Airborne cameras for natural grassland classification in the Pampa biome / Câmeras aerotransportadas para classificação da vegetação em pastagem natural no bioma Pampa

ABSTRACT: The extension of the area occupied by the inter tussock stratum and tussock stratum in natural pastures is essential for the productive performance of grazing animals. Images obtained from unmanned remote sensors can provide useful information, especially because they have a high spatial resolution. Thus, this study evaluated the performance of the supervised adaptive classification applied to aerial images obtained from an onboard drone camera to map the area covered by tussocks in a natural pasture of the Pampa biome. The study was carried out in a natural pasture area managed since 1986 under different forage allowances, considering treatments of 8, 12, and 16 kg of dry matter per 100 kg live weight (% LW). An aerial image from September 2017, obtained with a Canon S100 camera onboard a drone at an altitude of 120 m, with a spatial resolution of 5 cm, was used. The random forest and support vector machine classifiers were tested associated with specific classification rules. False-color images showed considerable visual similarity in the large patterns of the vegetation distribution and the validation performed with independent samples when compared to the classified images. The tested classifiers were able to measure the area covered by the tussock stratum, which could be an indicator of the quality vegetation in a natural grassland of the Pampa biome.

RESUMO: A quantidade de área ocupada por estrato inferior e superior em pastagens naturais tem grande importância sobre o desempenho produtivo dos animais em pastejo. Imagens obtidas de sensores remotos não tripulados podem fornecer informações úteis, especialmente por possuírem alta resolução espacial. O objetivo deste trabalho foi avaliar o desempenho de classificação supervisionada adaptativa aplicada a imagem aérea obtida por câmera a bordo de drone, no mapeamento da área coberta por touceiras em pastagem natural do bioma Pampa. O estudo foi realizado em área de pastagem natural, manejada desde 1986 sob diferentes ofertas de forragem, tendo sido considerados os tratamentos 8, 12 e 16 kg de matéria seca por 100 kg de peso vivo (% PV). Foi utilizada uma imagem aérea, de setembro de 2017, obtida com uma câmera Canon S100, a bordo de um drone a 120 m de altitude, correspondendo a resolução espacial de 5 cm. Foram testados dois classificadores, Random Forest e Support Vector Machine associados a regras específicas de classificação. As imagens de falsa cor, quando comparadas às imagens classificadas, apresentaram considerável semelhança visual nos grandes padrões de distribuição da vegetação, bem como na validação feita com amostras independentes. Os classificadores testados foram capazes de mensurar a área coberta por estrato superior, podendo ser um indicador da qualidade da vegetação, em pastagem natural do bioma Pampa.

Airborne cameras for natural grassland classification in the Pampa biome / Câmeras aerotransportadas para classificação da vegetação em pastagem natural no bioma Pampa

The extension of the area occupied by the inter tussock stratum and tussock stratum in natural pastures is essential for the productive performance of grazing animals. Images obtained from unmanned remote sensors can provide useful information, especially because they have a high spatial resolution. Thus, this study evaluated the performance of the supervised adaptive classification applied to aerial images obtained from an onboard drone camera to map the area covered by tussocks in a natural pasture of the Pampa biome. The study was carried out in a natural pasture area managed since 1986 under different forage allowances, considering treatments of 8, 12, and 16 kg of dry matter per 100 kg live weight (% LW). An aerial image from September 2017, obtained with a Canon S100 camera onboard a drone at an altitude of 120 m, with a spatial resolution of 5 cm, was used. The random forest and support vector machine classifiers were tested associated with specific classification rules. False-color images showed considerable visual similarity in the large patterns of the vegetation distribution and the validation performed with independent samples when compared to the classified images. The tested classifiers were able to measure the area covered by the tussock stratum, which could be an indicator of the quality vegetation in a natural grassland of the Pampa biome.

A quantidade de área ocupada por estrato inferior e superior em pastagens naturais tem grande importância sobre o desempenho produtivo dos animais em pastejo. Imagens obtidas de sensores remotos não tripulados podem fornecer informações úteis, especialmente por possuírem alta resolução espacial. O objetivo deste trabalho foi avaliar o desempenho de classificação supervisionada adaptativa aplicada a imagem aérea obtida por câmera a bordo de drone, no mapeamento da área coberta por touceiras em pastagem natural do bioma Pampa. O estudo foi realizado em área de pastagem natural, manejada desde 1986 sob diferentes ofertas de forragem, tendo sido considerados os tratamentos 8, 12 e 16 kg de matéria seca por 100 kg de peso vivo (% PV). Foi utilizada uma imagem aérea, de setembro de 2017, obtida com uma câmera Canon S100, a bordo de um drone a 120 m de altitude, correspondendo a resolução espacial de 5 cm. Foram testados dois classificadores, Random Forest e Support Vector Machine associados a regras específicas de classificação. As imagens de falsa cor, quando comparadas às imagens classificadas, apresentaram considerável semelhança visual nos grandes padrões de distribuição da vegetação, bem como na validação feita com amostras independentes. Os classificadores testados foram capazes de mensurar a área coberta por estrato superior, podendo ser um indicador da qualidade da vegetação, em pastagem natural do bioma Pampa.

