The importance of artificial intelligence-based methods in precipitation modeling studies: a bibliometric analysis

Aydın O., Kılar H.

THEORETICAL AND APPLIED CLIMATOLOGY, cilt.156, sa.602, ss.1-20, 2025 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 156 Sayı: 602
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1007/s00704-025-05837-w
  • Dergi Adı: THEORETICAL AND APPLIED CLIMATOLOGY
  • Derginin Tarandığı İndeksler: Scopus, Science Citation Index Expanded (SCI-EXPANDED), Academic Search Premier, IBZ Online, PASCAL, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Artic & Antarctic Regions, BIOSIS, Environment Index, Geobase, Index Islamicus, INSPEC, CAB Abstracts, Pollution Abstracts, Veterinary Science Database
  • Sayfa Sayıları: ss.1-20
  • Ankara Üniversitesi Adresli: Evet

Özet

Modeling climate parameters is essential for understanding climate variability, tracking changes over time, adapting to

climate change, and assessing its impacts. Precipitation is especially important in climate science because it significantly

influences ecosystems, agriculture, extreme weather events, and the hydrological cycle. In this context, using Artificial

Intelligence (AI), Artificial Neural Networks (ANN), Machine Learning (ML), and Deep Learning (DL) methods in pre-

cipitation modeling has become a key area of research. This study was conducted using the “Clarivate Analytics Web

of Science (WoS)” database on September 17, 2024. A total of 112,721 articles that utilized AI methods in precipitation

modeling from 1995 to 2023 were reviewed. These articles were ranked by citation count, leading to the selection of 238

papers for further analysis. The study focuses on three time periods: 1995–2004, 2005–2014, and 2015–2023. The 238

identified articles received a total of 42,351 citations, averaging 177.95 citations per article. The average citation count

was highest in the first period (1995–2004) but declined in the 2015–2023 period. The journal with the most citations is

“Atmospheric Environment,” and the most cited paper is by Gardner and Dorling (1998). The “Journal of Hydrology”

has the highest H-index at 40. The most commonly used term in publications is “machine learning,” along with other

important terms like “precipitation,” “artificial neural networks,” “deep learning,” “rainfall,” and “rainfall-runoff.” In

conclusion, this study provides a bibliometric analysis of key topics related to precipitation modeling from 1995 to 2023,

highlighting directions for future research.