A scientometric study on Artificial Intelligence for landslide prediction: Trends, collaborations, and advances
Open Access
- 21 August 2025
- journal article
- Published by CPRM in Journal of the Geological Survey of Brazil
- Vol. 8 (3)
Abstract
This scientometric study analysed 1,834 publications (2009–2023) on artificial intelligence applications in landslide prediction, revealing rapid growth (26.66% annual citation rate) with an average of 45.80 citations per paper. Despite the increased number of publications, the citation impact has not increased proportionally. The top 25 authors contributed 50.87% of the total output, while international collaborations (42.42% of papers) drove progress, with China and Vietnam as key contributors. Funded research (1,307 papers) generated 59,863 citations. Geology dominated the discipline, although agriculture achieved the highest citation impact. Q1 journals (e.g. Catena and Landslides) outperformed Q2 venues (e.g. Remote sensing) in terms of citations. Among the 227 highly cited papers (12.38% of the total), the average citation count was 215.1. The core themes included machine learning, landslide susceptibility, and deep learning. The findings highlight AI’s multidisciplinary potential of AI but underscore the need for enhanced international collaboration, explainable AI for model transparency, and strategies to mitigate citation biases to maximise research impact.Keywords
This publication has 31 references indexed in Scilit:
- Machine learning and deep learning-based landslide susceptibility mapping using geospatial techniques in Wayanad, Kerala state, IndiaHydroResearch, 2025
- Application of artificial intelligence in three aspects of landslide risk assessment: A comprehensive reviewRock Mechanics Bulletin, 2024
- Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessmentEnvironmental Science and Pollution Research, 2024
- Global Stem Cell Research in Orthopaedics: A Bibliometric Study from 1995 to 2020Indian Journal of Orthopaedics, 2024
- Artificial intelligence and machine learning for disaster prediction: a scientometric analysis of highly cited papersNatural Hazards, 2024
- Global research output and highly-cited publications on prosthetic joint infections: A bibliometric analysis (2003-2022)Journal of Clinical Orthopaedics and Trauma, 2024
- How many authors are (too) many? A retrospective, descriptive analysis of authorship in biomedical publicationsScientometrics, 2024
- Deep Learning in Landslide Studies: A Review2023
- Literature review and bibliometric analysis on data-driven assessment of landslide susceptibilityJournal of Mountain Science, 2022
- Landslide susceptibility mapping & prediction using Support Vector Machine for Mandakini River Basin, Garhwal Himalaya, IndiaGeomorphology, 2017