MACHINE LEARNING-BASED ASSESSMENT OF LEAF-CUTTING ANT INFESTATION IN Eucalyptus FOREST PLANTATIONS
Main Article Content
Abstract
Background: Brazilian planted forests play a critical role in global wood and fiber production but face significant productivity challenges from pests and diseases. Leaf-cutting ants (Atta spp. and Acromyrmex spp.) are the main pest in the Brazilian planted forests and cause significant productivity losses every year. Identifying areas most susceptible to colony establishment and growth is crucial for implementing effective management strategies. This study aims to assess the influence of edaphoclimatic and landscape variables on the establishment and expansion of leaf-cutting ant colonies and identify the key factors driving their occurrence.
Results: Based on a decade of monitoring data from 33,000 Eucalyptus stands across five regions, Random Forest models reached accuracies of 83% for predicting initial nests and 78% for predicting large nests.
Conclusion: The machine learning models effectively detected both initial and large nests, revealing that edaphoclimatic and landscape conditions exert varying levels of influence across macro-regions.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
The published articles are freely distributed among researchers and social media, and all authors transfer the copyright to Cerne. The research findings can also be used in classroom teaching, conferences, dissertations/theses, and other applications without any restriction. We strongly recommend citing the article to reach a wider audience. The Author also declares that the work is original and free of plagiarism. The authors agree with the publication and are responsible for the accuracy of the information.