The degree that farming systems follow the principles of OA can be represented as continuous scale, however, a clear line can be drawn between farmers who complied with the minimum requirements of organic standards and those who do not . On this scale, also conventional farmers can be by the extent to which they come close to the boundary of organic compliance, based on the amount and frequency of chemical inputs they use . Furthermore, organic farmers can be grouped according to whether they practice organic farming because they do not have access to chemical inputs or whether they practice organic farming intentionally . In our case studies, organicby-default farmers, which were in the control and not in the intervention groups, were rather uncommon, as most farmers used chemical inputs from time to time, even though some used them only in small quantities. Both groups practice organic farming intentionally and can be further distinguished as farmers who manage their farm only passively and those who manage their farm organically in an active way. Among the latter group, we can further distinguish between farmers who merely substitute conventional inputs by organic ones and those who actively follow agroecological principles and design their farm accordingly for a sound organic nutrient and pest management. While the latter group can be considered closest to implementing the principles of OA, according to our data it is the absolute minority among smallholder farmers in SSA. This emphasises the necessity to view organic agriculture as a farming system that requires a systemic shift beyond the view of single practices that is increasingly taken up by agroecology or regenerative agriculture . Cultivating soil, producing crops, and preparation and distribution of the resulting products is a practice that dates back thousands of years, aeroponic tower garden system and since has been playing a vital role in contributing to the global economy.
In many developing countries, agriculture is a major source for income and employment in rural communities which constitute 45% of the world’s population. Around 26.7% of the world population secure their livelihoods from agriculture. Yet, despite its historical impact on food security, employment and socioeconomic development and stability, the sector still faces structural weaknesses and challenges. These include, but not limited to, pests, vulnerability to climate change, inadequate farming practices and uninformed decision making related to planning, support and protection. The lack of effective support for farmers to adopt good agricultural practices and prevention methods are yet another factors that hinder both the productivity and food security in large scale rural communities. Farmers need up-to-date advice on crops’ diseases, crop patterns and adequate prevention actions to face developing circumstances. Currently, farmers’ access to such information is limited due to current support system being inconsistent, unreliable and often not timely – hence delivered advice can become irrelevant. Over the last two decades, advancements in the agricultural industry has been made through the application of data analytic tools and decision support systems , with noticeable impact in irrigation management, precision agriculture and optimal farming. Though these systems are very useful in offering structured analysis and information to the farmers in a step by step manner, difficulty in usage due to their sophisticated nature, especially for farmers with low literacy in developing countries is often times a challenge. Several systems exist, including related informal forums, social networks, and interactive voice response systems where peers and experts interact with each other and exchange suggestions and opinions on issues raised by farmers. Governments have also tried to handle enquiries and concerns raised by farmers via establishing agri-centres at rural hubs where experts provide suggestions on farmers’ complaints and enquiries by telephony. Whilst this approach seems to facilitate reasonable results, nonetheless, due to the high user demand, it is practically not feasible to provide effective response to extremely large numbers of phone calls, and does not offer a structured way to keep track, and use, of the historic record of enquiries made, resolved and otherwise.
Moreover, providing adequate responses for farmers’ queries is difficult for domain experts as comprehensive information regarding the context of the problem and underlying issues may not be adequately communicated through conventional phone calls. For a sustainable farming practice, the development of an automated query/complaint management system is still an open problem. Mohit Jain et al. proposed a conversational agent for resolving farmer queries by using IBM Watson Speech-based system and Google Translator. However, there is still a high demand for efficient query/complaint management system to enhance the usability and acceptability aspects for farmers with limited literacy while keeping the system highly scalable, available around-the-clock and have manageable overheads. This study aims to resolve the problem of support and advice for farmers in place of the current manual system, deployed in Egypt, by presenting a framework for Complaint Management and Decision Support System for Sustainable Farming . It is based on the application of knowledge discovery and analytics on agricultural data and farmers’ complaints, deployed on a Cloud platform. The automated system is to provide adequate and timely advice for farmers upon their enquires/ complaints, and also to foresee near future development of circumstances by the experts. Consequently, enabling agricultural experts to broadcast early warning signals of threats, mainly pests and disease, and the needed prevention actions to be undertaken by farmers. The system can be deployed to serve villages around farming fields in Egypt and will aim at improving welfare and development in rural parts of the country, and open opportunities for further research and development in the field. The rest of the paper is structured as follows: In Section 2, a literature review of decision support and expert systems in agriculture is presented. Section 3 describes the system requirements and applications constraints. Section 4 presents the system architecture with an illustration of the services/features offered by AgroSupport Analytics system. In Section 5, we present the software application architecture.
