The Application of Artificial Intelligence for Predicting Genetic and Population Dynamics of Coffee Pollinators: A Comprehensive Global Insights

¹ Department of Biology, Universitas Lampung, Jl. Sumantri Brojonegoro 1, Bandar Lampung, Indonesia
² Department of Computer Science, Universitas Lampung, Jl. Sumantri Brojonegoro 1, Bandar Lampung, Indonesia
³ Department of Plantation Crops Cultivation, Politeknik Negeri Lampung, Jl. Sukarno-Hatta 10, Bandar Lampung, Indonesia
⁴ Center for Biomedical Research, National Research and Innovation Agency (BRIN), Cibinong-Bogor, Indonesia

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Coffee is a globally important agricultural commodity whose productivity and long-term sustainability are highly dependent on insect pollinators, particularly bees, which play a crucial role in pollination efficiency, genetic diversity, and yield stability. Recent advances in artificial intelligence (AI) offer promising tools for predicting pollinator genetic patterns and population dynamics; however, existing research in this area remains fragmented across multiple disciplines. This study employed a systematic bibliometric approach to examine global research trends in AI applications for predicting the genetics and population dynamics of coffee pollinators, based on an analysis of 172 Scopus-indexed publications published between 2003 and 2023. Descriptive statistics and network visualization techniques, including co-authorship, co-citation, keyword co-occurrence, and density analyses, were conducted using the VOSviewer to identify collaboration patterns and underlying thematic structures. The results revealed a marked increase in research output after 2015, reflecting growing interdisciplinary integration among artificial intelligence, ecology, and agricultural sciences. Research activity was predominantly concentrated in countries with strong AI capabilities and research infrastructures, while major coffee-producing countries such as Indonesia demonstrated moderate but steadily increasing contributions. Thematic analyses further indicated that studies on coffee pollinators are largely embedded within broader AI-driven agriculture, genomics, and environmental research frameworks suggesting that this field represents an emerging research domain that remains underdeveloped in terms of focused empirical investigation. Overall, this review underscores the considerable potential of AI-based approaches to advance coffee pollinator management and highlights the need for more targeted, interdisciplinary research to support sustainable coffee production.