Prediction of crop yield is a necessary activity for maximizing the worldwide meals provide, significantly in growing nations. This examine investigated lettuce yield prediction utilizing 4 machine learning models, specifically, help vector regressor, excessive gradient boosting, random forest, and deep neural community.
It was cultivated in three hydroponics techniques, which interacted with three completely different magnetic unit strengths beneath a managed greenhouse surroundings in the course of the rising season in 2018 and 2019. Three eventualities consisting of the mixtures of enter variables (i.e., leaf quantity, water consumption, dry weight, stem size, and stem diameter) had been assessed. The XGB mannequin with state of affairs 3 (all enter variables) yielded the bottom root imply sq. error of 8.88 g adopted by SVR with the identical state of affairs that achieved 9.55 g, and the very best end result was by RF with state of affairs 1 which achieved 12.89 g.
All mannequin eventualities having Scatter Index values lower than 0.1 had been labeled as glorious in predicting contemporary lettuce yield. Based on the entire efficiency statistics, the 2 greatest models had been SVR with state of affairs 3 and DNN with state of affairs 2. However, DNN with state of affairs 2 requiring fewer enter variables is most well-liked. The potential of the DNN mannequin to predict contemporary lettuce yield is promising, and it may be utilized on a big scale as a speedy software for decision-makers to handle crop yield.
Read the whole analysis at www.researchgate.web.
Orsini, Francesco & Mendez-Espinoza, Ana & Carotti, Laura & El-Ssawy, Wessam & Al-Ansari, Nadhir & Mokhtar, Ali & He, Hongming & Saad, Sh & Shauket, Saad & Gyasi-Agyei, Yeboah & Abuarab, Mohamed. (2022). Using Machine Learning Models to Predict Hydroponically Grown Lettuce Yield. Plant Science. 13. 1-10. 10.3389/fpls.2022.706042.
https://www.hortidaily.com/article/9406959/using-machine-learning-models-to-predict-hydroponically-grown-lettuce-yield/
