The new queries or complaints can be filtered by selecting the ‘unresolved’ status. Supervisor can read the new query or complaint and based on the content, assigns it to one of the agro-experts with relevant expertise. Upon assignment, the status of the query or complaint is automatically changed to ‘in process’ by the system and an email is also sent to agro-expert, notifying them that a new query or complaint has been assigned. Supervisor can see the list of all argo-experts and can also see the list of queries or complaints assigned to each argo-expert. Moreover, supervisor can monitor the performance of every argo-expert based on the number of queries or complaints resolved by them.After login, agro-expert can see their dashboard, with a list of all queries or complaints assigned to them. The new queries or complaints can be filtered by clicking the ‘unresolved’ status. Agro-expert can click the query or complaint to study its content and view the provided images/audio files and then can submit the response by adding a solution or a comment or a question to ask farmer to elaborate the problem further. Based on the response,square plastic pot agro-expert can change the status of the query or complaint to ‘resolved’ or can leave it as ‘in process’.
Agro-experts receive a system generated automated email for each query or complaint assigned to them or when status of a query or complaint is changed. Agro-experts can also visualize their performance based on the number of queries or complaints they resolved.Agriculture in developing countries contributes a big portion to national GDP, but there is a lack of effective support for farmers to adopt suitable agricultural practices through technology advancements. Farmers usually require timely advice and suggestions on crop patterns, diseases and prevention actions to tackle emerging situations. However, the development of a reliable, scalable, real time responsive system that is available 24/7 and fulfills the information requirements and support of farmers is still an open issue, especially in large agricultural countries like Egypt. The agri-culture sector’s data can be historical as well as processes related. Processing and analysing these massive amounts of data is challenging and involves a number of critical decisions such as selection of data storage depending on the nature and modalities of data involved. The large amounts of data being collected in the agriculture sector is expected to have an impact not only on smart farming but will also improve the decision-making capabilities of the farmers and government. The future of agriculture undoubtedly seems to lie in embarking on big data technologies and smart farming. Moreover, integration of concepts like Data Force Analytics and by providing a series of training to the system users, the whole process can be speed up overtime.
Consequently, farmers will be able to directly interact with such systems for their queries without interacting with human resources. To make a progress towards few of these challenges, the architecture of AgroSupportAnalytics has been developed. This has enabled building a support system that facilitates the provision of timely advice and relevant predictions to farmers. This, operational currently, will ensure a reduction and mitigation of significant negative effects of many serious challenges and threats facing the farming community and hence the agriculture sector in Egypt. The support provided will be more consistent, timely, reliable, and at easy reach, not only for ‘research centres’ but also for the ’agricultural associations,’ with minimal training and resources needed. The developed architecture of Agro Support Analytics has been designed on the basis of the following non-functional requirements. Scalability ‘ The Agro Support Analytics has several separated components in the architecture that allows easy scalability by upgrading one or more of those individual components. As an example, if the number of farmers/users/clients grows that may require splitting the Web Service by adding new capacity to deal with the client demand which means more Web Servers on the Information and Analysis Services Layer. Resilience and Redundancy ‘ The architecture of Agro Support Analytics is resilient as the critical components can be split in tiers that are clustered and geographically split to ensure failover, hence a more resilient system. Maintenance flexibility – As with the case of scalability, having distinct tiers allows pin pointed maintenance actions that do not produce collateral unwanted effects. This means that maintenance scheduling has fewer dependencies from 3rd party components. Developer Friendly Environment ‘ Having the several coding layers split by distinct tiers allows developers to focus on their individual task without having to share resources or bear in mind collateral potential impacts in each other’s tasks/domains. This is the type of architecture that also empowers frameworks and programming cultures like that of Agile development methodologies.
The prototype system is being operational currently and undergoing a process of outreach campaign to ensure sufficient stakeholder awareness of the services and capabilities it provides. A few snapshots of the Agro Support Analytics system is shown as Fig. 4. A transition stage is expected to follow in the near future whereby both farmers and agricultural experts will be using the system for their usual query-response activities. That is, besides the efficiency and effectiveness in dealing with farmers’ enquiries, the presented system can provide a sustainable and near real-time advice to the large sector of farmers in Egypt, that is besides vitally needed insights and projections of future events, relevant to their decision and action making. Currently, the Agro Support Analytics system doesn’t directly cater for IoT integration and analytics, which can also be an interesting future direction.The increase in population growth is accompanied by an increase in demand for food production. The FAO reported that the world population would be reached 9.73 billion by 2050, and the increase will continue till reach 11.2 billion by 2100 . Many challenges impede agricultural production, which leads to a decrease in crop productivity, such as soil salinity in arid conditions . In addition, the climate also affects the quantity and quality of crops and may lead to an increase in soil sensitivity to desertification . Therefore, the focus on survey land resources to use in agricultural development in arid regions is necessary . In developing world countries, the agricultural sector is one of the most important pillars of national income. Therefore, implementing new technologies to improve the agricultural sector is a significant issue for supporting the national economy in those countries . Agricultural production includes the production of food for humans and livestock, in addition to the raw materials needed for the industrial process. Since the ancient time till now, there are several agricultural development revolutions; the first agricultural revolution was by Egyptian and Greek ancient civilizations that had reflected interesting of the ancient people in the development of agricultural methods, where papyri indicating the develop irrigation systems from more than 6000 BCE.
