Towards an Efficient Recommender Systems in Smart Agriculture: A deep reinforcement learning approach
Mohamed Bouni, Badr Hssina, Khadija Douzi, Samira Douzi
Abstract
A profitable agriculture system is the fundamental foundation of a rising economy. Precise prediction of crop yield focuses primarily on agriculture research that has a significant effect on making decisions such as import-export, pricing, and distribution of specific crops. There is a severe need to utilize advanced technologies in order to improve yield quality and creation, anticipate crop yields, and study crop diseases/infections. The most prevalent issue among farmers is that they do not select the appropriate crop based on their soil needs. As a result, they see a significant decrease in production. In this paper, we presented a deep reinforcement learning (DRL)-based crop classification system for precision agriculture selection to solve the farmers' dilemma. DRL-based advanced agriculture techniques eliminate bad options and boost production in the crop recommendation system. We compared the proposed recommendation system with the various machine learning algorithms, such as Random Tree, Naive Bayes, and K-Nearest Neighbor, for a site-specific crop with effective accuracy.