Climate Change, Deep Learning, and Plant Disease: A Bibliometric Analysis (2000-2025)

Abstract

Climate change is reshaping environmental conditions in ways that influence the occurrence, spread, and severity of plant diseases, creating growing challenges for agricultural productivity and global food security. At the same time, advances in artificial intelligence, particularly deep learning, have provided new opportunities for improving plant disease detection, diagnosis, and prediction. Although research on climate change and plant health, as well as deep learning applications in agriculture, has expanded considerably in recent years, studies combining these topics remain limited and dispersed. This study presents a bibliometric analysis of the scientific literature linking climate change, deep learning, and plant disease between 2000 and 2025. Bibliographic data were collected from the Scopus database using a structured search strategy. After screening and applying the inclusion criteria, 59 relevant publications were selected for analysis. The dataset was examined using Bibliometrix (R package) and VOSviewer to evaluate publication trends, influential authors, leading journals, productive countries and institutions, citation patterns, collaboration networks, and keyword relationships. Based on the results, the first publication linking climate change, deep learning, and plant disease was identified in 2019, showing the recent emergence of this research field. However, publication output has increased rapidly since then, with an annual growth rate of 51.31%, reflecting growing interest in the use of artificial intelligence to address climate-related agricultural challenges. The average document age of 2.76 years further confirms the recent and emerging nature of this field. Citation analysis demonstrated that the earliest publications have had a strong influence on subsequent research, particularly studies published in 2019 and 2020. Despite the increasing number of studies, important gaps remain, especially regarding the integration of climate data with advanced deep learning models for large-scale disease prediction. By providing a comprehensive overview of research trends, influential contributions, and emerging themes, this study offers valuable insights for researchers and policymakers working to develop climate-resilient and data-driven approaches for plant disease management.