Identification of invasive trees in a Brazilian subtropical forest using remotely piloted aircraft systems and machine learning

Abstract. We aimed to combine the use of images obtained from remotely piloted aircraft systems (RPAS) and machine learning (ML) to identify the invasive alien species Psidium guajava in a protected area in southern Brazil. Field data were obtained in a sampling area, where the species’ geographic coordinates were collected with a global positioning system device. Remote data were collected with the Parrot Sequoia® multispectral camera onboard the Phantom 4® Pro platform. Image processing was used to generate reflectance maps and vegetation indices, after which four classes of interest were defined for model training. The supervised classification involved two approaches (pixel-based—BP and object-based image analysis—OBIA) and two ML algorithms compared (random forest—RF and support vector machine—SVM). For performance analysis, confusion matrices with user and producer accuracies, Kappa values and overall accuracy (OA) were calculated. The results demonstrate that the multispectral composition was excellent in identifying the invasive P. guajava, in an OBIA approach with the RF algorithm (0.90 Kappa and 93% OA). Thus, considering the priority of biodiversity conservation and the importance of the Brazilian Atlantic Forest for the maintenance of endemic and endangered species, we present a robust methodology to identify the invasive species P. guajava in subtropical forest, which can be applied in management strategies for the species control and eradication.

• Publication year

  2023

• Venue

  Journal of Applied Remote Sensing

• Publication date

  2023-07-01

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1117/1.JRS.17.034514
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

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

  2023influential reference
• Comparison of Random Forest and Support Vector Machine Classifiers for Regional Land Cover Mapping Using Coarse Resolution FY-3C Images

  2022cited by this paper
• Surprisingly high economic costs of biological invasions in protected areas

  2022cited by this paper
• Remotely Piloted Aircraft Systems (RPAS) and machine learning: A review in the context of forest science

  2021cited by this paper
• Geospatial Approaches to Monitoring the Spread of Invasive Species of Solidago spp

  2021cited by this paper
• The economic costs of biological invasions in Brazil: a first assessment

  2021cited by this paper
• Monitoring Invasive Plant Species Using Hyperspectral Remote Sensing Data

  2021cited by this paper
• Distribution of Invasive Alien Species in Brazilian Ecoregions and Protected Areas

  2021cited by this paper
• Comparison of Support Vector Machine and Random Forest Algorithms for Invasive and Expansive Species Classification Using Airborne Hyperspectral Data

  2020cited by this paper
• Vegetation Index Based In Unmanned Aerial Vehicle (Uav) To Improve The Management Of Invasive Plants In Protected Areas, Southern Brazil.

  2020cited by this paper
• ESPÉCIES EXÓTICAS INVASORAS EM UNIDADES DE CONSERVAÇÃO NA REGIÃO SUL DO BRASIL

  2019cited by this paper
• Multispectral Approach for Identifying Invasive Plant Species Based on Flowering Phenology Characteristics

  2019cited by this paper
• COMPOSIÇÃO ARBÓREA DA FLORESTA ESTACIONAL DECIDUAL EM RELAÇÃO A HETEROGENEIDADE AMBIENTAL NO REBORDO DO PLANALTO MERIDIONAL, RS

  2019cited by this paper
• UAV data as alternative to field sampling to map woody invasive species based on combined Sentinel-1 and Sentinel-2 data

  2019cited by this paper
• Mapping Vegetation at Species Level with High-Resolution Multispectral and Lidar Data Over a Large Spatial Area: A Case Study with Kudzu

  2019influential reference
• Object-Based Land Cover Classification of Cork Oak Woodlands using UAV Imagery and Orfeo ToolBox

  2019influential reference
• How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing

  2019cited by this paper
• Forest habitat invasions – Who with whom, where and why

  2018cited by this paper
• Mapping the Flowering of an Invasive Plant Using Unmanned Aerial Vehicles: Is There Potential for Biocontrol Monitoring?

  2018cited by this paper
• R S Y N T H E S I S Neighbour tolerance, not suppression, provides competitive advantage to non-native plants

  2018cited by this paper
• Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data

  2018cited by this paper
• SENSORIAMENTO REMOTO NO ESTUDO DA VEGETAÇÃO: PRINCÍPIOS FÍSICOS, SENSORES E MÉTODOS.

