Over the years, economic loss in the agricultural sector has been attributed to the late detection of varying plant diseases due to incongruent detection technologies. With the advent of disruptive technologies and their deployment, such as incorporating artificial intelligence (AI) models into unmanned autonomous vehicles for real-time monitoring, the curtailment of losses and inadvertent waste of agricultural produce can be significantly addressed. This study examines the role of deploying AI models in improving the early and accurate detection of crop lesions for prompt, intuitive, and decisive action to forestall recurrence and guarantee a return on investment to farmers. Furthermore, the chapter established scientific basis for the acceleration of crop yields through allied mechano-biosynthesis in a quest to cushion the effect of the contemporary global food crisis. Connected intelligence in smart farming can be achieved through convergence technology for cost effective agro-allied production by improving the limitations of UAVs and AI-models.
Top1.0 Introduction
Agriculture is among the most prevailing sectors contributing to the world’s economy, as the consumption of farm produce is integral to man’s existence and survival. However, agricultural yield is susceptible to biotic stresses caused by pathogens (that is, viruses, bacteria, and fungi) in plants leading to significant losses in terms of decreased productivity (Kulkarni, 2018), when not attended to during the early stages. With the increasing number of farmers around the world and the adoption of emerging technologies, it is still very challenging to provide adequate food to the constantly growing population of humans. Crop disease inhibits food availability (Gao et al., 2020), promotes food scarcity, and incurs agricultural and economic losses to farmers. According to Ahmad et al. (2021), annual crop losses worldwide caused by plant disease are approximately $60billion. Regrettably, a substantial proportion of exported fruits are rejected annually due to symptoms of fruit diseases (Kulkarni, 2018). Therefore, early disease detection using cognitive capabilities innovative technologies guarantees quality crop output (Zhang et al., 2020). The introduction of technology as an enabler to accelerate the overall farming process and guarantee increased productivity is termed smart farming or smart agriculture. It involves the deployment of cognitive methods and machines for responsive, timely, tractable, and trustworthy evaluation of agricultural activities such as crop monitoring, disease detection, livestock management, etc. With smart farming, expended efforts by farmers can be eased while increasing the quantity, quality, and efficiency of the agricultural production process. However, these cognitive methods and machines need to work synergistically to optimize their utility in any agricultural setting and ensure good returns on investment.
Smart farming/agriculture for early plant disease detection entails the convergence of varied disruptive technologies such as the embedded cognition capacity of artificial intelligence (AI) algorithms, edge computing, and networks, coupled with the autonomous navigation capability of unmanned aerial vehicles (UAVs) otherwise called drones, for real-time monitoring of the developmental stages and healthiness of plants for intuitive inferencing and evidence-based conclusions and decisions. Currently, advancement in agriculture is engineered via converging technologies such as UAVs, Internet of Things (IoT), Deep Learning (DL) algorithms, wireless sensor networks, and cloud computing (Ajakwe et al., 2023d; Ramli et al., 2020). These technological advancements are to necessitate precision agriculture (PA). PA is an act that gathers, maps, and analyses data based on agricultural land variability and helps to draw relevant and useful inferences for proactive farm management decisions based on the results of such analysis, coupled with a proper application of pesticides and fertilizers in a controlled manner. Crop disease monitoring and control is a crucial aspect of smart agriculture facilitated by PA with regards to timely intervention. Manual monitoring of crop disease is capital and labor-intensive, time-consuming, and highly erroneous, thereby reducing production targets. The introduction of modifiable UAVs to enable agricultural processes is one of the phenomenal benefits of PA.