Egyptians and Greeks developed several agricultural machinery and equipment, for example, tympanum, pumps, Shadouf, and Sakai . The second agricultural revolution was showed during the 17th century that followed the end of feudalism in the continent of Europe. Furthermore, the third agricultural revolution had activated during 1930–1960 of the last century, where an expansion uses of mineral fertilizers to increase agricultural production, as well as increased usage of pesticides parallel with the development of various agricultural machinery . The fourth agricultural revolution occurred during the past two decades, which there was a significant development in information communication technology and AI. These technologies have facilitated controlling the equipment and devices remotely, where robots have been used in agricultural operations such as harvesting and weeding, and also drones have also been used to fertilize crops and monitor crop growth stages. Smart agriculture is a technology that relies on its implementation on the use of AI and IoT in cyber-physical farm management . Smart agriculture addresses many issues related to crop production as it allows monitoring of the changes of climate factors, soil characteristics, soil moisture, etc. The Internet of Things technology is able to link various remote sensors such as robots, ground sensors, and drones, as this technology allows devices to be linked together using the internet to be operated automatically . The main idea of precision agriculture is improving the spatial management practices to increase crop production on the one hand and avoid the misuse of fertilizers and pesticides on the other hand . Numerous research has been conducted on applying ANN models in smart irrigation water management . The estimation of reference evapotranspiration is one of the essential parameters for crop irrigation because it determines irrigation scheduling . The Penman-Monteith model is the most often used for estimating evapotranspiration, although it needs a large amount of data for accurate ET estimates. Because GIS is linked with remote sensing, artificial intelligence, GPS technology, and other technologies,potted blackberry plant it may conserve a significant quantity of water that would otherwise be needed for irrigation. Mohd et al. created SWAMP ; a web-based Geospatial DecisionSupport System ; and a graphical user interface based on widget technology for simple access to different views for the rice IWM Scheme.
The system offers data on irrigation water demand and supply, as well as irrigation efficiency and a water productivity index. One of the most significant aspects of this system is providing real-time information by visualizing the presented results. Climate-Smart Agriculture was created to address three key issues: food security, adaptation, and mitigation . CSA has received much interest, particularly in developing countries, because of its potential to improve food security and farm system resilience while lowering greenhouse gas emissions . This is particularly important in Africa, where economic development is based on agricultural expansion, which is the most susceptible to climate change . Smart Agriculture is an evolution of precision agriculture by innovating smart methods to achieve multifunctional regarding the farm management remotely supported by alternatives appropriate solutions of farm management in real-time. Fig. 1 showed that robots could fulfill essential roles in controlling the agricultural process and anticipate automatic analysis and planning so that the electronic cyber-physical cycle becomes semi-autonomous . European Union , highlighted the technologies importance of high-resolution satellite images, Unmanned Aerial Vehicles , agricultural robots, and sensor nodes to collect data that could be integrated into future strategies of European agriculture smart farming signed in April 2019 by 24 EU countries . Parallel to expanding the various sensing methods for collecting, processing,and analyzing data, the volume of data used in agricultural management has become very big. Thus this leads to a decrease in the ability of the 4G network to connect all components of the smart network in remote locations. Recently, after the operation of the ultra-fast 5G switch, the process of transferring and processing data has become easy . Smart agriculture technology based on the Internet of Things technologies has many advantages related to all agricultural processes and practices in real-time, which include irrigation and plant protection, improving product quality, fertilization process control, and disease prediction, etc.. The advantages of smart agriculture can be summarized as follows: 1) Increasing the amount of real-time data on the crop, 2) Remote monitoring and controlling of farmers, 3) Controlling water and other natural resources, 4) Improving livestock management, 5)Accurate evaluation of soil and crops; 6)Improving agricultural production. This work aims to review published articles on the techniques above with regards to smart farming, in addition, highlight some approaches to smart farming in developing countries.The current work considered a large number of research topics to explore scientific methods relating to smart farming. Consequently, this work covered many aspects regarding the agricultural practices, decision-making, and technologies involved. We have used several sources from various scientific publishers such as Springer, Elsevier, Wiley, MDPI, etc. The sources varied from books, book chapters, conference proceedings, and articles, in addition to research project reports. Thus, this work has relied on 58 published documents, most of which were published during the last three years, and the authors from different countries worldwide. Meanwhile, a particular focus was dedicated to some smart agriculture approaches in the Africa continent. Subsequently, the review highlights the main components of smart farming, such as IoT, the role of internet connection, and smart sensing.