Machine learning-assisted analysis for agronomic dataset of 49 Balangu (Lallemantia iberica L.) ecotypes from different regions of Iran.

The Balangu (Lallemantia iberica) species have a high gastronomical impact in the Middle East and Balkan region. It is widely used in the local food industry, such as confectionery, edible oil, and protein food. In this study, 49 ecotypes were collected from different regions of Iran. 37 agronomic traits were measured during the growing season and at harvest time. To find the correlation between the grain yield per unit area, grain yield per single plant (GYSP), oil percent (OP), and protein percent (PP) with other measured traits, which these were utilized as the labels of different machine learning (ML) procedures including Linear Regression (LR), Support Vector Regression (SVR), Random Forest Regression (RFR), and Gradient Boosting Decision Tree Regression (GBDTR). It was observed that there is a linear relationship between the measured agronomic traits and the considered labels. So, the LR, RFR, and GBDTR models showed the lowest mean absolute error, mean square error, and root mean square error than SVR models and good prediction ability of the test data. Although, the RFR and GBDTR have naturally lower bias than other methods in this study, but the GBDTR scheme is preferred because of the over-fitting shortcoming of the RFR technique. The GBDTR method showed better results rather than the other ML regression methods according to the RMSE 3.302, 0.040, 0.028, and 0.060 for GYUA, GYSP, OP, and PP, respectively.

Intercropping System and N2 Fixing Bacteria Can Increase Land Use Efficiency and Improve the Essential Oil Quantity and Quality of Sweet Basil (Ocimum basilicum L.).

Intercropping fodder plants with medicinal plants, in addition to enhancing productivity, can remarkably reduce the population of weeds, pests and diseases and for naturally meeting of livestock medicinal needs. Two experiments were conducted to evaluate biological yield, essential oil (EO) composition and yield of sweet basil (Ocimum basilicum L.) treated with N2 fixing bacteria in additive intercropping with forage maize during the 2018 and 2019. Treatments were arranged in factorial split-plot-in time in randomized complete block design with three replications. The factors were 100% chemical fertilizer (N), N2 fixing bacteria (Azospirillum brasilense and Azotobacter chroococcum), integration of N2 fixing bacteria + 50% nitrogen chemical fertilizer and control. The cropping pattern factor included of sole cropping basil and the additive intercropping of maize + 25% basil, maize + 50% basil, maize + 75% basil, and maize + 100% basil. The results indicated that the highest essential oil yield (30.8 kg ha-1) and essential oil percentage (0.75%) were obtained in sole cropping with A. brasilense and A. chroococcum + 50% chemical nitrogen fertilizer application in second harvest in 2019. In both cropping systems, the N2 fixing bacteria application significantly increased fresh and dry yield and land equivalent ratio (LER) as compared to control plants. In both years of experiments could remarkably vary depending on type of treatment. In both years, eight constituents including methyl chavicol (17.24-51.28%), Z-citral (neral) (8.33-24.3%), geranial (10.2-31.3%), (E)-caryophyllene (1.05-5.64%), α-trans-bergamotene (0.53-1.7%), α-humulene (0.4-1.69%), germacrene-D (0.2-1.88%), and (Z)-α- bisabolene (1.16-3.86%) were the main constituents of EO. The highest content of methyl chavicol was found through sole cropping of sweet basil with nitrogen chemical fertilizer followed by sole cropping of sweet basil with an integration of A. brasilense and A. chroococcum + 50% nitrogen chemical fertilizer in 2018 and 2019. Intercropping system and N2 fixing bacteria can be effective in reducing chemical fertilizer consumption and environmental pollution and achieving the sustainable agriculture goals.