Thiza Falqueto Altoé

Thiza Falqueto Altoé

Auto-generated profile, based on publicly available information

Thiza Falqueto Altoé

Federal University of Lavras, Brazil

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021 in CERNE
Verified
Journal Article
Open access
AGAnny Francielly Ataide Gonçalves
Anny Francielly Ataide Gonçalves
JSJuscelina Arcanjo Santos
Juscelina Arcanjo Santos
Luciano Cavalcante de Jesus FrançaLuciano Cavalcante de Jesus França
Luciano Cavalcante de Jesus França
OCOtávio Campoe
Otávio Campoe
TAThiza Falqueto Altoé
Thiza Falqueto Altoé
JSJosé Roberto Soares Scolforo
José Roberto Soares Scolforo

1 January 2019 in Floresta e Ambiente
Verified
Journal Article
Open access
PDF file
KPKalill José Viana da Páscoa
Kalill José Viana da Páscoa
JSJosé Roberto Soares Scolforo
José Roberto Soares Scolforo
AFAntonio Carlos Ferraz Filho
Antonio Carlos Ferraz Filho
TAThiza Falqueto Altoé
Thiza Falqueto Altoé
LGLucas Rezende Gomide
Lucas Rezende Gomide
This study aimed to evaluate the growth of Eremanthus erythropappus (DC.) MacLeish submitted to different planting spacing and growth modelling based on the diameter and crown area projection, as well as to identify the best management strategy to be applied to control the competition, period and intensity of thinning. The evaluated planting spacings were: 1.5 × 1.5 m; 1.5 × 2.0 m; 1.5 × 2.5 m and 1.5 × 3.0 m. Diametric growth modelling in function of the age and crown area projection according to the mixed models methodology was efficient and the individual tree modelling allowed for defining a correct thinning prescription for tree plantations in relation to the percentage of removal needed at each spacing, thus permitting the trees to grow free from competition and produce trees with larger diameters.

26 December 2019
Verified
Book Chapter
Open access
LSLuciane Naimeke Schmidt
Luciane Naimeke Schmidt
AGAnny Francielly Ataide Gonçalves
Anny Francielly Ataide Gonçalves
XOXimena Mendes de Oliveira
Ximena Mendes de Oliveira
LBLorena Barbosa
Lorena Barbosa
AFAlexandre Molino Fogli
Alexandre Molino Fogli
JSJosé Roberto Soares Scolforo
José Roberto Soares Scolforo
O conceito de biodiversidade está intimamente associado com a variedade genética capaz de diferenciar os indivíduos e suas respectivas populações. Portanto, a diversidade biológica é resultado do longo processo da história evolutiva, que permite a seleção do conjunto de espécies em um dado local. E, esse conjunto de espécies que compõe os ecossistemas fornece serviços fundamentais a existência da humanidade. No entanto, a extensa exploração antrópica promove diversas alterações na dinâmica dos ecossistemas, o que culmina, em muitos casos, na perda da biodiversidade local e consequentemente dos serviços ecossistêmicos. Isso nos impõe um grande desafio na atualidade: frear as pressões que oferecem riscos à biodiversidade global. Para tanto, conhecer essa biodiversidade presente em diferentes escalas (local, regional, global) pode representar o primeiro passo para proposição de medidas que visam a conservação, isto porque, esse mesmo conhecimento possibilita a construção de mapas de distribuição das espécies ao longo de gradientes ambientais, bem como a identificação daquelas que estão sob risco de extinção. Atualmente, há 34 áreas no mundo classificadas como Biodiversity Hotspots, correspondendo a áreas ricas em espécies endêmicas (aquelas que só ocorrem ali). Particularmente, o Brasil apresenta dois ecossistemas que incluem Hotspots (Floresta Atlântica e Cerrado) e ainda estima-se que nosso país possua cerca de 20% de toda a biodiversidade mundial, dados que nos colocam diante de uma problemática: temos estratégias potenciais para caracterização, conservação e manejo sustentável dessa biodiversidade? A obra "Biodiversidade Brasileira: Aspectos do Estado Atual 2" foi elaborada a partir da coletânea de trabalhos científicos, desenvolvidos por pesquisadores de diferentes instituições, e vislumbra contribuir para o aprofundamento do conhecimento acerca da biodiversidade brasileira sob diferentes aspectos. O e-Book contempla 6 capítulos, entre os quais encontramos discussões acerca da ocorrência e dinâmica de espécies em ecossistemas diversificados, como: marinhos, amazônicos e de cerrado. Além desses, um dos trabalhos aborda o emprego de ferramentas digitais na educação ambiental, com enfoque na conservação da biodiversidade. Desta forma, o presente volume é dedicado a discussão da biodiversidade brasileira e representa uma ferramenta de ampliação do conhecimento, sendo voltada a todos aqueles que tenham interesse em conhecer mais sobre a temática, sejam em instituições públicas ou privadas, pesquisadores ou acadêmicos de todos os níveis (graduação e pós-graduação). Desejamos que aqueles que buscam conhecer mais das riquezas biológicas de nosso país, encontrem nessa obra uma alternativa de conhecimento. Magnólia de Araújo Campos Daniele Jovem-Azevêdo

