Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Gustavo Manzon Nunes has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Spatio-temporal analysis of urban land use/land cover changes in Cuiabá and Várzea Grande, Mato Grosso, Brazil

    by Anaangélica Pereira da Silva, Karoline Assuero Cintra, Carolina Cardoso Costa, Andréa Fernanda Perozo dos Santos, Jaçanan Eloisa de Freitas Milani, Gustavo Manzon Nunes

    This study addresses the rapid urbanization in the municipalities of Cuiabá and Várzea Grande, located in the state of Mato Grosso, which face environmental challenges due to population growth. Using Remote Sensing and Geographic Information System tools, the research employed data from the Planet constellation and the Random Forest algorithm to map vegetation cover and changes in urban parameters between 2018 and 2023. The results allowed the quantification of four cover classes and highlighted a significant increase in the wooded area in both municipalities during the period, contributing to the shelter of fauna species and thermal comfort of the neighborhood. The accuracy assessment of the results indicates results of excellent quality (Cuiabá-MT) and very good (Várzea Grande-MT). The importance of urban planning in the conservation of wooded areas is highlighted, especially in cities with high average temperatures, where the conversion of native areas affects environmental conditions. It is concluded that there is a permanent need for more efficient urban planning to balance population growth with environmental conservation, thus ensuring local quality of life.

  • Open Access

    Uso del algoritmo Random Forest para el mapeo del uso y ocupación del suelo relacionados con bienes minerales en la APA (Área de Protección Ambiental) das cabeceiras do rio Cuiabá, Mato Grosso, Brasil.

    by Segundo Durval, Gustavo Manzon Nunes

    Brasil posee una de las mayores redes de áreas protegidas del mundo, abarcando aproximadamente el 18 % de su territorio. Las unidades de conservación se dividen en diferentes categorías (UC de protección integral y UC de uso sostenible), las cuales deben analizarse por separado para verificar su compatibilidad con la actividad minera. Este estudio tuvo como objetivo evaluar el desempeño del algoritmo Random Forest aplicado a datos Sentinel-2, generando una matriz de confusión y utilizando el coeficiente Kappa, con el propósito de medir la concordancia entre clasificaciones categóricas en el mapeo del uso y ocupación del suelo en el Área de Protección Ambiental (APA) Cabeceiras del río Cuiabá. Se obtuvo una precisión global del 91,11 % (164/180) y un coeficiente Kappa de 0,87. Como resultado final, se generó un producto innovador orientado a la toma de decisiones más sostenibles en el uso de los recursos naturales y minerales, de relevancia tanto regional como global.Parte superior do formulário

  • Open Access

    Dinámica de la vegetación en la región de Pirizal (Pantanal-MT, Brasil) mediante análisis temporal con datos PlanetScope

    by Vaniele Santana de Almeida, Segundo Durval, Gustavo Manzon Nunes

    Los humedales del Pantanal se distinguen por su dinámica ecológica, impulsada por variaciones estacionales y regímenes de inundación-sequía. Ubicada en la planicie de inundación del Pantanal Norte - Brasil e influida por el bioma Cerrado, la región de Pirizal presenta vegetación adaptada tanto al fuego como a las inundaciones, y es frecuentemente impactada por eventos extremos como incendios forestales. Este estudio tuvo como objetivo analizar la variación de macrohábitats (fitofisionomías) en la región utilizando imágenes multiespectrales adquiridas del satélite Planetscope (SuperDove) para los años 2020 (temporadas húmeda y seca) y 2024 (post-incendio). Los resultados indicaron que, en marzo de 2020, las clases cartografiadas predominantes fueron Campos de Murunduns, Cambarazal y Campo de Mimoso. Para octubre del mismo año, se evidenciaron efectos de incendios forestales, con una reducción significativa en los Campos de Murunduns y la emergencia de áreas quemadas. Entre 2020 y 2024, se registró una reducción de aproximadamente el 31.41% en el área de Campo de Murunduns, mientras que los Campos de Mimoso casi duplicaron su extensión (+93.47%). El Pimental mostró un incremento del 28.29%, el Cambarazal del 7.07%, y el Cerrado Stricto sensu también registró un crecimiento del 12.64%, destacando la resiliencia diferenciada de las fitofisionomías ante los impactos del fuego. Se concluye que, a pesar de los impactos causados por los incendios de 2020, la vegetación de Pirizal demuestra resiliencia y capacidad de regeneración. El uso del Teledetección se ha demostrado como una herramienta efectiva para monitorear estas dinámicas y contribuir a la conservación en la región.

