A two-year (2020–2021) field experiment was conducted to investigate the impact of particular nanoparticles and biofertilizers on the growth, yield, and biochemical attributes of peanuts (Cv. Giza 6). Before planting, the seeds were inoculated with two biofertilizers, mycorrhiza and phosphorine, and were considered the main plot. The subplot contained foliar sprays of nanoparticles, i.e., 200 ppm boron (B), 200 ppm calcium (Ca), their combination (Ca+B), and the control (no spray). The results revealed that mycorrhiza significantly increased 100-seed weight (70.45 g), seed yield (1.9 ton/ha), biological yield (7.5 ton/ha), crop growth rate (CGR) (2.9 g day⁻¹ m⁻²), branching number (12.5), and protein content (22.96) compared with the control or phosphorine. Among the nanoparticles, Ca+B maximally improved plant height, CGR, 100-seed weight, shelling percentage, seed yield, oil content, and seed protein, while plants treated with B exhibited maximum seed nitrogen, pods per plant, and biological yield compared to other treatments. Overall, plants treated with Ca and B nanoparticles and mycorrhiza exhibited remarkable improvement in their growth, yield, and biochemical attributes, suggesting that nanotechnology and biofertilization are steps toward environmentally friendly, progressive farming. This study laid the basis for further elucidation of the molecular mechanism of plants in response to these nanoparticles and biofertilizers.

A field trial was conducted to investigate the productivity of three bread wheat cultivars, namely Giza-168, Shandawel-1, and Misr-2, under different fertilization treatments, i.e., azotobacter inoculation, 25% nitrogen (N) + azotobacter, 50%N + azotobacter, 75%N + azotobacter, and 100%N of the recommended level (180 kg/ha). The treatments were laid in a split-plot design, and each was replicated three times. The findings showed that wheat cultivars examined in the two seasons exhibited significant variations (p ≤ 0.05) in plant height (PH, cm), number of tillers m⁻² (NTM), number of spikelets per spike (NSS), 1000-grain weight (TGW, g), spike length (SL, cm), biological yield (BY, ton ha⁻¹), grain yield (GY, ton ha⁻¹), straw yield (SY, ton ha⁻¹), harvest index (HI, %), protein content (PC, %), days to 50% heading (DTH), and chlorophyll content (CC, SPAD). As a result, Giza-168 had a higher GY (14%), HI (27%), and TGW (10%) than any of the other two cultivars in both growing seasons. Furthermore, Misr-2 exhibited the highest PH (16%), NTM (26%), NSS (28%), SL (10%), BY (30%), SY (46%), and CC (3%). The application of the two treatments of 100%N and N75% + azotobacter exhibited high and statistically similar performance, resulting in an increase in all studied traits by greater than 30–50% compared to the other three treatments. According to the findings of the current investigation, the application of N fertilizer combined with azotobacter increased wheat yield more than either solely azotobacter or N application. We concluded that the application of nitrogen combined with azotobacter reduced the quantity of applied nitrogen by 25%.

The assessment of food and industrial crops during harvesting is important to determine the quality and downstream processing requirements, which in turn affect their market value. While machine learning models have been developed for this purpose, their deployment is hindered by the high cost of labelling the crop images to provide data for model training. This study examines the capabilities of semi-supervised and active learning to minimise effort when labelling cotton lint samples while maintaining high classification accuracy. Random forest classification models were developed using supervised learning, semi-supervised learning, and active learning to determine Egyptian cotton grade. Compared to supervised learning (80.20–82.66%) and semi-supervised learning (81.39–85.26%), active learning models were able to achieve higher accuracy (82.85–85.33%) with up to 46.4% reduction in the volume of labelled data required. The primary obstacle when using machine learning for Egyptian cotton grading is the time required for labelling cotton lint samples. However, by applying active learning, this study successfully decreased the time needed from 422.5 to 177.5 min. The findings of this study demonstrate that active learning is a promising approach for developing accurate and efficient machine learning models for grading food and industrial crops.