23 November 2022
Verified
Book Chapter
Closed access
PDF file
JBJoão Paulo Simões Branquinho
João Paulo Simões Branquinho
MCMônica Canaan Carvalho
Mônica Canaan Carvalho
TAThiza Falqueto Altoé
Thiza Falqueto Altoé
Luciano Cavalcante de Jesus FrançaLuciano Cavalcante de Jesus França
Luciano Cavalcante de Jesus França
Fausto Weimar Acerbi JúniorFausto Weimar Acerbi Júnior
Fausto Weimar Acerbi Júnior

27 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
MCMarcelo Vitor Gualberto Santo Chaves
Marcelo Vitor Gualberto Santo Chaves
MPMarcelo Lourençoni Pauletti
Marcelo Lourençoni Pauletti
MSMateus Gabriel de Souza
Mateus Gabriel de Souza
FCFrancisco Kimerling Campos
Francisco Kimerling Campos
KPKalill José Viana da Páscoa
Kalill José Viana da Páscoa
LCLuis Marcelo Tavares de Carvalho
Luis Marcelo Tavares de Carvalho
Monitoring deforestation within Legal Reserves (LRs) requires methods capable of integrating spectral, spatial, and temporal information over large areas. This study developed and evaluated a semantic segmentation model based on a U-Net++ architecture with an EfficientNet-B0 backbone to identify deforestation in LRs declared in the Brazilian Rural Environmental Registry (CAR) in the state of Pará. Temporal differences in NDVI, NBR, and NDRE derived from Harmonized Sentinel-2 MSI imagery were stacked as three input channels. The model-development dataset comprised 6,949 LRs, divided into 70% for training and 30% for validation. The best model was selected according to the lowest validation loss, and the final decision threshold was calibrated using the Matthews Correlation Coefficient (MCC) at the LR level. During validation, the model achieved an IoU of 0.6820 and a Dice coefficient of 0.8110 at the pixel level, as well as an F1-score of 0.9743 and an MCC of 0.9492 at the LR level. The independent test included 2,500 LRs balanced between deforested and non-deforested classes, each represented by two distinct temporal combinations (CT1 and CT2), in addition to a Maximum Fusion strategy based on pixel-wise probabilities. At the LR level, Maximum Fusion achieved the best overall performance, with an accuracy of 0.9216, F1-score of 0.9183, MCC of 0.8460, and sensitivity of 0.8808. At the pixel level, however, CT1 achieved the highest IoU (0.2294), indicating lower geometric agreement with PRODES polygons during independent testing. Overall, the model was more consistent in identifying the occurrence of deforestation within LRs than in reproducing its exact spatial geometry. The results also highlight the influence of temporal image selection and the potential of integrating multiple observations to support environmental monitoring.

17 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
MCMarcelo Vitor Gualberto Santo Chaves
Marcelo Vitor Gualberto Santo Chaves
MPMarcelo Lourençoni Pauletti
Marcelo Lourençoni Pauletti
MSMateus Gabriel de Souza
Mateus Gabriel de Souza
FCFrancisco Kimerling Campos
Francisco Kimerling Campos
KPKalill José Viana da Páscoa
Kalill José Viana da Páscoa
LCLuis Marcelo Tavares de Carvalho
Luis Marcelo Tavares de Carvalho
Monitoring deforestation within Legal Reserves (LRs) requires methods capable of integrating spectral, spatial, and temporal information over large areas. This study developed and evaluated a semantic segmentation model based on a U-Net++ architecture with an EfficientNet-B0 backbone to identify deforestation in LRs declared in the Brazilian Rural Environmental Registry (CAR) in the state of Pará. Temporal differences in NDVI, NBR, and NDRE derived from Harmonized Sentinel-2 MSI imagery were stacked as three input channels. The model-development dataset comprised 6,949 LRs, divided into 70% for training and 30% for validation. The best model was selected according to the lowest validation loss, and the final decision threshold was calibrated using the Matthews Correlation Coefficient (MCC) at the LR level. During validation, the model achieved an IoU of 0.6820 and a Dice coefficient of 0.8110 at the pixel level, as well as an F1-score of 0.9743 and an MCC of 0.9492 at the LR level. The independent test included 2,500 LRs balanced between deforested and non-deforested classes, each represented by two distinct temporal combinations (CT1 and CT2), in addition to a Maximum Fusion strategy based on pixel-wise probabilities. At the LR level, Maximum Fusion achieved the best overall performance, with an accuracy of 0.9216, F1-score of 0.9183, MCC of 0.8460, and sensitivity of 0.8808. At the pixel level, however, CT1 achieved the highest IoU (0.2294), indicating lower geometric agreement with PRODES polygons during independent testing. Overall, the model was more consistent in identifying the occurrence of deforestation within LRs than in reproducing its exact spatial geometry. The results also highlight the influence of temporal image selection and the potential of integrating multiple observations to support environmental monitoring.