SYSTEMATIC REVIEW article
Front. For. Glob. Change
Sec. Forest Management
K-means classification of long-term global vegetation index variation
Provisionally accepted
- 1KNU G-LAMP Project Group, Kyungpook National University, Daegu, Republic of Korea
- 2KNU G-LAMP Project Group; BK21 Weather Extremes Education & Research Team, Kyungpook National University College of Natural Sciences, Daegu, Republic of Korea
- 3Korea Institute of Atmospheric Prediction Systems, Dongjak-gu, Republic of Korea
- 4KNU G-LAMP Project Group; Department of Statistics, Kyungpook National University College of Natural Sciences, Daegu, Republic of Korea
- 5National Institute of Meteorological Sciences, Seogwipo-si, Republic of Korea
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
This study investigates global vegetation changes based on the Normalized Difference Vegetation Index (NDVI) in response to recent global warming during 1982–2022. The NDVI trend exhibited an increasing tendency in Europe, western Russia, India, China, and Central Africa, whereas it declined over Canada, South America, South Africa, and eastern Central Asia. In order to objectively categorize the long-term change of NDVI variability, this study attempted a classification of NDVI frequency changes using the k-means clustering. Arid and semi-arid regions exhibited persistently low NDVI values, whereas high-latitude tundra and transitional zones showed strong seasonal variations and extended growing seasons due to rising temperatures. Subtropic-midlatitude humid regions showed seasonal fluctuations linked to cropping cycles, while tropical rainforests maintained high NDVI values but with increasing variability over time. The k-means clustering results also indicated that vegetation diversity has been increasing in response to global warming and hydrological cycle changes. Additionally, NDVI trends suggested an overall extension of vegetation growth periods, with earlier spring leaf-out and prolonged autumn retention in many regions. These findings have important implication in terms of providing a new insight on vegetation-climate interactions, thereby serving as a robust basis for further process-based predicting ecosystem-climate feed backs.
Keywords: NDVI, vegetation, Global Warming, K-Means clustering, Calinski–Harabasz-Index
Received: 31 Aug 2025; Accepted: 28 Nov 2025.
Copyright: © 2025 Choi, Song, Gim, Kim and Park. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Hwan-Jin Song
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.