Marcos Wellausen Dias de Freitas

O desastre climático de abril e maio de 2024 no Rio Grande do Sul envolveu movimentos de massa, enxurradas e inundações prolongadas. O emprego de geotecnologias é essencial no monitoramento e gestão dos desastres, permitindo o acesso rápido a informações geoespaciais. Portanto, este trabalho teve como objetivo mapear a mancha de inundação e a área diretamente afetada (ADA) para a Região Hidrográfica do Guaíba (RHGB) a partir de imagens ópticas Planet. A metodologia incluiu a aplicação da Análise de Componentes Principais, GEOBIA, classificação com Random Forest, e pós-processamento. Os resultados indicaram que a mancha de inundação na RHGB possuiu uma área de 2.911,18 km² e a ADA de 4.137,06 km², com 4,85% da área total da RHGB atingida pela inundação. O mapeamento com imagens de alta resolução espacial permite detalhar a magnitude do evento e determinar com maior precisão as áreas atingidas, principalmente em áreas urbanas.

The Pampa biome has been transforming its traditional landscape since the 1950s. Comprehending the spatiotemporal dynamics of land use and land cover change (LUCC) in the Pampa and its primary drivers is crucial in formulating territorial planning and environmental management. Therefore, the purpose of this paper is to use the potential of Principal Components Analysis (PCA) to analyze LUCC in the Pampa biome between 1985-2020, based on the synthesis of the MapBiomas project database. The methodology is divided into three stages, the first is in GEE where pre-processing and PCA are carried out, and the second is in Planetary Computer where correlation coefficients are calculated. Finally, in QGIS 3.10.4, reclassification and cartographic production were conducted. The LUCC processes identified in the Pampa Biome reveal a significant transformation of its landscape, characterized by a reduction in the extent of grassland formations due to the expansion of anthropogenic activities. The conversion of natural grasslands to agricultural land uses, particularly soy, forestry, and farming, has been a prevalent trend. The results of the analysis highlight that the large-scale conversion of grassland areas is a recent phenomenon in the Pampa, occurring mainly between 1995 and 2010, linked to the replacement of cattle ranching by large-scale agriculture.

Urbanization in large cities has altered the urban thermal balance, creating urban heat islands. In this context, green areas are crucial in regulating the urban climate. This study uses remote sensing data to evaluate their performance using the fractional vegetation cover (FVC) and its impact on land surface temperature (LST) in Metropolitan Lima, Peru, between 1986 and 2024. The spatial and temporal relationship between FVC and LST is analyzed, and districts are classified based on their effectiveness in thermal regulation. The Mann–Kendall test was applied to identify trends along with a Spearman correlation analysis and a clustering analysis to group districts according to the cooling effectiveness of their urban green areas. The results show that urban expansion has increased LST by an average of 6.43 °C since 1990, and there is a significant negative correlation (p < 0.001) between FVC and LST, indicating positive impacts of vegetation regulating LST at a spatial level. However, it does not reduce LST at a temporal level. This suggests that, while effective locally, green areas are insufficient to counteract the overall warming of LST over time. Based on FVC and LST characteristics, the districts have been classified into four groups: those with well-preserved green areas, such as La Molina and San Isidro, which have a lower LST, compared to areas where urbanization has replaced vegetation, such as Carabayllo and Lurigancho (Chosica). Finally, this study highlights the importance of integrating green area management into urban planning to mitigate urban warming and promote sustainable development.

A Amazônia representa o maior bioma do Brasil, assumindo uma posição proeminente no contexto global. O incremento das atividades agropecuárias e a extração dos recursos naturais de forma desenfreada põem em risco a manutenção desse ambiente natural, introduzindo novos hábitos culturais centrados na vida urbana. Consolida-se, assim, a homogeneização da paisagem, que pode ser observada a partir das consequências da atividade humana. Nesse contexto, as Terras Indígenas atuam como “escudos”, protegendo seus povos, a biodiversidade, os estoques de carbono e os serviços ecossistêmicos. As Terras Indígenas de Povos Isolados referem-se aos territórios de indígenas que não possuem contato direto com a sociedade em geral e, consequentemente, seus territórios sofrem maior pressão para invasão e exploração de recursos naturais. Essa pesquisa propõe um Índice de Homogeneização da Paisagem (IHP) voltado para espaços de indígenas isolados, neste caso a Terra Indígena Piripkura, e os Setores Censitários em seu interior e em seu entorno, a fim de fornecer subsídios para a tomada de decisões e planejamento territorial. De maneira geral, a aplicação desse índice demonstrou maior IHP em áreas próximas a rodovias, sedes urbanas e com maior densidade populacional, enquanto áreas de Unidade de Conservação e Terras Indígenas apresentaram um índice menor.