  • Open Access

    Análisis de la caducidad foliar en plantaciones de Tectona grandis mediante datos multiespectrales orbitales y obtenidos con UAV

    by Gustavo Manzon Nunes, Diego Santos da Silva, Jaçanan Eloisa de Freitas Milani, Maricéia Tatiana Vilani, Segundo Durval Pereira Rezende, Mallu Arenhart Pirolla, Fernando Scognamiglio Torres

    El estudio propuesto se centra en comparar análisis aplicados a rodales de Tectona grandis manejados por la empresa 4M Agroflorestal Ltda, ubicados en la Fazenda Rancho Alegre, en el municipio de São José dos Quatro Marcos, Mato Grosso, Brasil. La finca se encuentra a aproximadamente 300 km de Cuiabá y abarca un área total de 483 hectáreas, de las cuales 284 hectáreas están cubiertas por rodales de teca divididos en 10 parcelas. Los datos se recolectaron en octubre de 2022 mediante misiones de vuelo con la cámara multiespectral Micasense Altum integrada en un UAV DJI Matrice 100, así como se adquirieron imágenes del satélite Planet SuperDove. Posteriormente, se procesaron los datos para obtener el Índice de Área Foliar (IAF) de cada parcela, con el objetivo de cuantificar el porcentaje de área foliar y, consecuentemente, comparar estos porcentajes, considerando la relación estadística derivada del hecho de que ambas fuentes de datos (Altum y Planet) para el área de estudio en la misma fecha (4 de octubre de 2022). El análisis de datos confirmó que en las cinco parcelas ubicadas en la parte norte de la finca, los datos Planet subestimaron la cobertura foliar, mientras que en las cinco parcelas del sur, sobreestimaron el área foliar. Por otro lado, los datos de la cámara Micasense Altum, integrada con un UAV, demostraron mayor exactitud en la medición espacial de doseles individuales, principalmente debido a su resolución espacial a nivel centimétrico, lo que permite avances en el manejo forestal de rodales plantados.

  • Open Access

    Remotely piloted aircraft system (RPAS) applied to the forest Inventory of Tectona grandis Linn f.: an RGB-based approach

    by Italo Luiz Corrêa Lenzi, Gustavo Manzon Nunes, Manuel Eduardo Ferreira, Evandro Orfanó Figueiredo, Rômulo Mora, Ronaldo Drescher

    Advances in the forestry sector are closely linked to scientific research and the implementation of technologies in the areas of sensors, aerial images, GPS, learning algorithms, data processing, as well as the use of computer intelligence systems to obtain and analyze data in forestry plantations, which require tools that provide a higher degree of precision, reduced costs and less time for data collection. This constant evolution of the sector, together with the improvement of Remotely Piloted Aircraft Systems (RPAS), paves the way for the use of this platform in forest data collection. In this article we discussed the use of RPAS to obtain dendrometric and morphometric variables to estimate wood volume in two Tectona grandis Linn f. stands, where field measurement and overflight were carried out using the Phantom 4 Pro RPAS. The aerial photos were processed using Pix4Dmapper software to generate the orthomosaic, digital terrain model and surface. Using these products, information was collected on the total height, crown area and crown diameter of the trees, with the aim of estimating volume (v) using the variables collected from the images (indirect method) and with the addition of the variables collected in the field (direct method). The estimates of v showed satisfactory results through the evaluation statistics, and it was possible to estimate forest production from data obtained by RPAS, obtaining an adjusted coefficient of determination of 66% in the indirect method and the estimate together with the field data showed an adjusted coefficient of determination of 94%.

