A bibliometric analysis on artificial intelligence-based irrigation modeling techniques over the period of 1997-2023

Abstract

A bibliometric analysis was performed over the period 1997–2023, to pinpoint important trends, emphasis, and geographic distribution of international irrigation modeling research using new intelligence-based approaches. We mined the data for this study from the databases of the online version of the Web of Science. The data was analyzed using the Excel program, and the bibliometric mapping was performed using the VOSviewer software. A total of 1627 articles met the required criteria. The findings indicated that the number of articles had increased rapidly over the past five years and that English was the prevalent language (≈100%). Researchers in 99 countries have published in this field of research. China ranked first with 401 articles (24.7%), followed by the United States of America with 276 articles (17.0%). Egypt and Saudi Arabia are two of the top 10 countries in the world for research on the use of artificial intelligence in irrigation modeling. These articles were published in 423 journals; Agricultural Water Management was the most productive journal (86 articles, 5.3%), followed by Computers and Electronics in Agriculture (82, 5.0%). The most productive author is Kisi Ozgur from Turkey (43 articles, 2.6%). Taking into account all the institutions working on irrigation modeling (2026 institutions), Egyptian Knowledge Bank was ranked first (75 articles, 4.6%), followed by Northwest A&F University (China) (69 articles, 4.2%). Artificial neural networks and machine learning were the most commonly used intelligence-based techniques for irrigation modeling. Reinforcement learning was the least popular technique for irrigation modeling, which could be due to its complexity and data requirements.