Seasonal dynamics of vegetation indices as a criterion for grouping grassland typologies

This study aimed to characterize the average seasonal pattern of the vegetation in southern grassland in Brazil, and the variability found in the time series of vegetation indices. It also sought to identify similarities in the seasonal pattern of different grassland typologies. Moderate Resolution Imaging Spectroradiometer (MODIS), Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) images from Feb to Dec, 2000 to 2014 were analyzed for ten regions. The grassland typologies studied showed EVI and NDVI profiles consistent with the seasonal dynamics of grassland vegetation under the influence of a subtropical climate, with highest values in the indices during the warm seasons of the year (spring and summer) and lowest in the colder seasons (autumn and winter). Considering the values of EVI and NDVI, grassland typologies were allocated to four groups with similar temporal profiles. Among the groups formed from the EVI index it is possible to identify differences between grassland typologies during the autumn and winter, while the NDVI showed differences only in winter as compared to the other seasons.

Seasonal dynamics of vegetation indices as a criterion for grouping grassland typologies

This study aimed to characterize the average seasonal pattern of the vegetation in southern grassland in Brazil, and the variability found in the time series of vegetation indices. It also sought to identify similarities in the seasonal pattern of different grassland typologies. Moderate Resolution Imaging Spectroradiometer (MODIS), Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) images from Feb to Dec, 2000 to 2014 were analyzed for ten regions. The grassland typologies studied showed EVI and NDVI profiles consistent with the seasonal dynamics of grassland vegetation under the influence of a subtropical climate, with highest values in the indices during the warm seasons of the year (spring and summer) and lowest in the colder seasons (autumn and winter). Considering the values of EVI and NDVI, grassland typologies were allocated to four groups with similar temporal profiles. Among the groups formed from the EVI index it is possible to identify differences between grassland typologies during the autumn and winter, while the NDVI showed differences only in winter as compared to the other seasons.(AU)

Two approaches to calculate TVDI in humid subtropical climate of southern Brazil

Soybean crops occupy most areas in Rio Grande do Sul State and are highly dependent on rainfall since most of them are non-irrigated. Rainfall during the harvest period is often insufficient to meet the water demand, making water indicators an important tool for the crops. This study compared two approaches in the parameterization process of TVDI (Temperature-Vegetation Dryness Index) in a subtropical climate region of Brazil. The process used Moderate Resolution Imaging Spectroradiometer (MODIS) images of the surface temperature (TS) and Normalized Difference Vegetation Index (NDVI), with spatial resolutions of 1,000 m and periods of 8-16 d, respectively. The evaporative triangles for the TS/NDVI scatter plots were built either for each image (scene-specific parameterization) or for all images at once (crop-type parameterization). The rainfall data were obtained from meteorological stations located in the study site and the analysis period comprised two contrasting harvests regarding soybean yield (most important crop in the region). The scene-specific parameterization allowed to analyze water status in the study site by inspecting the wet and dry edge of each image and identifying the areas of stress in each one. TVDI crop parameterization showed that the model was able to determine the time and frequency of water stress events during the crop-seasons. TVDI crop-parameterization, therefore, is more consistent for crop monitoring and forecasting purposes.

Two approaches to calculate TVDI in humid subtropical climate of southern Brazil

Soybean crops occupy most areas in Rio Grande do Sul State and are highly dependent on rainfall since most of them are non-irrigated. Rainfall during the harvest period is often insufficient to meet the water demand, making water indicators an important tool for the crops. This study compared two approaches in the parameterization process of TVDI (Temperature-Vegetation Dryness Index) in a subtropical climate region of Brazil. The process used Moderate Resolution Imaging Spectroradiometer (MODIS) images of the surface temperature (TS) and Normalized Difference Vegetation Index (NDVI), with spatial resolutions of 1,000 m and periods of 8-16 d, respectively. The evaporative triangles for the TS/NDVI scatter plots were built either for each image (scene-specific parameterization) or for all images at once (crop-type parameterization). The rainfall data were obtained from meteorological stations located in the study site and the analysis period comprised two contrasting harvests regarding soybean yield (most important crop in the region). The scene-specific parameterization allowed to analyze water status in the study site by inspecting the wet and dry edge of each image and identifying the areas of stress in each one. TVDI crop parameterization showed that the model was able to determine the time and frequency of water stress events during the crop-seasons. TVDI crop-parameterization, therefore, is more consistent for crop monitoring and forecasting purposes.(AU)

