Woody Plant Encroachment in a Seasonal Tropical Savanna: Lessons about Classifiers and Accuracy from UAV Images

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2023-04, Vol.15 (9), p.2342
• Main Authors: Costa, Lucas Silva, Sano, Edson Eyji, Ferreira, Manuel Eduardo, Munhoz, Cássia Beatriz Rodrigues, Costa, João Vítor Silva, Rufino Alves Júnior, Leomar, de Mello, Thiago Roure Bandeira, da Cunha Bustamante, Mercedes Maria
• Format: Article
• Language: English
• Subjects: Accuracy; Aerial surveys; Algorithms; Aridity; Biodiversity; Cameras; Cerrado; Classification; Classifiers; Color imagery; Decision trees; drone; Drone aircraft; Ecological function; Ecosystems; Encroachment; Environmental impact; Grasslands; Image acquisition; Image classification; Indigenous species; Machine learning; mesic biome; Mosaics; multispectral; object-based image analysis; plant invasion; Rainy season; Remote sensing; Savannahs; Seasons; Sensors; Support vector machines; Tropical environment; Tropical environments; Unmanned aerial vehicles; Woodlands; Woody plants
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15092342

Woody plant encroachment in grassy ecosystems is a widely reported phenomenon associated with negative impacts on ecosystem functions. Most studies of this phenomenon have been carried out in arid and semi-arid grasslands. Therefore, studies in tropical regions, particularly savannas, which are composed of grassland and woodland mosaics, are needed. Our objective was to evaluate the accuracy of woody encroachment classification in the Brazilian Cerrado, a tropical savanna. We acquired dry and wet season unmanned aerial vehicle (UAV) images using RGB and multispectral cameras that were processed by the support vector machine (SVM), decision tree (DT), and random forest (RF) classifiers. We also compared two validation methods: the orthomosaic and in situ methods. We targeted two native woody species: Baccharis retusa and Trembleya parviflora. Identification of these two species was statistically (p < 0.05) most accurate in the wet season RGB images classified by the RF algorithm, with an overall accuracy (OA) of 92.7%. Relating to validation assessments, the in situ method was more susceptible to underfitting scenarios, especially using an RF classifier. The OA was higher in grassland than in woodland formations. Our results show that woody encroachment classification in a tropical savanna is possible using UAV images and field surveys and is suggested to be conducted during the wet season. It is challenging to classify UAV images in highly diverse ecosystems such as the Cerrado; therefore, whenever possible, researchers should use multiple accuracy assessment methods. In the case of using in situ accuracy assessment, we suggest a minimum of 40 training samples per class and to use multiple classifiers (e.g., RF and DT). Our findings contribute to the generation of tools that optimize time and cost for the monitoring and management of woody encroachment in tropical savannas.