Detecting Invasive Alien Plant Species Using Remote Sensing, Machine Learning and Deep Learning
Journal of Sensors · 2024-01 · 2024 (1)
DOI: 10.1155/2024/8854675 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Sensors, online erschienen am 12.11.2024. Verfasst von Perry B. Rakgoale und 1 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 173 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation.
Abstract (Originalsprache)
Invasive alien plants (IAPs) are nonnative species that pose significant threats to the environment by outcompeting native vegetation and disrupting ecosystem functions. Efforts to monitor and eradicate IAPs have been limited due to the challenges in accurately identifying these plants using traditional remote sensing (RS) methods. This paper reviews the literature to identify the most accurate and reliable plant detection methods for IAPs. Advanced searches were conducted on ScienceDirect, Scopus and Institute of Electrical and Electronics Engineers (IEEE) Xplore databases using keywords such as ‘Remote Sensing (RS)’, ‘Machine Learning (ML)’, ‘Deep Learning (DL)’, ‘Invasive Alien Plant (IAP)’ and ‘detection’. The search yielded 1689 articles: 1129 focused on the RS methodologies, 303 on ML, 142 on DL and 115 combining all three approaches. The review found that the RF and support vector machine (SVM) algorithms are the most effective for detecting IAPs. This suggests that future research should prioritize the application of ML and DL techniques, particularly RF and SVM, due to their high potential for improving IAP identification and aiding in their eradication. These advancements align with Sustainable Development Goal (SDG) 15, which emphasizes the protection, restoration and sustainable use of terrestrial ecosystems, and SDG 8, which promotes sustained, inclusive and sustainable economic growth. Effective IAP management not only preserves biodiversity but also creates economic opportunities by improving land value and usability. This review underscores the importance of integrating advanced technological methods in environmental management to support both ecological and economic objectives.
Förderung
- National Research Foundation
Zitieren
APA
Rakgoale, P. B., & Ngetar, S. N. (2024). Detecting Invasive Alien Plant Species Using Remote Sensing, Machine Learning and Deep Learning. Journal of Sensors, 2024(1). https://doi.org/10.1155/2024/8854675
Vancouver
Rakgoale PB, Ngetar SN. Detecting Invasive Alien Plant Species Using Remote Sensing, Machine Learning and Deep Learning. Journal of Sensors. 2024;2024(1). doi:10.1155/2024/8854675
BibTeX
@article{Rakgoale2024,
author = {Rakgoale, Perry B. and Ngetar, Silas Njoya},
title = {Detecting Invasive Alien Plant Species Using Remote Sensing, Machine Learning and Deep Learning},
journal = {Journal of Sensors},
year = {2024},
volume = {2024},
number = {1},
doi = {10.1155/2024/8854675}
}
EUVIMED