Jansle Vieira Rocha

Spectral variables, growth analysis and yield of sugarcane

Spectral information is well related with agronomic variables and can be used in crop monitoring and yield forecasting. This paper describes a multitemporal research with the sugarcane variety SP80-1842, studying its spectral behavior using field spectroscopy and its relationship with agronomic parameters such as leaf area index (LAI), number of stalks per meter (NPM), yield (TSS) and total biomass (BMT). A commercial sugarcane field in Araras/SP/Brazil was monitored for two seasons. Radiometric data and agronomic characterization were gathered in 9 field campaigns. Spectral vegetation indices had similar patterns in both seasons and adjusted to agronomic parameters. Band 4 (B4), Simple Ratio (SR), Normalized Difference Vegetation Index (NDVI), and Soil Adjusted Vegetation Index (SAVI) increased their values until the end of the vegetative stage, around 240 days after harvest (DAC). After that stage, B4 reflectance and NDVI values began to stabilize and decrease because the crop reached ripening and senescence stages. Band 3 (B3) and RVI presented decreased values since the beginning of the cycle, followed by a stabilization stage. Later these values had a slight increase caused by the lower amount of green vegetation. Spectral variables B3, RVI, NDVI, and SAVI were highly correlated (above 0.79) with LAI, TSS, and BMT, and about 0.50 with NPM. The best regression models were verified for RVI, LAI, and NPM, which explained 0.97 of TSS variation and 0.99 of BMT variation.

Estimativa de áreas com culturas de verão no Paraná, por meio de imagens multitemporais EVI/Modis

O objetivo deste trabalho foi estimar e mapear as areas com as culturas de soja e milho, no Parana, com uso de imagens multitemporais EVI/Modis. Foram avaliados os anos‑safra de 2004/2005 a 2007/2008. Em razao da alta dinâmica temporal e da heterogeneidade de datas de semeadura das culturas no estado, foram utilizadas cenas que contemplavam as fases de pre‑plantio e de desenvolvimento inicial das culturas, para gerar a imagem de minimo EVI (IMIE), e cenas que consideravam o pico vegetativo das culturas, para gerar a imagem de maximo EVI (IMAE). Estas imagens foram utilizadas para gerar a composicao colorida RGB (R, IMAE; GB, IMIE), o que permitiu a confeccao de mascara das areas com soja e milho. As estimativas das areas de mascara por municipio foram comparadas com dados oficiais de producao agricola municipal, tendo-se observado bons ajustes (R²>0,84, d>0,95, c>0,85) entre os dados. Para a avaliacao da exatidao espacial das mascaras, imagens Landsat‑5/TM e AWiFS/IRS foram usadas como referencia para construcao da matriz de erros. Os resultados obtidos sao indicativos de que a metodologia proposta e altamente eficiente e pode ser utilizada para mapeamento dessas culturas.

Growth indices ans productivity in sugarcane

O conhecimento do desenvolvimento temporal de variaveis agronomicas da cultura da cana-de-acucar e um aspecto preponderante, e ainda pouco explorado, para o desenvolvimento de modelos de entendimento e predicao da producao em estudos de sensoriamento remoto. O presente descreve a analise da evolucao temporal de variaveis agronomicas da cana-de-acucar como a biomassa total (BMT), produtividade (TCH), indice de area foliar (IAF) e numero de plantas por metro (NPM). Durante duas safras um talhao comercial em Araras/SP cultivado com a variedade SP80-1842 no 4o e 5o cortes foi acompanhado em oito campanhas de campo para a coleta de dados. O IAF, o NPM, a TCH e a BMT foram coletados em 18 amostras de 2 m em tres linhas de cana-de-acucar. Analise de regressao linear e multipla foram usadas para a analise do crescimento da cultura e para o estudo da correlacao e ajuste de modelos entre as variaveis agronomicas e a BMT e a TCH. O modelo Gompertz, de curva sigmoidal, foi o modelo que melhor se ajustou para a curva de BMT e para a TCH com r2 = 0,8987 e r2 = 0,9682, respectivamente. A BMT e o IAF tiveram melhores ajustes com curvas exponencial cubica e exponencial quadratica, respectivamente. A BMT e a TCH foram bem relacionadas com o IAF nas duas primeiras fases do ciclo, ajustando-se regressoes lineares. Para a fase de maturacao, a BMT e a TCH foram mais relacionadas com o NPM que com o IAF e as curvas obtiveram valores menores de que r2 que as demais fases do ciclo.

