Camile Sothe

Camile Sothe
McMaster University | McMaster · School of Earth Environment & Society

PhD in Remote Sensing

About

26
Publications
6,976
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
254
Citations
Introduction
PhD in Remote Sensing (National Institute for Space Research -INPE). Bachelor's degree and MSc. in Forest Engineering (Santa Catarina State University - UDESC)
Additional affiliations
February 2016 - December 2019
National Institute for Space Research, Brazil
Position
  • PhD Student

Publications

Publications (26)
Article
Full-text available
Terrestrial ecosystems of Canada store a large amount of organic carbon (C) in soils, peats and plant materials, yet little is known about the C stock size and distributions, both spatially and in various C pools. As temperature rises, C is becoming available for disturbance, decomposition and eventual release into the atmosphere, which makes the q...
Article
Full-text available
Canada has extensive forests and peatlands that play key roles in global carbon cycle. Canadian soils and peatlands are assumed to store approximately 20% of the world’s soil carbon stock. However, the spatial and vertical distributions of the soil organic carbon (SOC) concentration in Canada have not been systematically investigated. SOC concentra...
Article
This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data. Our model implements a partial loss function that enables dense tree semantic labeling outcomes from non-dense training samples, and a distance regression com...
Preprint
Full-text available
This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data. Our model implements a partial loss function that enables dense tree semantic labeling outcomes from non-dense training samples, and a distance regression com...
Article
Full-text available
The Atlantic Rainforest biome, where fire events were originally less frequent, is now increasingly at risk of burning due to anthropogenic influences on the climate and landscape. Identifying fire patterns and their leading causes in tropical forests is essential to improve prevention and fire management. We applied a filtering algorithm to remove...
Preprint
The Atlantic Rainforest biome, where fire events were originally less frequent, are now increasingly at risk of burning due to anthropogenic influences on the climate and landscape. Identifying fire patterns and their leading causes in tropical forests is essential to improve prevention and fire management. We applied a filtering algorithm to remov...
Conference Paper
Full-text available
O mapeamento de susceptibilidade é uma tarefa fundamental para prevenir impactos sociais e ambientais decorrentes de deslizamentos de terra, que possibilita identificar as áreas com maior ou menor probabilidade deste tipo de evento ocorrer. Este trabalho emprega uma abordagem espacial baseada em Modelos Aditivos Generalizados (GAM) associado a fato...
Article
Full-text available
The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced feature extraction and classification methods. Different from the traditional feature extraction methods, that highly depend on user’s knowledge, the convolutional neural networ...
Article
The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced classification methods. This study investigated the following topics concerning the classification of 16 tree species in two subtropical forest fragments of Southern Brazil: i)...
Article
In the case of tree species delineation with very high spatial resolution (VHR) images, is desirable that each segment corresponds to one individual tree crown (ITC). However, in order to have a segmentation algorithm that generates segments matching to ITCs, its parameters ought to be properly tuned. Aiming to avoid time-consuming trial-and-error...
Article
This work explores the integration of airborne Light Detection and Ranging (LiDAR) data and WorldView-2 (WV2) images to classify the land cover of a subtropical forest area in Southern Brazil. Different deep and machine learning methods were used: one based on convolutional neural network (CNN) and three ensemble methods. We adopted both pixel- (in...
Article
Full-text available
The use of remote sensing data for tree species classification in tropical forests is still a challenging task, due to their high floristic and spectral diversity. In this sense, novel sensors on board of unmanned aerial vehicle (UAV) platforms are a rapidly evolving technology that provides new possibilities for tropical tree species mapping. Besi...
Conference Paper
Full-text available
Progress in tree species mapping with hyperspectral data usually is limited by the multi-class classification framework, which imposes the requirement of exhaustively defining all species encountered in a landscape. As the research objective may be to map only one or a few species of interest, it is necessary to explore alternative classification m...
Article
Full-text available
Neste artigo, é analisada a distribuição espacial da suscetibilidade a movimentos de massa da Bacia Hidrográfica do Rio Luís Alves, localizada no estado de Santa Catarina. A modelagem empregada baseia-se em processos pontuais espaciais, na qual se define uma medida de suscetibilidade que varia continuamente sobre a região de estudo e é estimada por...
Article
Full-text available
Mass movement is a natural phenomenon frequently associated with damages to the society. Its inventories assist the comprehension of mass movement spatial distribution and susceptibility. Thus remote sensing techniques enable detection and mapping of mass movement scars worldwide in large scales and in areas of diffi cult access. However, its use i...
Article
Full-text available
Resumo: A classificação remota dos diferentes estádios sucessionais da vegetação ainda constitui um desafio devido à similaridade espectral destas classes. Este artigo tem o objetivo de avaliar o desempenho de imagens Landsat-8 e RapidEye para a classificação do estádio sucessional da vegetação em um fragmento de Floresta Ombrófila Mista, localizad...
Article
Full-text available
Studies designed to discriminate different successional forest stages play a strategic role in forest management, forest policy and environmental conservation in tropical environments. The discrimination of different successional forest stages is still a challenge due to the spectral similarity among the concerned classes. Considering this, the obj...
Article
Full-text available
RESUMO Este estudo realizou o levantamento de 465 autos de infração ambiental (AIA) lavrados na área de abrangência da Polícia Militar Ambiental (PMA) de Tijucas, no período de 2010 até 2014. Para a análise, utilizou-se a estatística descritiva aliada com informações obtidas na literatura. Os resultados mostraram que as principais tipificações da á...
Conference Paper
Full-text available
Mass movements are destructive natural phenomena that can lead to serious problems such as economic loss, damage to natural resources and even injuries and deaths. Efforts have been made to semi automate the interpretation of remote sensing data in order to improve efficiency and support specialists in recognizing mass movements' scars. However, th...
Conference Paper
Full-text available
In the past, different approaches for automated mass movements identification based on multispectral orbital images were developed to focus on the analysis of the spatial distribution of mass movements occurrences related to distinct triggering events. However, a continual multi-temporal analysis is important for monitoring vegetation recovery of a...
Article
Full-text available
This study aimed to evaluate open source softwares in order to classify secondary successional forest stages in Shade Tolerant Mixed Forest (FOM) environments in Southern Brazil. Two test sites were selected in the mountainous region of Santa Catarina State. We used scenes from the airborne system for acquisition and post-processing of images (SAAP...
Article
Full-text available
The aim of the study was to evaluate the yield of raw Cupressus lusitanica Mill wood by the tangential sawing process for two diameter classes, from 20 to 27 cm (I) and greater than 27.1 cm (II). The performance evaluation of the sawing process was performed by the determination of yield: gross, with cross-sectional sections with knots, with transv...

Projects

Project (1)
Project
Determine Cupressus lusitanica Mill. wood characteristics are necessary to understand how different conifer species grow at Santa Catarina State plateau and what is the most valuable industrial use.