Modeling and detection of invasive trees using UAV image and machine learning in a subtropical forest in Brazil

• Published in: Ecological informatics Vol. 74; p. 101989
• Main Authors: da Silva, Sally Deborah Pereira, Eugenio, Fernando Coelho, Fantinel, Roberta Aparecida, Amaral, Lucio de Paula, dos Santos, Alexandre Rosa, Mallmann, Caroline Lorenci, dos Santos, Fernanda Dias, Pereira, Rudiney Soares, Ruoso, Régis
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.05.2023
• Subjects: biodiversity; Biological invasion. Biodiversity conservation. Remote sensing. OBIA. Mean-shift segmentation; Brazil; data collection; Hovenia dulcis; image interpretation; invasive species; model validation; species; support vector machines; surveys; tropical forests; Brazil; Biological invasion. Biodiversity conservation. Remote sensing. OBIA. Mean-shift segmentation
• ISSN: 1574-9541
• DOI: 10.1016/j.ecoinf.2023.101989

Protected areas play an extremely important role in the conservation of global biodiversity. However, these areas are subject to the introduction of invasive alien species (IAS), which cause damage to native environments. The present study aimed to use images obtained by Unmanned Aerial Vehicles (UAVs) combined with machine learning (ML) algorithms to identify the IAS Hovenia dulcis in a Conservation Unit in southern Brazil. Field data were obtained in a sample area, where the floristic survey of the H. dulcis species was carried out. To obtain remote data, a UAV with a built-in RGB sensor was used. Subsequently, the images were processed for orthomosaic generation and the spatial distribution of the inventoried species, based on manual photointerpretation. Furthermore, in the supervised classification process, four classes of interest were defined: H. dulcis, similar species, shade, and other species. The process involved two approaches (pixel-based - PB and object-based image analysis - OBIA) and two ML algorithms were compared (Random Forest - RF and Support Vector Machine - SVM). Samples were separated into 90% for training and 10% for model validation. For performance analysis, overall accuracy (OA) and Kappa index metrics were calculated. The results show that the RF algorithm in the PB approach had the best performance in the classification of the IAS H. dulcis, presenting a kappa of 0.87 and OA of 91.5%, in the training data set and 90.91% of success in the model validation dataset. Our study demonstrated to be able to reach the results to respond to the raised hypotheses. Furthermore, the UAV-RGB data combined with ML are highly accurate to identify H. dulcis in relation to the other species that make up the forest stratum of the study area. •Approach to identify invasive tree species in the Atlantic Forest biome•Detection of the invasive H. dulcis using UAV data and machine learning•Invasive species H. dulcis was identified with 90.91% of accuracy