Image Classification of Wheat Rust Based on Ensemble Learning.

Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat.

Can deficit irrigations be an optimum solution for increasing water productivity under arid conditions? A case study on wheat plants.

Water scarcity is of growing concern in many countries around the world, especially within the arid and semi-arid zones. Accordingly, rationalizing irrigation water has become an obligation to achieve the sustainable developmental goals of these countries. This may take place via using deficit irrigation which is long thought to be an effective strategy to save and improve water productivity. The current study is a trial to evaluate the pros and cons of using 50 and 75 % of the irrigation requirements (IR) of wheat (deficit irrigations) versus 100 %IR, while precisely charting changes in wheat growth parameters, antioxidant enzymes in plant shoots and the overall nutritional status of plants (NPK contents). Accordingly, a field experiment was conducted for two successive seasons, followed a split-plot design in which deficit irrigations (two irrigations to achieve 50 % of the irrigations requirements (IR), three irrigations to attain 75 % IR, and four irrigations to fulfill 100 % IR) were placed in main plots while four different studied wheat cultivars were in subplots. Results obtained herein indicate that deficit irrigations led to significant reductions in growth parameters and productivity of all wheat cultivars, especially when using 50 % IR. It also decreased NPK contents within plant shoots while elevated their contents of proline, peroxidase, and catalase enzymes. On the other hand, this type of irrigation decreased virtual water content (VWC, the amount of water used in production on ton of wheat grains). Stress tolerance index (STI), and financial revenues per unit area were also assessed. The obtained values of grain productivity, STI, VWC and financial revenues were weighted via PCA analyses, and then introduced in a novel model to estimate the efficiency of deficit irrigations (ODEI) whose results specified that the overall efficiency decreased as follows: 50 %IR < 75 %IR < 100 %IR. In conclusion, deficit irrigation is not deemed appropriate for rationalizing irrigation water while growing wheat on arid soils.

Insights on the Nutritional Profiling of Cantaloupe (Cucumis melo L.) via 1-Naphthalene Acetic Acid.

The nutritional components of cantaloupe, including vitamins, minerals, antioxidants, and dietary fiber, contribute to overall health, improved immunity, hydration, and protection against chronic diseases. This study was conducted to investigate the influence of different concentrations (0 (control), 100, 150, and 200 ppm) of 1-naphthalene acetic acid (1-NAA) on the nutritional components of the cantaloupe (Cucumis melo L. Var. Super White Honey). All the studied treatments were applied twice at the 2nd and 4th leaf stages. The applied concentrations of 1-NAA significantly improved the sex expression and fruit yield attributes. Different nutritional components like proximate contents, minerals, vitamins, selected fatty acids, and amino acids were analyzed. The results showed that the maximum moisture content, proteins, carbohydrates, ash, and energy were recorded with 100 ppm. The higher lipids were recorded during the supplementation of 150 ppm. Significantly greater fibers were recorded using 200 ppm. Regarding minerals, 100 ppm was found to be the best as it increased calcium (Ca), magnesium (Mg), potassium (K), sodium (Na), phosphorous (P), manganese (Mn), copper (Cu), iron (Fe), and zinc (Zn). Vitamins were also found to be the maximum with 100 ppm, including vitamin A, vitamin B, vitamin C, vitamin D, vitamin E, and vitamin K. Total selected fatty acids and amino acids were also found significantly greater in the fruits administered 100 ppm.

Investigation on the use of ensemble learning and big data in crop identification.

The agriculture sector in Egypt faces several problems, such as climate change, water storage, and yield variability. The comprehensive capabilities of Big Data (BD) can help in tackling the uncertainty of food supply occurs due to several factors such as soil erosion, water pollution, climate change, socio-cultural growth, governmental regulations, and market fluctuations. Crop identification and monitoring plays a vital role in modern agriculture. Although several machine learning models have been utilized in identifying crops, the performance of ensemble learning has not been investigated extensively. The massive volume of satellite imageries has been established as a big data problem forcing to deploy the proposed solution using big data technologies to manage, store, analyze, and visualize satellite data. In this paper, we have developed a weighted voting mechanism for improving crop classification performance in a large scale, based on ensemble learning and big data schema. Built upon Apache Spark, the popular DB Framework, the proposed approach was tested on El Salheya, Ismaili governate. The proposed ensemble approach boosted accuracy by 6.5%, 1.9%, 4.4%, 4.9%, 4.7% in precision, recall, F-score, Overall Accuracy (OA), and Matthews correlation coefficient (MCC) metrics respectively. Our findings confirm the generalization of the proposed crop identification approach at a large-scale setting.

Assessment of land suitability using a soil-indicator-based approach in a geomatics environment.

The study aims to develop new approach for soil suitability evaluation, Based on the fact that choosing the proper agricultural sites is a requirement for good ergonomic and financial feasibility. The AHP included a selection of different criteria used for analysis and categorized according to their usefulness in relation to the growth conditions/requirements of the selected crops. Lithology, soil physicochemical, topography (slope and elevation), climate (temperature and rainfall), and irrigation water were the main criteria selected for the study. The study indicated that the area is suitable for agricultural use, taking into account the quality of the water used to maintain the quality of the soil. According to the FAO the suitability result was for S1 (0.71%), S2 (19.81%), S3 (41.46%), N1 (18.33%) and N2 (19.68%) of the total area. While the results obtained from the new approach for the study 9.51%, 30.82%, 40.12% and 19.54 for very high, high, moderate, low and very low suitability respectively, Taking into account that the constraints units of FAO is located in very low suitability class with 0.69% of the total area which Not valid for crop production due to some restrictions. The findings of the study will help narrow the area to the suitable sites that may further be sustainably used for annual and/or perennial crops. The proposed approach has high potential in applications for assessing land conditions and can facilitate optimal planning for agricultural use.