Maize plays a vital role in global food security, making accurate and timely yield prediction essential for effective agricultural planning, policy formulation and resource management. In recent decades, advances in remote sensing and machine learning have transformed crop yield forecasting by enabling scalable, data-driven and high-resolution assessments that outperform conventional agronomic approaches. This bibliometric analysis provides a comprehensive assessment of global research trends, collaboration patterns and thematic evolution in remote sensing and machine learning-based maize yield prediction from 2000–2025. A total of 493 peer-reviewed articles indexed in the Scopus database were analysed using established bibliometric techniques. The results reveal a strong annual growth rate of 15.34 %, with an exponential increase in publications after 2018, reflecting rapidly growing interest in digital and AI-driven agriculture. The United States and China emerge as dominant contributors, forming a highly influential collaborative core, while countries such as India and Brazil show increasing research engagement. Remote Sensing emerges as the most productive and influential journal in this field. Thematic analysis reveals a clear shift from traditional vegetation indices toward advanced non-linear approaches, including Random Forest, deep learning models and UAV. The growing emphasis on multi-source data fusion and artificial intelligence reflects the fields’ response to climate variability and the needs of precision agriculture. Overall, the integration of satellite observations with machine learning has become central to modern maize yield forecasting. Furthermore, these advancements hold strong potential to enhance sustainable farm management, climate resilience and global food security.
Sakthivel et al. (Wed,) studied this question.