Smart agriculture has taken more attention during the last decade due to the bio-hazards of climate change impacts, extreme weather events, population explosion, food security demands and natural resources shortage. The Egyptian government has taken initiative in dealing with plants diseases especially tomato which is one of the most important vegetable crops worldwide that are affected by many diseases causing high yield loss. Deep learning techniques have become the main focus in the direction of identifying tomato leaf diseases. This study evaluated different deep learning models pre-trained on ImageNet dataset such as ResNet50, InceptionV3, AlexNet, MobileNetV1, MobileNetV2 and MobileNetV3.To the best of our knowledge MobileNetV3 has not been tested on tomato leaf diseases. Each of the former deep learning models has been evaluated and optimized with different techniques. The evaluation shows that MobileNetV3 Small has achieved an accuracy of 98.99% while MobileNetV3 Large has achieved an accuracy of 99.81%. All models have been deployed on a workstation to evaluate their performance by calculating the prediction time on tomato leaf images. The models were also deployed on a Raspberry Pi 4 in order to build an Internet of Things (IoT) device capable of tomato leaf disease detection. MobileNetV3 Small had a latency of 66 ms and 251 ms on the workstation and the Raspberry Pi 4, respectively. On the other hand, MobileNetV3 Large had a latency of 50 ms on the workstation and 348 ms on the Raspberry Pi 4.

Aims: Assess The sustainable production of tomato and cucumber under greenhouse conditions for meeting the challenges of natural resources shortage, food security and economic. Study Design:  Two experiments performed in complete randomized blocks with three replicates. Place and Duration of Study: Central Laboratory for Agriculture Climate (CLAC), Agriculture Research Center, Egypt, during two autumn seasons of 2018 and 2019 (tomato) and two spring seasons of 2019 and 2020 (cucumber). Methodology: Different soilless culture systems for producing tomato and cucumber under greenhouse were investigated: Hydroponic systems (Nutrient film technique (NFT) and deep flow technique (DFT)); and substrate systems (Dutch bucket, pot, container, and horizontal bag). Vegetative characteristics, yield parameters, N, P, and K contents, and environmental impact assessment were measured. Results: Substrate systems gave the highest vegetative growth characteristics, yield parameters, N, P and K contents of tomato and cucumber leaves, as well as the highest power use efficiencies compared to hydroponic systems. Container and bags systems gave the highest results of tomato and cucumber vegetative growth, respectively, but the highest yield and net profits records belonged to bags and pots respectively. Bags substrate system gave the highest net profit yield (10.1Kg/ plant and 21881 LE / greenhouse) of tomato plant under plastic house followed by container system that presented the highest yield (10.6 Kg/ plant) but the total cost mainly substrate cost contributed to reduce its net profit yield. While for the highest yield and net profit of cucumber, the pots system (8.1Kg/ plant and 13243 LE / greenhouse) followed container system (7.65Kg/ plant and 9045 LE / greenhouse) and bags system (7.15Kg/ plant and 10270 LE / greenhouse) were recommended. The lowest yield, the highest average power use, cost and efficiency and lowest total cost were estimated by NFT system in both of tomato and cucumber investigations. Conclusion: The substrate systems presented more sustainability for tomato and cucumber production under plastichouse conditions. Bags substrate system gave the highest net profit yield of tomato plant under plastic house followed by container system that presented the highest yield but the total cost mainly substrate cost contributed to reduce its net profit yield. While for the highest yield and net profit of cucumber, the pots system followed container system and bags system were recommended. The lowest yield, the highest average power use, cost and efficiency and lowest total cost were estimated by NFT system in both of tomato and cucumber investigations.

The potato plants (Solanum tuberosum L.) vs. valor were exposed to different levels of nitrogen fertilizer (60, 100, 140, 180 kg N/feddan (4200 m2)) and in-row plant spacing (12.5, 25 and 50 cm) for maximizing the yield production to match food security needs under climate change impacts on Delta region, Egypt. The experiment was carried out during two growing seasons (2010/2011 and 2011/2012) in split plot design at El-Bossily Farm, Agricultural Research Center, El-Behira Governorate, Egypt. The vegetative growth characteristics and yield parameters were measured. The result of this study verified that increasing nitrogen level up to 180 kg N/feddan significantly increased the vegetative growth, total and marketable yields than the other N treatments. The in-row plant spacing 50 cm was significantly increased vegetative growth and yield (kg/plant), but the total yield (kg/m2) had different trend. The highest total yield /m2 was obtained by 12.5 cm treatment. The interaction effect of 180 kg/feddan of N and 12.5cm in-row plant spacing were increased the total tuber yield (kg/m2) significantly. In contrary, the best marketable yield (tubers > 35 mm) /m2 was obtained by 25 and 50 cm in-row plants. This study was concluded that the best agronomic practices for potato production obtained by application 180 kg N/feddan of with in-row plant spacing 25 cm treatment. The economical consideration of the different treatments showed that the best total net income was obtained by 180 kg/feddan N with 50 cm in-row plant spacing.

Smart agriculture motivates more farmers every day via different applications with a view of maximizing food production as well as minimizing the climate change impacts, COVID-19 crisis, and natural resources shortages. Developing the agricultural production process based on smart agriculture and IoT technology has become extremely vital to preserve natural resources, increase sustainability and ecological agricultural food production, and satisfy food security demands. Smart agriculture is mainly based on sensing and monitoring micro-climate and environmental data (collection) and analysis. Data collected from different sources (internet, remote sensing database, and sensors) can provide a wealth of information for agriculture operators, allowing them to take appropriate actions in a timely manner. Developing microcontrollers, sensors, and actuators integrated with IoT to include all agricultural procedures especially in developed countries become more necessary.