Machine Learning Models for Intelligent Farmer Support Systems: A Comparative Approach Using Random Forest, Prophet, and YOLOv8

In this article, we highlight the role of agriculture in modern societies, not only for the economic development of many countries, but especially for regions with pressing needs and underdevelopment where the majority of the population relies on agriculture for survival. Today, with great technological advances, agriculture has moved beyond rudimentary methods, adopting a gigantic advancement with artificial intelligence (ML), which has transformed and given a boost to farmers, making production more relevant and improving its performance. This sector has been crucial for the development and economic growth of many nations, contributing to and positively impacting the gross domestic product of many developed and non-developed countries.

The challenges for farmers are still many, ranging from soil preparation, seed selection, auxiliary technological means, paced support platforms, disease detection, non-mechanized irrigation, self-sufficient harvesting with autonomous systems, yield forecasting, weed control, etc. This study presents an in-depth analysis of the significant advancements in information and communication technologies in this sector, which have revolutionized it. From machine learning, which has naturally been the biggest and most effective driver of this activity through autonomous data monitoring and control processes and methods, this study presents the different machine learning methods employed in agriculture, highlighting their advantages and challenges, and generating tangible and visible results aimed at bringing autonomy to farmers. Models such as Random Forest, YOLOv8, and Prophet are ML-based models coupled with artificial intelligence, capable of providing prompt and effective real-time responses. The study also includes a comparison focused on these models, their operations, and their major advantages in the world of technological modernity.

© 2026 — Authors retain the copyright of this article. This is an open access article distributed under the Creative Commons Attribution License (CC BY 4.0) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.