  2018cited by this paper
• Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

  2017cited by this paper
• Invasive Plant Species of the World: A reference guide to environmental weeds

  2017cited by this paper
• Plant invasion science in protected areas: progress and priorities

  2017cited by this paper
• Random forest in remote sensing: A review of applications and future directions

  2016cited by this paper
• Classification Methods For Remotely Sensed Data

  2016cited by this paper
• Assessment of Red-Edge Position Extraction Techniques: A Case Study for Norway Spruce Forests Using HyMap and Simulated Sentinel-2 Data

  2016cited by this paper
• Estimating Forest Aboveground Biomass by Combining Optical and SAR Data: A Case Study in Genhe, Inner Mongolia, China

  2016cited by this paper
• The Global Invasive Species Database

  2016cited by this paper
• CARACTERIZAÇÃO ESPECTRAL E NDVI DE ESPÉCIES FLORESTAIS DAS FAMÍLIAS FABACEAE, MYRTACEAE, RUTACEAE E SALICACEAE

  2016cited by this paper
• ANÁLISE DERIVATIVA DE DADOS DE REFLECTÂNCIA OBTIDOS POR ESPECTRORRADIOMETRIA PARA CARACTERIZAÇÃO DE ESPÉCIES ARBÓREAS

  2016cited by this paper
• Review of studies on tree species classification from remotely sensed data

  2016cited by this paper
• How much do we know about distribution and ecology of naturalized and invasive alien plant species? A case study from subtropical southern Brazil

  2015cited by this paper
• Índice de Vegetação por Diferença Normalizada para Caracterização da Dinâmica Florestal no Parque Estadual Quarta Colônia, Estado do Rio Grande do Sul-Brasil (Normalized Difference Vegetation Index for Characterization of Forest Dynamic in Parque...)

  2015cited by this paper
• Object-Based Urban Tree Species Classification Using Bi-Temporal WorldView-2 and WorldView-3 Images

  2015influential reference
• Relação solo-vegetação em remanescente da floresta estacional decidual na Região Central do Rio Grande do Sul

  2014cited by this paper
• Köppen's climate classification map for Brazil

  2013cited by this paper
• Towards automatic lithological classification from remote sensing data using support vector machines

  2010cited by this paper
• Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data

  2010cited by this paper
• Brazilian Atlantic Forest lato sensu: the most ancient Brazilian forest, and a biodiversity hotspot, is highly threatened by climate change.

  2010cited by this paper
• Allelopathic evidence in exotic guava (Psidium guajava L.)

  2010cited by this paper
• Citrus aurantium L. (laranja-apepu) e Hovenia dulcis Thunb. (uva-do-japão): espécies exóticas invasoras da trilha do Poço Preto no Parque Nacional do Iguaçu, Paraná, Brasil

  2008cited by this paper
• Psidium guajava: a review of its traditional uses, phytochemistry and pharmacology.

  2008cited by this paper
• A broad-band leaf chlorophyll vegetation index at the canopy scale

  2008cited by this paper
• Wide Dynamic Range Vegetation Index for remote quantification of biophysical characteristics of vegetation.

  2004cited by this paper
• Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture

  2004cited by this paper
• Plant Invaders. The Threat to Natural Ecosystems

  2004cited by this paper
• An assessment of support vector machines for land cover classification

  2002cited by this paper
• Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture

  2002cited by this paper
• Mean Shift: A Robust Approach Toward Feature Space Analysis

  2002cited by this paper
• Random Forests

  2001cited by this paper
• Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance

  2000cited by this paper
• Global biodiversity scenarios for the year 2100.

  2000cited by this paper
• The Nature of Statistical Learning Theory

  2000cited by this paper
• A comparison of vegetation indices over a global set of TM images for EOS-MODIS

  1997cited by this paper
• Optimization of soil-adjusted vegetation indices

  1996cited by this paper
• Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation

  1994cited by this paper
• A Modified Soil Adjusted Vegetation Index

  1994cited by this paper
• A soil-adjusted vegetation index (SAVI)

  1988cited by this paper
• Growth Inhibition from Guava Root Exudates

  1983cited by this paper
• The measurement of observer agreement for categorical data.

  1977cited by this paper
• Monitoring vegetation systems in the great plains with ERTS

  1973cited by this paper
• Monitoring the Vernal Advancement and Retrogradation (Green Wave Effect) of Natural Vegetation. [Great Plains Corridor]

  1973cited by this paper
• Occurrence of Plant Growth Inhibitors in Tropical and Subtropical Vegetation

  1969cited by this paper
• An Analysis of Variance Test for Normality (Complete Samples)

  1965cited by this paper

• No citing papers are available for this paper.