AI camera system cuts crop breeding costs by predicting potato yields
Researchers have developed a faster way to breed potatoes suited to climate change by using image analysis instead of expensive genetic tests. The method cuts breeding timelines and costs while maintaining prediction accuracy, potentially accelerating development of hardier crops for farmers facing unpredictable weather.
Originaltitel: Phenomics-assisted sparse testing for potato breeding.
**Bildanalys ökar avkastningen i potatisodling — utan dyrare gentest** SLU har utvecklat en metod som kombinerar bildbaserad växtanalys med sparsmakad provtagning i potatisförädling. Genom att mäta miljöparametrar från drönbilder och kameror kan försök utvärdera fler genotyper samtidigt som kostnaderna hålls nere. Forskarna testade flera prediktionsmodeller på flermiljöförsök. Modeller baserade enbart på miljökärnor från bilddata nådde samma eller högre träffsäkerhet än genomiska prediktionsmodeller. Störst effekt sågs för tuberkvalitet — en nyckelegenskap för avkastning. Metoden utvecklades vid SLU Alnarp och löser ett praktiskt problem för förädlingsprogram med begränsade resurser. Istället för att bara förlita sig på genotypanalys kan producenter nu använda bildövervakning för att välja bättre sorter snabbare. Det sparar tid och pengar i växtförädlingen.
In recent decades, global weather patterns have shifted dramatically, introducing greater unpredictability into agriculture. A major challenge in plant breeding is developing selection strategies that remain accurate under such uncertainty. Sparse testing is a well-established approach to increase the number of genotypes evaluated in field trials while keeping costs manageable. However, incorporating image-based data into sparse testing remains challenging. We developed a strategy to integrate high-throughput phenotyping data into sparse testing in potato breeding to improve predictive performance in multi-environment trials. Our approach involved constructing an environmental kernel derived from the covariance matrix of image-based data. We assessed the predictive performance of several regression models under sparse testing, including those based on genomic or phenomic data alone and in combination. Models using only the proposed environmental kernel achieved predictive accuracies comparable to, or exceeding, those of genomic prediction models in various sparse testing scenarios. The best results were observed for tuber yield, a key trait in potato breeding. These findings highlight the potential of image-based environmental kernels to improve the efficiency and accuracy of sparse testing. This approach is cost-effective and scalable, particularly useful for breeding programs with limited resources.