Drought conditions pose significant challenges to sustainable agriculture and food security. Identifying microbial strains that can mitigate drought effects is crucial to enhance crop resilience and productivity. This study presents a comprehensive comparison of several machine learning models, including Random Forest, Decision Tree, XGBoost, Support Vector Machine (SVM), and Artificial Neural Network (ANN), to predict optimal microbial strains for this purpose. Models were assessed on multiple metrics, such as accuracy, standard deviation of results, gains, total computation time, and training time per 1000 rows of data. Notably, the Gradient Boosted Trees model outperformed others in accuracy but required extensive computational resources. This underscores the balance between accuracy and computational efficiency in machine learning applications. Leveraging machine learning for selecting microbial strains signifies a leap beyond traditional methods, offering improved efficiency and efficacy. These insights hold profound implications for agriculture, especially concerning drought mitigation, thus furthering the cause of sustainable agriculture and ensuring food security.

Most publications on the influence of environmental factors on macroinvertebrate communities focus on large rivers, whereas relatively few examine small watercourses in agricultural areas, which, due to their size and pressure from intensive agricultural production, are much more susceptible to the effects of unfavourable environmental conditions or anthropopressure. The aim of our study was to compare the biodiversity of macrozoobenthos assemblages and to determine the effects of physicochemical and hydrological conditions on their abundance and density in 10 small rivers in agricultural areas located in northwest (53°23′ N 15°14′ E) and central (52°11′ N 20°48′ E) Poland. In total, 105 taxa were recorded, with the majority being euryoecious. Among the assessed physicochemical parameters, oxygenation was found to affect the density and number of taxa; another important factor was the content of nitrate nitrogen. Sensitivity to changes in water temperature was observed in some macrozoobenthos taxa (especially Decapoda). Of the examined hydrological parameters, the greatest effects were exerted by speed, flow, and depth.

Drought is regarded as one of the environmental constraints threatening agriculture worldwide. Melatonin is a pleiotropic molecule prevalent in plants capable of promoting plant endogenous resilience to many environmental challenges including drought. Banana is an important staple food consumed in developing countries especially in Africa. In this research, we studied the role of melatonin in the growth of bananas subjected to drought under the Egyptian semi-arid conditions. To achieve this objective, a field experiment on banana (Musa spp., cv. Williams) mother plants and first ratoon was conducted on a private farm for two seasons - 2019 and 2020. Three irrigation treatments, 100, 90 and 80% irrigation water requirements (IWR) were used in conjunction with four concentrations of melatonin as a foliar spray (0 μmol, 40 μmol, 60 μmol, and 80 μmol) to determine the effect of both treatments on banana plant performance under drought. The results showed that there was a substantial difference between treatments, with the foliar application of melatonin at 80 μmol concentration improving most of the yield attributes, relative water content, total chlorophyll and proline with water deficit. However, the foliar application of the molecule lowered the biochemical characteristics mostly at 80% IWR under the Egyptian semi-arid conditions. Overall, there was a concentration-dependent response with regards to IWR for the two seasons 2019 and 2020.