Orbital spectral variables, growth analysis and sugarcane yield

Temporal analysis of crop development in commercial fields requires tools for large area monitoring, such as remote sensing. This paper describes the temporal evolution of sugar cane biophysical parameters such as total biomass (BMT), yield (TSS), leaf area index (LAI), and number of plants per linear meter (NPM) correlated to Landsat data. During the 2000 and 2001 cropping seasons, a commercial sugarcane field in Araras, Sao Paulo state, Brazil, planted with the SP80-1842 sugarcane variety in the 4th and 5th cuts, was monitored using nine Landsat images. Spectral data were correlated with agronomic data, obtained simultaneously to the imagery acquisition. Two methodologies were used to collect spectral data from the images: four pixels (2 × 2) window and average of total pixels in the field. Linear and multiple regression analysis was used to study the spectral behavior of the plants and to correlate with agronomic variables (days after harvest-DAC, LAI, NPM, BMT and TSS). No difference was observed between the methodologies to collect spectral data. The best models to describe the spectral crop development in relation to DAC were the quadratic and cubic models. Ratio vegetation index and normalized difference vegetation index demonstrated correlation with DAC, band 3 (B3) was correlated with LAI, and NDVI was well correlated with TSS and BMT. The best fit curves to estimate TSS and BMT presented r2 between 0.68 and 0.97, suggesting good potential in using orbital spectral data to monitor sugarcane fields.

Mapeamento de culturas de verão no Estado do Paraná por meio de composições decendiais de NDVI do sensor spot vegetation

The search for low subjectivity area estimates has increased the use of remote sensing for agricultural monitoring and crop yield prediction, leading to more flexibility in data acquisition and lower costs comparing to traditional methods such as census and surveys. Low spatial resolution satellite images with higher frequency in image acquisition have shown to be adequate for cropland mapping and monitoring in large areas. The main goal of this study was to map the Summer crops in the State of Paraná, Brazil, using 10-day composition of NDVI SPOT Vegetation data for 2005/2006, 2006/2007 and 2007/2008 cropping seasons. For this, a supervised digital classification method with Parallelepiped algorithm in multitemporal RGB image composites was used, in order to generate masks of Summer cultures for each 10-day composition. Accuracy assessment was performed using Kappa index, overall accuracy and Willmotts concordance index, resulting in good levels of accuracy. This methodology allowed the accomplishment, with free and low resolution data, of the mapping of Summer cultures at State level.A busca por menor subjetividade em estimativas de area tem aumentado a utilizacao do sensoriamento remoto para monitoramento agricola e previsao de safras, pois proporciona maior agilidade na aquisicao de dados e menor custo em relacao a metodos tradicionais de censos e pesquisas. Imagens de satelite de baixa resolucao espacial e alta periodicidade sao adequadas para o mapeamento, acompanhamento e desenvolvimento de culturas em areas extensas. O objetivo deste trabalho foi mapear culturas de verao no Estado do Parana por meio de composicoes decendiais de imagens NDVI do satelite SPOT Vegetation para safras de 2005/2006, 2006/2007 e 2007/2008. Para isso, foi utilizado um metodo de classificacao digital supervisionada com algoritmo Paralelepipedo em composicoes RGB multitemporais das imagens, de forma a gerar mascaras das culturas de verao para cada composicao decendial. A verificacao da acuracia das mascaras foi realizada utilizando indice Kappa, exatidao global e indice de concordância de Willmott, resultando em bons indices de acerto. Essa metodologia possibilitou realizar, com dados gratuitos e de baixa resolucao espacial, o mapeamento de culturas de verao em nivel estadual.

Height estimation of sugarcane using an unmanned aerial system UAS based on structure from motion SfM point clouds

ABSTRACT The use of unmanned aerial systems (UAS) as remote-sensing platforms has tremendous potential for obtaining detailed, site-specific descriptions of crop features, which would be very useful for precision agriculture. In sugarcane plantations, for example, cane height can be an indicator of yield and other parameters because it is highly influenced by the soil, total sugar content, leaf nitrogen content, temperature and light intensity. This article describes the generation of crop surface models (CSMs) from high-resolution images that were obtained using a UAS to estimate sugarcane height. Using a UAS with an on-board RGB camera, we created densified three-dimensional point clouds of the study area in two different flight line directions (North/South and East/West) using structure from motion (SfM) with multi-view stereo (MVS). Then, the digital surface model (DSM) and digital terrain model (DTM) were extracted and used to create CSMs. Maps of sugarcane height were created based on this information. We investigated the influences of different flight line directions (N/S and E/W) on sugarcane height estimations and their accuracy by comparing our maps with ground references. From the validation conducted using both flight lines, the average heights were closer to the field-verified data. The resulting maps showed differences in sugarcane height that were confirmed by field measurements. This method has potential for future use by sugarcane-related industries, researchers and farmers to estimate average crop height.

