In the present study, we used device visualization in tandem with deep learning to detect weeds in the wheat crop system in actual time. We selected the PMAS Arid Agriculture University research farm and wheat crop fields in diverse weather environments to collect the weed images. Some 6000 images were collected for the study. Throughout the season, tfhe databank was assembled to detect the weeds. For this study, we used two different frameworks, TensorFlow and PyTorch, to apply deep learning algorithms. PyTorch’s implementation of deep learning algorithms performed comparatively better than that of TensorFlow. We concluded that the neural network implemented through the PyTorch framework achieves a superior outcome in speed and accuracy compared to other networks, such as YOLO variants. This work implemented deep learning models for weed detection using different frameworks. While working on real-time detection models, it is very important to consider the inference time and detection accuracy. Therefore, we have compared the results in terms of execution time and prediction accuracy. In particular, the accuracy of weed removal from wheat crops was judged to be 0.89 and 0.91, respectively, with inference times of 9.43 ms and 12.38 ms on the NVIDIA RTX2070 GPU for each picture (640 × 640).

The agriculture sector plays a very important role in the increasing population, year by year, to fulfill requirements and contributes significantly to the economy of the country. One of the main challenges in agriculture is the prevention and early detection of pest attack on crops. Farmers spend a significant amount of time and money in detecting pests and diseases, often by looking at plant leaves and analyzing the presence of diseases and pests. Late detection of pest attacks and improper use of pesticide application can cause damage to plants and compromise food quality. This problem can be solved through artificial intelligence, machine learning, and accurate image classification systems. In recent years, machine learning has made improvements in image recognition and classification. Hence, in this research article, we used convolutional neural network (CNN)-based models, such as the Cov2D library and VGG-16, to identify pest attacks. Our experiments involved a personal dataset consisting of 7000 images of pest-attacked leaf samples of different positions on maize plants, categorized into two classes. The Google Colab environment was used for experimentation and implementation, specially designed for cloud computing and machine learning.

Smart farming and precision agriculture rely on the different components of IoT, such as sensors, drones, and robotic devices. IoT in agriculture is the network of interconnected devices that corresponds in real time, simultaneously, to gather, analyze, and transfer the data, which, ultimately, generate a decision to be taken by the farmer. The availability of the 4G/3G does not support the precision practices in real time due to the bandwidth, connectivity, and the speed of data-transfer issues. Further, 5G technology in the agricultural sector has put its greater influence in real-time monitoring, unmanned aerial vehicles, virtual consultation and predictive maintenance, artificially intelligent robotics, and data analytics and cloud repositories. Conclusively, the speed, connectivity, scalability and processing power, and limitations can be overcome with the availability of 5G structures.

The depletion of usable agricultural lands has brought up a scenario of vertical farming. This type of farming is mostly considered soil-less farming in the vertical direction. Three of the commonly used soil-less ways for vertical farming include hydroponic, aeroponic, and aquaponic. Although it is not very popular in developing countries, investment has been made by many European counties and efforts to use vertical farming as a commercial product are on the path to success. Food security issues can be addressed through this farming type as well.

Lentil (Lens culinaris Medic) is the main pulse crop and usually has low production due to numerous factors and cultivation practices. A field study was designed to investigate the best trace elements (Co, Nin, and Se) for sole application or in combination as fertigation after sowing for the lentil variety (NIA Masoor-2005). Comparatively better crop growth and yield with better quality were obtained through the application of Co, Ni, and Se, at 600, 600, and 300 g ha-1, respectively. The maximum grain yield (1638 kg ha-1) was harvested from the treatment where Co, Ni, and Se were applied at 600 g ha-1, which was 15% higher than that of the control receiving no trace elements. According to economic analyses, the best performing treatment is the use of Ni and Co in full doses, as Se has high and does not have economically effective results. All three trace elements had a positive impact on lentil nodulation (up to 33%), seed protein (4.6%), and yield increase (15%) over the control receiving no trace elements. However, with the application of Co and Ni at 600 g ha-1, each was found to be the most economical and showed comparable results regarding growth, nodulation, and yield contributing parameters compared to Co, Ni, and Se, each at 600 g ha-1. It was concluded that the use of trace elements (Co, Ni, and Se), individually or in combination, is economical and has the capacity to increase the yield and nodulation of lentils.