AI-powered drone imaging identifies resilient wheat varieties

AI News


Increasing wheat resilience to climate change without compromising yields has become an urgent priority for the agricultural sector. Now, research led by a research team from the University of Barcelona and the Agrotechnio Research Center has identified an innovative way to address this challenge. It combines advanced technology and artificial intelligence to select the best varieties of this crop.


Research published in journals plant phenomicssuggests a shift in perspective that requires focusing not only on yield, but also on the ability of wheat to maintain consistent yields despite changing weather conditions. The findings show that this combination of productivity and stability is key to ensuring safe harvest under fluctuating environmental conditions.

The authors of the study are researchers Jara Jauregui, José Luis Araus, and Shawn Carlisle Kefauver from the Department of Evolutionary Biology, Ecology, and Environmental Sciences in UB’s School of Biology and Agriculture. Nieves Aparicio and Sara Álvarez from the Agricultural Technology Institute of Castilla and León (ITACyL) and Maria Teresa Nieto from the National Institute of Agriculture and Food Research and Technology (INIA-CSIC).

Drone for monitoring wheat crops

The researchers analyzed 64 varieties of durum wheat grown under two different Mediterranean conditions: irrigated and rainfed. The aim was to identify which genotypes combine high yield and stable performance under different environments, including differences in temperature and water availability.

One of the most surprising findings was that the varieties chosen were not those that retained their green leaves the longest until the end of the season, but rather those that grew actively at the beginning of the season and matured slightly earlier.

In contrast, rejected lines had lower initial vigor and retained green leaves longer, but this does not guarantee better yields.

As part of the project, the team used ground sensors and drones equipped with RGB, multispectral, and thermal cameras to enable them to monitor crop growth throughout the growing cycle. This technology provides critical information about wheat before harvest, eliminating the need for harvesting and reducing both the cost and time required for analysis.

Using all this data, the team trained an artificial intelligence model that can predict both yield and production stability for different varieties with high accuracy.

This strategy could be a very useful tool for plant breeding programs and could help develop wheat varieties better equipped to meet the challenges of climate change.

Being green doesn’t always mean good

The researchers first analyzed the yield and stability characteristics of durum wheat separately. They found that the highest yielding genotypes were characterized by high initial vigor and persistent green color during the rapid growth phase until the end of the growing season. In contrast, the most stable genotypes have lower initial vigor, slower growth, and shorter cycles, allowing them to better utilize available resources for grain production. To identify the balance between these compensatory mechanisms, experts have developed cultivar selection methods that combine competitive yield with good stability.

This study concludes that vigorous early growth combined with early ripening is a key factor to help wheat cope better with drought and high temperatures and achieve more stable yields under fluctuating environmental conditions.

reference: Jauregui-Beso J, Aparicio N, Alvarez S et al. Multisensor phenotyping of yield and yield stability for genotype selection in durum wheat. plant phenomics. 2026;8(1):100178. doi: 10.1016/j.plaphe.2026.100178

This article has been reprinted from the following material: Note: Materials may be edited for length and content. Please contact the citation source for details. You can access our press release publishing policy here.



Source link