Predicting the quality of soybean seeds stored in different environments and packaging using machine learning

Abstract

The monitoring and evaluating the physical and physiological quality of seeds throughout storage requires technical and financial resources and is subject to sampling and laboratory errors. Therefore, machine learning (ML) techniques could help optimize the processes and obtain accurate results for decision-making in the seed storage process. This study aimed to analyze the performance of ML algorithms from variables monitored during seed conditioning (temperature and packaging) and storage time to predict the physical and physiological quality of stored soybean seeds. Data analysis was performed using the Artificial Neural Networks, decision tree algorithms REPTree and M5P, Random Forest, and Linear Regression. In predicting seed quality, the combination of the input variables temperature and storage time for REPTree and Random Forest algorithms outperformed the linear regression, providing higher accuracy indices. Among the most important results, it was observed for apparent specific mass that T + P + ST, T + ST, P + ST, and ST had the highest r means and the lowest MAE means, however, Person's r coefficient for these inputs was 0.63 and the MAE between 9.59 to 10.47. The germination results for inputs T + P + ST and T + ST had the best results (r = 0.65 and r = 0.67, respectively) in the ANN, REPTree, M5P and RF models. Using computational intelligence algorithms is an excellent alternative to predict the quality of soybean seeds from the information of easy-to-measure variables.

Monitoring and predicting corn grain quality on the transport and post-harvest operations in storage units using sensors and machine learning models

“…Some authors have reported that, during serial reactions in the grain mass, oxidations of grain constituents occur, which consequently leads to losses of total carbohydrates, starch, proteins, and oils 70 . In research on grains stored in different packages, André et al 25 found that the ANN, M5P and RF models can be used to predict the apparent specific mass, supporting our results. Even though the ANN, M5P, and RF models did not show significant differences among themselves by the SK test (p < 0.05) (Fig.…”

“…ANNs are useful tools for analyzing and interpreting complex food safety data, predicting the physical and chemical quality of grains 23 . In this sense, machine learning models have been widely used to predict the quality of soybeans during transport 21 and stored corn 18 , in determining the quality of wheat during storage 24 , as well as in the evaluation of the germination rate of stored soybean seeds 25 . Some recent studies have demonstrated the effectiveness of machine learning models in predicting the viability, vigor and germination speed of seeds of different crops.…”

FEDformer-Based Paddy Quality Assessment Model Affected by Toxin Change in Different Storage Environments

“…Traditional models include moving average (MA), autoregressive (AR), and autoregressive moving average (ARIMA) models, all of which are widely used for time series forecasting [ 19 , 20 ]. Coradi et al [ 1 ] developed six linear regression models to predict grain storage quality and evaluated the models to achieve high prediction accuracy; André et al [ 37 ] used machine learning methods such as artificial neural networks, decision tree algorithm REPTree, and random forest to predict the quality of soybean seeds for decision making in the seed storage process. Jaques et al [ 37 ] evaluated decision tree algorithms (e.g., REPTree and M5P), random forests, and linear regression in predicting the physical and physiological quality of soybean seeds.…”

“…Coradi et al [ 1 ] developed six linear regression models to predict grain storage quality and evaluated the models to achieve high prediction accuracy; André et al [ 37 ] used machine learning methods such as artificial neural networks, decision tree algorithm REPTree, and random forest to predict the quality of soybean seeds for decision making in the seed storage process. Jaques et al [ 37 ] evaluated decision tree algorithms (e.g., REPTree and M5P), random forests, and linear regression in predicting the physical and physiological quality of soybean seeds. The results showed that these algorithms outperformed linear regression in terms of accuracy.…”

A logarithmically amortising temperature effect for supervised learning of wheat solar disinfestation of rice weevil Sitophilus oryzae (Coleoptera: Curculionidae) using plastic bags

“…For example, in 21 artificial neural networks (ANNs) were used as a predictive model in an Internet of Things (IoT) workflow where the gain quality was monitored to predict the quality of the stored grain and hence its deterioration during the post-harvest stages. In 22 , the quality of stored soybean seeds was predicted under different temperature and packaging conditions using several machine learning models, including ANN, REPTree and M5P decision tree algorithms, Random Forest (RF) and linear regression (LR) models. RF model has outperformed other models in predicting the physiological quality indices of such seeds.…”