The N-tiered architectural representation of the proposed system is described in Section 6. Section 7 offers the subsystem layering and component-level functionalities details. Section 8, presents the Applications of the AgroSupport Analytics system along with a brief case study of farmer query and complaint response that serves as a demonstrative proof of system. Section 9 concludes the paper.Agriculture in Egypt absorbs over 30% workforce and provides livelihood to more than 50% of rural population, but contributes only 11% to national GDP in 2019. This is mainly because each year a large portion of crops are wasted due to pests and diseases and also due to obsolete farming practices. It is believed, therefore, that timely farmers’ complaint resolution and access to information and expertise advice is vital to achieve sustainable and quality agriculture production. The existing farmers’ complaint management process follows a conventional query submission approach where farmers deliver, usually manually, their complaints and needs for support to their respective ‘agricultural associations’ distributed across Egypt. These, being in Arabic text, are received and then submitted to one of the national ‘centers’ distributed over the country to offer support for farmers in their villages. Several agricultural experts working at these centers subsequently process farmers’ enquiries, either instantly or by consulting the Agricultural Research Center via an interface designed for the purpose. A recommendation is usually provided. Most of the times, however, a ‘no known solution’ is delivered ‘ usually via phone calls. The portal provided by ARC offers access to a database of complaint-support pairs, which can sometimes features issues of inconsistency, redundancy, lack of structure, or missing value. The flow of the existing manual querying system is shown as Fig. 1. Even with a swift ‘‘round” of consultancy provided by the system, response from experts can get significantly delayed, mainly due to a large number of sent queries . Consequently, farmers, get an answer when it is too late for them to act. Similarly, the support provided by experts deals only with farmers’ instant complaints, lacking near future perspective on developing circumstances, and thus advice.For nearly two decades, decision support systems and data analytics have become efficient tools for providing precision agriculture and farming. Recently, Big data technologies are being widely adapted in agriculture domain mainly because the agriculture related data sets are becoming extremely large and complex that it is becoming difficult to process them using on–hand data management tools and/or traditional data processing applications.
CropSyst is a DSS developed into a suite of programs, including a crop simulator, a weather forecast generator, GIS modeler program, and a watershed utility program. CropSyst aims to simulate and optimize features like the soil water budget, soil–plant nitrogen budget, crop canopy and root growth, and yield. The AquaCrop model evaluates the production of maize crop under semi-arid climate conditions. García-Vila and Fereres later combined an economic model with the Aqua Crop simulator to optimized farm-level irrigation. Paredes et al. analysed and predicted the impact of irrigation management strategies against yield and economic returns of maize crop. Giusti and MarsiliLibelli introduced an inference based fuzzy DSS to optimally find irrigation actions based on the crop and site characteristics and conserving the water usage. Perini and Susi discussed the design and development aspects of a pest management DSS that can be used by the members of advisory services including pest experts and technicians. Xu et al.introduced an agricultural ecosystem management systems to extracts,dutch buckets for sale manage and analyze data regarding terrain, land utilization and planting. Kurlavicˇius et al. introduced a DSS for sustainable agriculture to predict the optimal crops grown and animals kept in particular regions, The system also predicts the resources required to carry out these activities under the varying environmental conditions. Antonopoulou et al. introduced a Web-based DSS to let farmers find the appropriate crops based on their regional and environmental conditions and also provide the best cultivation strategies and periods.Kaloxylos et al. later, proposed implementation of a cloud-based FMIS for managing a greenhouse. Fountas et al., Tayyebi et al. and Tan proposed perspectives of cloud computing as the key drivers in future development of FMIS and precision agriculture. Big data mining can facilitate the extraction of useful information from complex, variable, and large volume of the dataset, therefore can improve a DSS’s accuracy in various fields. The Millennium Project; for example, has identified many interesting challenges related to clean water, sustainable developments, climate changes, population and resources etc. This project has advocated the use of big geospatial data to save energy with eco-routing, i.e., avoiding congestion, stopping at red lights, turning points, and identifying elevation changes. Furthermore, a fuel consumption minimising technique has been proposed to achieve best travel time with reduced travel distance.
Recently, an unprecedented growth of Data Force Analytics enabled utilisation of big data technologies and digital sensors to manage data efficiently. Adopting such an approach in the field of agriculture can bring many benefits to support decisions. Nevertheless, data analytics still faces many challenges of handling extensive data and diverse data sets like semi-structured, unstructured, and streaming data. Therefore, in such Data Force Analytics developments there will be a strong need to effectively utilise datasets to facilitate users in finding their needs efficiently and effectively e.g. a qualitative study in points out a co-evolving tool to understand such needs/skills. Recently, organisations have started to use the concept of SelfService Analytics to encourage professionals or workers to perform queries with IT support and generate reports independently. The framework proposed in provides matrix called the governance of Self-Service Analytics , which uses the power of business intelligence tools and platform to support ITenabled analytic content development to help experts find the best solutions and get the decision rapidly. The geodatabase contains a visual analysis of tabular data to achieve the primary utilisation of practising BI system and GISs in data analytics. The Puerto de la Luz is a SmartPort solution, enabling real-time monitoring and collection of sensor data in a seaport infrastructure. It is a web-based GIS application, which uses an open-source big data architecture to achieve its functionality. The Spatial Decision Support System is an extension of DSS application, which supports an improvement in decision-making compared to non-spatial data. In particular, SDSS in agriculture has a positive impact on improving decision making.