brookings, South Dakota, with seven colleges and extensive agricultural research programs.

Sunish Sehgal

An SDSU professor and wheat researcher who previously was a research scientist at Kansas State before joining SDSU in 2014.

The details

Professor Sunish Sehgal began taking photos in 2022 to develop the tool, and in 2025 he and Maitiniyazi Maimaitijiang began building a working prototype. The model was built from smartphone and drone images of winter wheat taken at SDSU research farms near Pierre and Brookings and producer fields in Winner and Hayes.

Timeline

  1. 2022: Sehgal begins taking photos to develop the AI tool.

  2. May to July: Winter wheat images are collected five times for the platform.

  3. 2025: The team begins developing a working prototype.

  4. 2028: WheatAI is tentatively scheduled for public release.

The Big Picture

WheatAI automates wheat trait measurement that breeders have traditionally done by hand in field trials, aiming to reduce subjectivity and raise sample throughput. Its planned 2028 release would move image-based phenotyping from university labs toward everyday farm use.

Farmers and researchers in South Dakota could eventually use a free app to estimate wheat yield and disease risk from smartphone or drone photos. Earlier, more accurate crop assessments could support decisions about wheat fields before harvest.

The takeaway

AI-based image analysis may soon make wheat trait measurement faster and less subjective. Farmers and researchers should watch for the 2028 public release and its accuracy results.

Further reading

Explore more Botany coverage on crop traits and plant research.

More information

Visit the WheatAI wheat phenotyping web application for details on the platform.

Live Poll

Do you think AI tools for farming will mostly benefit everyday food buyers?