  • Open Access

    Spectral-Temporal Analysis Of Wetland Fires In The Pantanal-Brazil Supported By UAV Multispectral Imagery

    by Gustavo Manzon Nunes, Cátia Nunes da Cunha, Nubia da Silva

    The Wetlands of the Pantanal in Brazil are highly sensitive to environmental changes, and events such as wildfires pose a significant threat to biodiversity. In 2020, approximately 80% of its area was affected by high-intensity fires. Therefore, this study aimed to analyze, both spectrally and temporally over a three-year period (2019, 2020, and 2021), the behavior of four macrohabitats located within two study areas of the Private Reserve of Natural Heritage SESC Pantanal (RPPN SESC Pantanal), situated in the state of Mato Grosso, Brazil. For the analysis conducted over the three-year period in the study areas, the Micasense Altum multispectral camera was employed, along with processing methods involving spectral and temporal analysis. The results revealed a drastic decrease in reflectance within the red-edge and near-infrared (NIR) spectral bands in 2020, following the fire event, in both mapped areas. A subsequent recovery was observed in 2021, although reflectance levels remained below those recorded in 2019 (pre-fire conditions). The Acurizal and Tabocal macrohabitats exhibited the highest reflectance amplitudes and the greatest variability over the years, particularly in longer wavelengths (NIR). The Campina macrohabitat showed the lowest reflectance values, due to its vegetation being composed predominantly of shrub and herbaceous species. The Dry Forest (Mata Seca) displayed the highest spectral stability and demonstrated a continuous downward trend in average reflectance, indicating a loss of species diversity following the fire event. The findings contribute to the enhancement of conservation measures in wetland ecosystems, the management of protected areas, and the effectiveness of public policies, highlighting the potential of high-resolution multispectral data for spectral monitoring as a tool for detecting environmental changes.

  • Open Access

    Diagnóstico do impacto de incêndios em macro habitat na RPPN Sesc Pantanal sobre o ponto de vista de dados multiespectrais obtidos por RPAS/drone

    by Gustavo Manzon Nunes, Cátia Nunes da Cunha, Nubia Silva

    O ano de 2020 foi impactante devido à alta intensidade de incêndios no Pantanal. Deste modo, foram criados esforços nos mais variados campos do conhecimento para analisar e diagnosticar as causas e consequências desses incêndios. Tendo em vista a inovação com o uso de sensores multiespectrais integrados em RPAS, este trabalho visou monitorar e mapear temporalmente macro habitat na RPPN SESC Pantanal, caracterizando a cobertura da vegetação e as severidades causadas pelos incêndios ocorridos no ano de 2020. Foram realizados mapeamentos em três áreas com distintos macro habitat para os anos de 2019, 2020 e 2021, utilizando a câmera multispectral Micasense Altum e métodos de processamento avançados. Observou-se maior severidade causada pelos incêndios na Área 3 – Campina, seguida da Área 1 – Mata Seca com Tabocal com Campina e Área 2 – Mata Seca com Acuri. Os macro habitat mais afetados foram o Tabocal e Campina, com temperaturas pós incêndio superiores a 65 ºC. Estudos com dados calibrados e de alta resolução espacial e espectral são fundamentais para a compreensão da dinâmica de ambientes naturais, sobretudo de áreas úmidas que são altamente sensíveis. Os resultados obtidos permitem a melhor gestão da reserva e fornecem informações para órgãos ambientais de esfera estadual e federal acerca dos impactos dos incêndios no bioma Pantanal, subsidiando ações de conservação de áreas úmidas.

  • Open Access

    Hydrological Dynamics of the Pantanal, a Large Tropical Floodplain in Brazil, Revealed by Analysis of Sentinel-2 Satellite Imagery

    by Edelin Jean Milien, Gustavo Manzon Nunes, Girard Pierre, Stephen K. Hamilton, Catia Núnes Da Cunha

    Extensive tropical floodplain wetlands, such as the Brazilian Pantanal, are complex ecosystems composed of mosaics of permanently and seasonally flooded habitats and are increasingly threatened by land use and climate change. Spatial and interannual variability in the seasonal flood pulse is a fundamental ecological driver in these ecosystems. This study analyzes optical imagery from the Sentinel-2 satellite to determine the extent and seasonal patterns of inundation over five years in the northern Pantanal, a Ramsar site renowned for its wildlife. The study site is bordered by the Cuiabá and São Lourenço rivers, each with distinct flow regimes. Inundation patterns were revealed with a combination of water indices, supervised classification of land cover, and a digital elevation model. Total extent of flooding was underestimated by the optical imagery, but open water bodies were readily delineated with the land cover classification.


