Artificial intelligence and machine learning applications in agricultural supply chain: a critical commentary

Abstract

Integration of AI and ML technologies in the agricultural supply chain (ASC) is revolutionalizing, the domain by bringing in robust monitoring and prediction as well as quick decision-making abilities. A comprehensive literature analysis of the applications of artificial intelligence methods and machine learning algorithms in the agricultural supply chain is demonstrated in this study. In order to solve complicated challenges confronted by various areas of the agricultural supply chain, this literature analysis addresses different significant works that machine learning and artificial intelligence methods are used. Different AI and ML applications were suggested for the following areas of agriculture belonging to different phases: (i) crop yield prediction, prediction of soil properties and irrigation management; (ii) weather prediction, disease detection and weed detection, (iii) demand management and production planning, (iv) transportation, storage, inventory and retailing. In order to remain unbiased and objective, different studies from different journals were analyzed for each phase. It is observed that the majority of these studies focus on crop yield and soil properties prediction. It is also inferred that artificial neural networks, support vector machines, utilization of unmanned aerial vehicles, and remote sensors are fairly popular in the agriculture discipline.