Temporal dynamics of spectral reflectance and vegetation indices during canola crop cycle in southern Brazil / Dinâmica temporal dos índices da reflectância espectral e índices de vegetação durante o ciclo da cultura de canola no Sul do Brasil

The objective of this study was to characterize the variability of spectral reflectance and temporal profiles of vegetation indices associated with nitrogen fertilization, crop cycle periods, and weather conditions of the growing season in canola canopies in southern Brazil. An experiment was carried out during the 2013 and 2014 canola growing seasons at EMBRAPA Trigo, Passo Fundo, state of Rio Grande do Sul, Brazil. The experiment was conducted in a randomized block design with four replications. Five doses of nitrogen top dressing were used as treatments: 10, 20, 40, 80, and 160kg ha-1. Measurements were obtained with the spectroradiometer positioned above the canopy, to construct spectral reflectance curves for canola and establish temporal profiles for several vegetation indices (SR, NDVI, EVI, SAVI, and GNDVI). In addition, data on shoot dry matter were obtained and phenological stages were determined. The spectral reflectance curves of canola were reported to change with canopy growth and development. Temporal profiles of vegetation indices showed two maximum peaks, one before flowering and other after flowering. The indices SR, NDVI, EVI, SAVI, and GNDVI were able to characterize changes in the canola canopy over time, as a function of phenological phases, weather conditions, and nitrogen fertilization, throughout the development cycle. Plant growth and development, variations in crop management, and environmental conditions affect the spectral response of canola.

O objetivo deste trabalho foi caracterizar a variabilidade da reflectância espectral e dos perfis temporais dos índices de vegetação de dosséis de canola, associada à adubação nitrogenada, aos períodos do ciclo da cultura e às condições meteorológicas no sul do Brasil. Foi instalado um experimento nas safras de 2013 e 2014, na EMBRAPA Trigo, em Passo Fundo, RS. O delineamento experimental foi de blocos casualizados com quatro repetições. Foram utilizados os tratamentos de cinco doses de nitrogênio em cobertura: 10, 20, 40, 80, 160kg ha-1. Foram realizadas medições com espectrorradiômetro, sobre o dossel, para compor curvas de reflectância espectral da canola e perfis temporais dos índices de vegetação SR, NDVI, EVI, SAVI e GNDVI. Também foram obtidos dados de matéria seca da parte aérea e feitas determinações de fenologia. Verificou-se que as curvas de reflectância espectral da canola mudaram com o crescimento e desenvolvimento do dossel. Os perfis temporais dos índices de vegetação apresentaram dois picos máximos, um antes e outro após o florescimento. Os índices SR, NDVI, EVI, SAVI e GNDVI foram capazes de caracterizar temporalmente as modificações do dossel da canola ao longo do ciclo, em função de fases fenológicas, condições meteorológicas e adubação nitrogenada. O crescimento e desenvolvimento das plantas, as variações de manejo da cultura e as condições ambientais afetam a resposta espectral da canola.

Temporal dynamics of spectral reflectance and vegetation indices during canola crop cycle in southern Brazil / Dinâmica temporal dos índices da reflectância espectral e índices de vegetação durante o ciclo da cultura de canola no Sul do Brasil

The objective of this study was to characterize the variability of spectral reflectance and temporal profiles of vegetation indices associated with nitrogen fertilization, crop cycle periods, and weather conditions of the growing season in canola canopies in southern Brazil. An experiment was carried out during the 2013 and 2014 canola growing seasons at EMBRAPA Trigo, Passo Fundo, state of Rio Grande do Sul, Brazil. The experiment was conducted in a randomized block design with four replications. Five doses of nitrogen top dressing were used as treatments: 10, 20, 40, 80, and 160kg ha-1. Measurements were obtained with the spectroradiometer positioned above the canopy, to construct spectral reflectance curves for canola and establish temporal profiles for several vegetation indices (SR, NDVI, EVI, SAVI, and GNDVI). In addition, data on shoot dry matter were obtained and phenological stages were determined. The spectral reflectance curves of canola were reported to change with canopy growth and development. Temporal profiles of vegetation indices showed two maximum peaks, one before flowering and other after flowering. The indices SR, NDVI, EVI, SAVI, and GNDVI were able to characterize changes in the canola canopy over time, as a function of phenological phases, weather conditions, and nitrogen fertilization, throughout the development cycle. Plant growth and development, variations in crop management, and environmental conditions affect the spectral response of canola.(AU)

