HIGH-ACCURACY SVM CLASSIFICATION OF CERRADO VEGETATION USING PLANETSCOPE IMAGERY

- 319211
Poster
Favorite this paper
How to cite this paper?
Abstract

The Cerrado biome is one of the most biodiverse yet threatened in South America due to human activities, leading to biodiversity loss and environmental impacts. This study applied Support Vector Machine to classify the main Cerrado vegetation formations within a protected area, aiding monitoring efforts. The model achieved high accuracy (97.51%). Over the four years (2020-2024), class distribution remained stable, except during extreme events like the 2022 frost. The study also mapped areas dominated by Pteridium esculentum, concentrated near gallery forests. These maps provide valuable insights into vegetation dynamics, supporting conservation efforts against increasing anthropogenic threats.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Instituto Federal de Educação, Ciência e Tecnologia de Brasília
  • 2 Instituto Brasileiro de Geografia e Estatística (IBGE), Gerência de Meio Ambiente e Geografia
  • 3 Graduate Program in Natural Disasters (Unesp/CEMADEN)
Track
  • 14. Artificial intelligence for earth observation
Keywords
Machine Learning
Conservation Unit
Remote Sensing