Remote sensing data used in this study included MSI (Multispectral Instrument) Sentinel-2, SAR (Synthetic Aperture Radar) Sentinel-1, GLCM (Grey Level Co-Occurrence Matrix) texture data derived from Sentinel-1, and geomorphometric data derived from SRTM (Shuttle Radar Topography Mission) images. The input data was divided into separate groups for machine learning algorithms, including Support Vector Machine (SVM), Classification and Regression Tree (CART), and Random Forest (RF), which were implemented on the Google Earth Engine platform. RF showed the highest overall accuracies (93 to 97%), regardless of the dataset used as input, with the Kappa index ranging from 0.89 (optical and SAR data) to 0.95 (optical, SAR, and geomorphometric data). CART showed identical overall accuracy values (92.5%) except for the dataset supplemented with SAR texture data, which showed slightly lower accuracy (91.7%), with the Kappa index ranging from 0.89 to 0.91. The worst performance was classifying optical data by SVM, resulting in 59% accuracy and a Kappa index of 0.37. However, the synergy of optical, SAR, and geomorphometric data classified by SVM achieved 75% accuracy. Foram utilizados dados de sensoriamento remoto adquiridos pelos sensores MSI (Multispetral Instrument) do satélite Sentinel-2 e SAR (Synthetic Aperture Radar) Sentinel-1, dados de textura GLCM (Grey Level Co-Ocurrence Matrix) derivados das imagens Sentinel-1 e dados geomorfométricos derivados de imagens SRTM (Shuttle Radar Topography Mission). Os dados compuseram diferentes grupos de entrada para os classificadores de aprendizagem de máquina Support Vector Machine (SVM), Classification and Regression Tree (CART) e Random Forest (RF), implementados na plataforma Google Earth Engine. O RF apresentou as maiores exatidões globais (93 a 97%), independente do conjunto de dados utilizados como entrada, com o índice Kappa variando de 0,89 (dados ópticos e SAR) a 0,95 (dados ópticos, SAR e geomorfométricos). O CART apresentou valores idênticos de exatidão global (92,5%) exceto para o conjunto de dados acrescido dos dados de textura SAR, que apresentou exatidão ligeiramente mais baixa (91,7%), com índice Kappa variando de 0,89 a 0,91. O pior desempenho foi o da classificação de dados ópticos por SVM, resultando em 59% de exatidão e 0,37 de índice Kappa. Todavia, a sinergia de dados ópticos, SAR e geomorfométricos classificados por SVM atingiu 75% de exatidão.

The lack of a solid methodology defining urban and non-urban areas has hindered accurately estimating the Surface Urban Heat Island (SUHI). This study addresses this issue by using the official national urban areas limit together with a surrounding areas classification to define three different reference classes: the urban adjacent (Ua), the future urban adjacent (FUa), and the peri-urban (PUa), consequently providing a more accurate SUHI estimation on the nine northeastern Brazilian capitals. The land surface temperature was obtained in this study using the Sentinel-3 satellite data for 2019 and 2020. Subsequently, the maximum and average SUHI and the complementary indexes, specifically the Urban Thermal Field Variation Index (UTFVI) and the Thermal Discomfort Index (TDI), were calculated. The UTFVI expresses how harmful the eco-environmental spaces are, with a very strong SUHI for three capitals. In addition, the TDI, with values between 24.6–28.8 °C, expresses the population’s thermal comfort, with six capitals showing a very hot TDI. These findings highlight the need for strategies to mitigate the effects of the SUHI and ensure the population’s thermal comfort. Therefore, this study provides a better SUHI understanding and comparison for the Brazilian northeastern region, which has diverse areas, populations, and demographic variations.

Information regarding land use and cover is essential for effective environmental planning. The use of remote sensing images facilitates the elaboration of these mappings, due to the large availability of images and computational advances in the data processing. Therefore, this work aims to compare and evaluate the potential of the Principal Component Analysis technique to improve the accuracy of land use and cover classification in the Lajeado São José watershed. To this end, the Principal Component Analysis technique was applied to the Sentinel-2 image in Google Earth Engine. Then, in the same platform, the image classification was performed using the original spectral bands and the principal components generated, with two different classifiers: CART and Random Forest. In order to compare whether there is any increase in classification quality when using principal components in relation to spectral bands. The accuracy evaluation was produced through the analysis of stratified distributed control points. The results indicated that the best land use and cover classification was produced with the principal components combined with the Random Forest classifier, because it presented 87.7% of overall accuracy, and lower discordance of quantity (5.2%) and allocation (7.1%) in the accuracy evaluation. Therefore, it can be concluded from the accuracy analysis that the use of principal components can generate better results in land use and land cover classification when compared to the use of spectral bands.

The Surface Urban Heat Island (UHI) is caused by the difference in temperature between the urban and its surrounding areas. However, in the scientific literature, there is no solid methodology defining urban and non-urban areas, which is essential to estimate the SUHI with greater accuracy. This study uses the official national urban areas limit, to obtain the SUHI more accurately on the nine northeastern Brazilian capitals. The land surface temperature was obtained using the Sentinel 3 satellite data for the years 2019 and 2020. Afterward, the maximum and average SUHI, and the complementary indexes were calculated, such as the Urban Thermal Field Variation Index (UTFVI) and the Thermal Discomfort Index (TDI) for the urban areas and their surrounding areas. The Maximum and Average SUHI, obtained values between 1.85 and 8.25 and -4.92 and 2.59 degree difference, respectively, proving the SUHI existence in the study areas. The UTFVI, with values between 0.010 and 0.040, expresses how bad the eco-environmental spaces of urban are. The TDI, with values between 24.61 and 28.89 ºC, expresses the population’s thermal comfort. Therefore, this study provides a better understanding of the surface UHI pioneeringly for the Brazilian Northeast Region.