O objetivo deste trabalho foi caracterizar a variabilidade da reflectância espectral e dos perfis temporais dos índices de vegetação de dosséis de canola, associada à adubação nitrogenada, aos períodos do ciclo da cultura e às condições meteorológicas no sul do Brasil. Foi instalado um experimento nas safras de 2013 e 2014, na EMBRAPA Trigo, em Passo Fundo, RS. O delineamento experimental foi de blocos casualizados com quatro repetições. Foram utilizados os tratamentos de cinco doses de nitrogênio em cobertura: 10, 20, 40, 80, 160kg ha-1. Foram realizadas medições com espectrorradiômetro, sobre o dossel, para compor curvas de reflectância espectral da canola e perfis temporais dos índices de vegetação SR, NDVI, EVI, SAVI e GNDVI. Também foram obtidos dados de matéria seca da parte aérea e feitas determinações de fenologia. Verificou-se que as curvas de reflectância espectral da canola mudaram com o crescimento e desenvolvimento do dossel. Os perfis temporais dos índices de vegetação apresentaram dois picos máximos, um antes e outro após o florescimento. Os índices SR, NDVI, EVI, SAVI e GNDVI foram capazes de caracterizar temporalmente as modificações do dossel da canola ao longo do ciclo, em função de fases fenológicas, condições meteorológicas e adubação nitrogenada. O crescimento e desenvolvimento das plantas, as variações de manejo da cultura e as condições ambientais afetam a resposta espectral da canola.(AU)

Temporal profiles of vegetation indices for characterizing grazing intensity on natural grasslands in Pampa biome

The Pampa biome is an important ecosystem in Brazil that is highly relevant to livestock production. The objective of this study was to analyze the potential use of vegetation indices to discriminate grazing intensities on natural grasslands in the Pampa biome. Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) images from Jan to Dec, 2000 to 2013 series, were analyzed for natural grassland experimental units managed under high (forage allowance of 5 ± 2 % live weight LW), moderate (13 ± 5 % LW) and low grazing intensity (19 ± 7 % LW). Regardless of intensity, the temporal profiles showed lower NDVI and EVI during winter, increased values in spring because of summer species regrowth, slightly decreased values in summer, especially in years when there is a water deficit, and increased values in the fall associated with the beginning of winter forage development. The average temporal profiles of moderate grazing intensity exhibited greater vegetation index values compared with low and high grazing intensities. The temporal profiles of less vegetation index were associated with lower green biomass accumulation caused by the negative impact of stocking rates on the leaf area index under high grazing intensity and a floristic composition with a predominance of tussocks under low grazing intensity. Vegetation indices can be used for distinguishing moderate grazing intensity from low and high intensities. The average EVI values can discriminate moderate grazing intensity during any season, and the NDVI values can discriminate moderate grazing intensity during spring and winter.

Temporal profiles of vegetation indices for characterizing grazing intensity on natural grasslands in Pampa biome

The Pampa biome is an important ecosystem in Brazil that is highly relevant to livestock production. The objective of this study was to analyze the potential use of vegetation indices to discriminate grazing intensities on natural grasslands in the Pampa biome. Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) images from Jan to Dec, 2000 to 2013 series, were analyzed for natural grassland experimental units managed under high (forage allowance of 5 ± 2 % live weight LW), moderate (13 ± 5 % LW) and low grazing intensity (19 ± 7 % LW). Regardless of intensity, the temporal profiles showed lower NDVI and EVI during winter, increased values in spring because of summer species regrowth, slightly decreased values in summer, especially in years when there is a water deficit, and increased values in the fall associated with the beginning of winter forage development. The average temporal profiles of moderate grazing intensity exhibited greater vegetation index values compared with low and high grazing intensities. The temporal profiles of less vegetation index were associated with lower green biomass accumulation caused by the negative impact of stocking rates on the leaf area index under high grazing intensity and a floristic composition with a predominance of tussocks under low grazing intensity. Vegetation indices can be used for distinguishing moderate grazing intensity from low and high intensities. The average EVI values can discriminate moderate grazing intensity during any season, and the NDVI values can discriminate moderate grazing intensity during spring and winter.(AU)