MACHINE LEARNING MODELS FOR PREDICTING MECHANICAL DAMAGE, VIGOR AND VIABILITY OF SOYBEAN SEEDS DURING STORAGE

ABSTRACT

Artificial Intelligence has been widely applied in data prediction for better decision making and process optimization. In the post-harvest, the control of biotic and abiotic factors is fundamental for the conservation of seed quality. Meanwhile, the tetrazolium test has been used to evaluate seed quality, however, with several limitations that can lead to evaluation errors. Thus, machine learning models can be an alternative to predict the quality of soybean seeds, with gains in the speed of obtaining results in relation to laboratory analysis methods, making the processes more robust and with low operational cost. With this, the aim of this study was to identify the best machine learning model for predicting mechanical damage, vigor and viability of soybean seeds during storage, depending on different conditions (10, 15 and 25 ºC), packaging (with coating and uncoated) and storage times (0, 3, 6, 9 and 12 months). M5P decision tree (M5P) and Random Forest (RF) models showed the best performance for predicting seed vigor (r = 0.75 and MAE = 10.0), and viability (r = 0.85 and MAE = 5.1), and mechanical damage to seeds (r = 0.64 and MAE = 11.2). It was concluded that the Random Forest (RF) model was the one that best predicted the results of soybean seed quality, with a more simplified and agile analysis for the development of vigor and viability of soybean seeds in storage.

artificial intelligence; postharvest; storage packaging; storage temperature; storage time; tetrazolium test