| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.87 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
Atualmente, com o avanço de tecnologias e a facilidade de obtenção de imagens de satélite, o monitoramento e análises espaciais da vegetação terrestre, com custos reduzidos e de forma eficiente, possibilitam montar perfis de imagens multitemporais e sazonais da superfície terrestre. Este trabalho tem como objetivo identificar a melhor época para classificação e cálculo de índices de vegetação florestal no Parque Natural de Montesinho (PNM), e localizar os seus bosques de maior valor natural– azinheira (Quercus rotundifolia), carvalho negral (Quercus pyrenaica Willd.), pinheiro-bravo (Pinus pinaster Aiton) e castanheiro (Castanea sativa Miller) – através de técnicas de teledetecção remota e geoprocessamento. Todo o processamento dos dados foi realizado no software QGIS 3.18.1 utilizando o SCP (Semi-Automatic Classification Plugin). Foram utilizados índices de vegetação e a classificação supervisionada Random Forest (RF). Para a produção dos mapas recolheram-se as amostras de treinamento (ROI), com base no material de apoio: cartas de uso e ocupação do solo (COS), e o inventario florestal nacional (IFN) de 2015, disponibilizado pelo ICNF, onde foi possível identificar de forma remota os bosques das espécies estudadas. Para a validação dos resultados calculou-se o Índice Kappa e Exatidão Global para os três meses estudados: o mês com o maior índice foi o de julho (63%), seguido de fevereiro (41%) e outubro (15%). Podemos relacionar esses resultados com a estação do ano das imagens, sendo essas de inverno e de outono, onde as plantas estão em repouso vegetativo. Conclui-se que a classificação feita pelo RF para a identificação das espécies de interesse se ajusta melhor com o real (IFN) no mês de julho. No entanto é necessário mais estudo aplicado à área.
Currently, with the advancement of technologies and the ease of obtaining satellite images, the monitoring and spatial analysis of terrestrial vegetation, with reduced costs and efficiency, make it possible to assemble profiles of multitemporal and seasonal images of the earth's surface. This work aims to identify the best time for classification and calculation of forest vegetation indices in the Montesinho Natural Park (PNM) and to locate its forests of greatest natural value holm oak (Quercus rotundifolia), black oak (Quercus pyrenaica Willd. ), maritime pine (Pinus pinaster Aiton) and chestnut (Castanea sativa Miller) using remote sensing and geoprocessing techniques. All data processing was performed in QGIS 3.18.1 software using SCP (Semi-Automatic Classification Plugin). Vegetation indices and the supervised Random Forest (RF) classification were used. For the production of maps, training samples (ROI) were collected, based on the support material: land use and occupation charts (COS), and the national forest inventory (IFN) of 2015, made available by the ICNF, where it was possible to remotely identify the forests of the studied species. To validate the results, the Kappa Index and Global Accuracy were calculated for the three months studied: the month with the highest index was July (63%), followed by February (41%) and October (15%). We can relate these results with the season of the year of the images, being those of winter and autumn, where the plants are in vegetative rest. It is concluded that the classification made by the RF for the identification of the species of interest fits better with the real (IFN) in the month of July. However, more study applied to the area is needed.
Currently, with the advancement of technologies and the ease of obtaining satellite images, the monitoring and spatial analysis of terrestrial vegetation, with reduced costs and efficiency, make it possible to assemble profiles of multitemporal and seasonal images of the earth's surface. This work aims to identify the best time for classification and calculation of forest vegetation indices in the Montesinho Natural Park (PNM) and to locate its forests of greatest natural value holm oak (Quercus rotundifolia), black oak (Quercus pyrenaica Willd. ), maritime pine (Pinus pinaster Aiton) and chestnut (Castanea sativa Miller) using remote sensing and geoprocessing techniques. All data processing was performed in QGIS 3.18.1 software using SCP (Semi-Automatic Classification Plugin). Vegetation indices and the supervised Random Forest (RF) classification were used. For the production of maps, training samples (ROI) were collected, based on the support material: land use and occupation charts (COS), and the national forest inventory (IFN) of 2015, made available by the ICNF, where it was possible to remotely identify the forests of the studied species. To validate the results, the Kappa Index and Global Accuracy were calculated for the three months studied: the month with the highest index was July (63%), followed by February (41%) and October (15%). We can relate these results with the season of the year of the images, being those of winter and autumn, where the plants are in vegetative rest. It is concluded that the classification made by the RF for the identification of the species of interest fits better with the real (IFN) in the month of July. However, more study applied to the area is needed.
Description
Mestrado de dupla diplomação com a UTFPR, Universidade Tecnológica Federal do Paraná
Keywords
Random forest Deteção remota Análise temporal