Applications of Machine Learning in Breeding for Stress Tolerance in Maize

ORNELLA, L; CERVIGNI G D L; TAPIA, E

Crop Stress and its Management: Perspectives and Strategies

Springer

Año: 2012; p. 163 - 192

Corn is one of the world?s most important cereals and a major source ofcalories for humanity, along with rice and wheat. Climate change and the use ofmarginal land for crop production requires the development of genotypes adaptedto stressful environments, particularly drought tolerant plants. Among the new tech-nologies currently available for accelerate the releasing of new genotypes there isan emerging discipline called Machine Learning (ML). A primary goal of ML algo-rithms is to automatically learn to recognize complex patterns and make intelligentdecisions based on data. This work reviews several strategic applications of ML inmaize breeding. Quantitative trait loci mapping, heterotic group assignment and thepopular genome-wide selection are some of the key areas currently addressed by theliterature. Results are encouraging and propose ML algorithms as a valuable alter-native to traditional statistical techniques applied in maize, even the more recentlyintroduced linear mixed models.