Egyptian cotton fibres have worldwide recognition due to their distinct quality and luxurious textile products known by the “Egyptian Cotton“ label. However, cotton fibre trading in Egypt still depends on human grading of cotton quality, which is resource-intensive and faces challenges in terms of subjectivity and expertise requirements. This study investigates colour vision and transfer learning to classify the grade of five long (Giza 86, Giza 90, and Giza 94) and extra-long (Giza 87 and Giza 96) staple cotton cultivars. Five Convolutional Neural networks (CNNs)—AlexNet, GoogleNet, SqueezeNet, VGG16, and VGG19—were fine-tuned, optimised, and tested on independent datasets. The highest classifications were 75.7%, 85.0%, 80.0%, 77.1%, and 90.0% for Giza 86, Giza 87, Giza 90, Giza 94, and Giza 96, respectively, with F1-Scores ranging from 51.9–100%, 66.7–100%, 42.9–100%, 40.0–100%, and 80.0–100%. Among the CNNs, AlexNet, GoogleNet, and VGG19 outperformed the others. Fused CNN models further improved classification accuracy by up to 7.2% for all cultivars except Giza 87. These results demonstrate the feasibility of developing a fast, low-cost, and low-skilled vision system that overcomes the inconsistencies and limitations of manual grading in the early stages of cotton fibre trading in Egypt.

Sugar beet production demands sustainable intensification approaches to enhance both yield and quality. This study examined the effects of foliar nano-ammonium nitrate (NH ₄ NO ₃ ) applications on five sugar beet cultivars – JAMPOL, BTS 9830, DEL 1135, ASEEL and Raspoly – over two growing seasons in Egypt’s Nile Delta, using a split-plot randomized complete block design. Three nano-NH ₄ NO ₃ concentrations (0, 50 and 100 ppm) were sprayed twice each season to assess impacts on growth, yield and quality parameters. The results indicated limited influence of treatments on primary yield metrics; taproot yields remained unaffected across all cultivars and seasons. Nonetheless, the 50 ppm treatment preserved optimal sugar quality, with sucrose content reaching 19.4 %, compared to 18 % in the controls. Carotenoid levels increased by 12 % under the 100 ppm treatment, reflecting enhanced nutritional quality. Among cultivars, ASEEL yielded the best results with taproot outputs of 34 t/ha and sugar yields of 6.1 t/ha under optimal conditions, demonstrating significant cultivar-dependent variation. Multivariate analysis revealed distinct response patterns among cultivars and treatments, with three-way interactions (Season × Cultivar × Nanoparticle) affecting several traits. Clustering identified four trait groups and three treatment clusters, highlighting sugar beet’s complex response to nanoparticles. Economic analysis shows limited benefits, with no significant increase in taproot yield, despite a rise in secondary metabolites. While nano-NH ₄ NO ₃ can modify biochemical parameters, the lack of yield improvements casts doubt on its economic feasibility. Cultivar choice primarily influences sugar beet performance, with environmental conditions also affecting treatment efficacy.

Egyptian cotton is one of the most important commodities to the Egyptian economy and is renowned globally for its quality, which is currently graded by manual inspection. This has several drawbacks including significant labour requirement, low inspection efficiency, and influence from inspection conditions such as light and human subjectivity. This current work uses a low-cost colour vision system, combined with machine learning to predict the cotton lint grade of the cultivars Giza 86, 97, 90, 94 and 96. Unsupervised and supervised machine learning approaches were explored and compared. Three different supervised learning algorithms were evaluated: linear discriminant analysis, decision trees and ensemble modelling. The highest accuracy models (77.3-98.2%) used an ensemble modelling technique to classify samples within the Egyptian cotton grades: Fully Good, Good, Fully Good Fair, Good Fair and Fully Fair. The unsupervised learning technique k-means showed that human error is more likely to occur when classifying lint belonging to the higher quality grades and underlined the need for an intelligent system to replace manual inspection.