Abstract

As the world faces growing challenges in ensuring food security, predicting crop yields accurately be- comes increasingly crucial. Traditionally, this prediction re- lied on methods limited by their inability to handle complex interactions between various factors like climate, soil, and farming practices. This is where Machine Learning (ML) emerges as a gamechanger. By harnessing the power of data-driven insights, ML offers highly accurate predictions surpassing traditional methods. This paper specifically dives into the potential and challenges of utilizing ML for crop yield prediction, highlighting its strengths and areas for further development. While traditional approaches often fall short in capturing the intricate relationships impacting yield, the proposed method leverages satellite imagery to extract valuable features and deliver precise predictions on granular levels. Ultimately, this paves the way for farmers to make informed decisions, optimize resource allocation, maximize production, and contribute significantly to global food security.