Evaluation and prediction of the physical properties and quality of Jatobá-do-Cerrado seeds processed and stored in different conditions using machine learning models

The conservation of seed quality throughout storage depends on established conditions, monitoring, sampling and laboratory analysis, which are subject to errors and require technical and financial resources. Thus, machine learning techniques can help optimize processes and obtain more accurate results for decision-making regarding the processing and conservation of stored seeds. Therefore, the aim was to assess and predict the physical properties (moisture content, seed mass, length, thickness, width, volume, apparent specific mass, projected area, sphericity, mean diameter, circular area, circularity, drag coefficient), and physicochemical quality (crude protein, ash content, and acidity index) of Jatob & aacute;-do-Cerrado seeds under different processing conditions with pulp, without pulp (scarification), without pulp (fermented), and storage conditions at 10 and 23 degrees C over six months. Data were analyzed on Weka software (Waikato Environment for Knowledge Analysis) version 3.9.5. testing the following models: Pearson correlation, Artificial Neural Networks, decision tree algorithms RepTree and M5P, Random Forest, and Linear Regression. Processing cerrado jatob & aacute; seeds by fermentation and storage at 10 degrees C minimized physical changes and preserved the physicochemical quality of the seeds in polyethylene plastic, glass container, tetrapack, and polyethylene container, over six months. The combination of processing, temperature, and packaging variables for Artificial Neural Networks, RepTree, Random Forest, and M5P algorithms outperformed linear regression, providing higher accuracy rates. Artificial Neural Network and Random Forest models were the best predicting the effects of treatments on changes in physical properties and physicochemical quality of jatob & aacute; seed.