Mapping skips in sugarcane fields using object-based analysis of unmanned aerial vehicle (UAV) images

Abstract The use of unmanned aerial vehicles (UAVs) as remote sensing platforms has tremendous potential for describing detailed site-specific features of crops, especially in early post-emergence, which was not possible previously with satellite images. This article describes an object-based image analysis (OBIA) procedure for UAV images, designed to map and extract information about skips in sugarcane planting rows. The procedure consists of three consecutive phases: (1) identification of sugarcane planting rows, (2) identification of the existent sugarcane within the crop rows, and (3) skip extraction and creation of field-extent crop maps. Results based on experimental fields achieved skip rates of between 2.29% and 10.66%, indicating a planting operation with excellent and good quality, respectively. The relationship of estimated versus observed skip length had a coefficient of determination of 0.97, which was confirmed by the value of the enhanced Wilmott concordance coefficient of 0.92, indicating good agreement. The OBIA procedure allowed a high level of automation and adaptability, and it provided useful information for decision making, agricultural monitoring, and the reduction of operational costs.

THE USE OF ALOS/PALSAR DATA FOR ESTIMATING SUGARCANE PRODUCTIVITY

Some models have been developed using agrometeorological and remote sensing data to estimate agriculture production. However, it is expected that the use of SAR images can improve their performance. The main objective of this study was to estimate the sugarcane production using a multiple linear regression model which considers agronomic data and ALOS/PALSAR images obtained from 2007/08, 2008/09 and 2009/10 cropping seasons. The performance of models was evaluated by coefficient of determination, t-test, Willmott agreement index (d), random error and standard error. The model was able to explain 79%, 12% and 74% of the variation in the observed productions of the 2007/08, 2008/09 and 2009/10 cropping seasons, respectively. Performance of the model for the 2008/09 cropping season was poor because of the occurrence of a long period of drought in that season. When the three seasons were considered all together, the model explained 66% of the variation. Results showed that SAR-based yield prediction models can contribute and assist sugar mill technicians to improve such estimates.

Effect of sugarcane-planting row directions on ALOS/PALSAR satellite images

This study investigated the effects of sugarcane-planting row directions in the HH- and VV-polarized, ALOS/PALSAR imageries. Twenty sugarcane fields from São Paulo State, Brazil, were classified into rows parallel and rows perpendicular to the range direction of the satellite. Backscattering coefficients (σ°) from 10 images were analyzed. For HH polarization, σ° values from fields with perpendicular rows were higher than those from parallel rows (∼1.2 dB). For HV polarization, there was no statistically significant difference. Therefore, HV-polarized PALSAR images are preferable for producing maps of cultivated areas with sugarcane or to discriminate sugarcane varieties, among other applications.

Correlation maps to assess soybean yield from EVI data in Paraná State, Brazil

Vegetation indices are widely used to monitor crop development and generally used as input data in models to forecast yield. The first step of this study consisted of using monthly Maximum Value Composites to create correlation maps using Enhanced Vegetation Index (EVI) from Moderate Resolution Imaging Spectroradiometer (MODIS) sensor mounted on Terra satellite and historical yield during the soybean crop cycle in Parana State, Brazil, from 2000/2001 to 2010/2011. We compared the ability of forecasting crop yield based on correlation maps and crop specific masks. We ran a preliminary regression model to test its ability on yield estimation for four municipalities during the soybean growing season. A regression model was developed for both methodologies to forecast soybean crop yield using leave-one-out cross validation. The Root Mean Squared Error (RMSE) values in the implementation of the model ranged from 0.037 t ha−1 to 0.19 t ha−1 using correlation maps, while for crop specific masks, it varied from 0.21 t ha−1 to 0.35 t ha−1. The model was able to explain 96 % to 98 % of the variance in estimated yield from correlation maps, while it was able to explain only 2 % to 67 % for crop specific mask approach. The results showed that the correlation maps could be used to predict crop yield more effectively than crop specific masks. In addition, this method can provide an indication of soybean yield prior to harvesting.