  • Open Access

    Use of Remotely Piloted Aircraft System Multispectral Data to Evaluate the Effects of Prescribed Burnings on Three Macrohabitats of Pantanal, Brazil

    by Harold E. Pineda Valles, Gustavo Manzon Nunes, Christian Niel Berlinck, Luiz Gustavo Gonçalves, Gabriel Henrique Pires de Mello Ribeiro

    The controlled use of fires to reduce combustible materials in prescribed burning helps to prevent the occurrence of forest fires. In recent decades, these fires have mainly been caused by anthropogenic activities. The study area is located in the Pantanal biome. In 2020, the greatest drought in 60 years happened in the Pantanal. The fire affected almost one third of the biome. The objective of this study is to evaluate the effect of prescribed burnings carried out in 2021 on three macrohabitats (M1: natural grassland flooded with a proliferation of Combretum spp., M2: natural grassland of seasonal swamps, and M3: natural grassland flooded with a proliferation of Vochysia divergens) inside the SESC Pantanal Private Natural Heritage Reserve. Multispectral and thermal data analyses were conducted with remotely piloted aircraft systems in 1 ha plots in three periods of the dry season with early, mid, and late burning. The land use and land cover classification indicate that the predominant vegetation type in these areas is seasonally flooded grassland, with percentages above 73%, except in zone three, which has a more diverse composition and structure, with the presence of arboreal specimens of V. divergem Pohl. The pattern of the thermal range showed differentiation pre- and post-burning. The burned area index indicated that fire was more efficient in the first two macrohabitats because they are natural grasslands, reducing the grass species in the burnings. Early and mid prescribed burnings are a good option to reduce the continuous accumulation of dry forest biomass fuel material and help to promote landscape heterogeneity. The use of multispectral sensor data with high spatial/spectral resolution can show the effects of fires, using highly detailed scales for technical decision making.


  • Open Access

    Integrated Fire Management as a Renewing Agent of Native Vegetation and Inhibitor of Invasive Plants in Vereda Habitats: Diagnosis by Remotely Piloted Aircraft Systems

    by Jéssika Cristina Nascente, Manuel Eduardo Ferreira, Gustavo Manzon Nunes

    The Cerrado biome is being gradually reduced. Remote sensing has been widely used to investigate spatio-temporal changes in the landscape, which are frequently limited to mapping with orbital sensors, while the Remotely Piloted Aircraft System (RPAS) proved to be advantageous in terms of spatial resolution and the application of advanced digital processing techniques. In this study, we investigated a vereda (humid area) of a conservation unit in the state of Mato Grosso, Brazil. Object-Based Image Analysis (OBIA) was applied to images obtained by RPAS to distinguish the phytophysiognomies of plant strata from the vereda and to diagnose the recovery of native and invasive vegetation after prescribed burning. The study was carried out in the following five stages: biomass collection; quality analysis of the land cover; phytosociological survey; collection of control points using a GNSS receiver (type L1/L2); and the capture of aerial images with an RGB camera coupled to a DJI Phantom 4 Pro, which was performed through overflights in three different periods. Object–Based Image Analysis was subsequently performed using the Nearest Neighbor classifier combined with Feature Space Optimization, obtaining classifications with accuracy and Kappa indexes greater than 80% and 0.80, respectively. The results of image processing allowed us to infer that fire acted as a renewing agent for native vegetation and as an inhibiting agent for invasive vegetation. The classification analyses combined with the phytosociological analysis allowed us to infer that the vereda is in the process of maturation. Therefore, the study demonstrated the potential of data obtained by RPAS for the diagnosis and analysis of vegetation dynamics in small wetlands submitted to Integrated Fire Management (IFM).