Foundation Models in Agriculture: A Comprehensive Review

Abstract

This paper explores the transformative potential of Foundation Models (FMs) in agriculture, driven by the need for efficient and intelligent decision support systems in the face of growing global population and climate change. It begins by outlining the development history of FMs, including general FM training processes, application trends and challenges, before focusing on Agricultural Foundation Models (AFMs). The paper examines the diversity and applications of AFMs in areas like crop classification, pest detection, and crop image segmentation, and delves into specific use cases such as agricultural knowledge question-answering, image and video analysis, decision support, and robotics. Furthermore, it discusses the challenges faced by AFMs, including data acquisition, training efficiency, data shift, and practical application challenges. Finally, the paper discusses future development directions for AFMs, emphasizing multimodal applications, integrating AFMs across the agricultural and food sectors, and intelligent decision-making systems, ultimately aiming to promote the digitalization and intelligent transformation of agriculture.