Search

The adoption of precision agriculture involves a demand for equipment and solutions to create an accurate diagnostic of the spatial variability to be managed at the field level. Sugarcane has faced some challenges due to the limited solutions adapted to the crop, which develops throughout the year and involving a large-scale harvest. LiDAR (Light Detection and Ranging) technology is a high-resolution tool that permits the measurement of vegetative growth in a non-destructive way, assisting, for example, in harvest planning. The objective was to describe the three-dimensional (3D) data processing to characterize the spatial variability of sugarcane fields in the pre-harvest period. An aerial platform was used for data acquisition 10 days before and after harvesting. The digital models of surface, of terrain, and the canopy height model (CHM) were generated to spatialize plants height based on point cloud. The LiDAR-derived metrics extracted were percentiles (P50th; P90th–P99th), with the highest value of the coefficient of variation observed for the P50th (59%), indicating that there is high spatial variability in plant height. The RMSE (Root Mean Squared Error) among field measurements and sugarcane stalk height from CHM was 0.47 m. This study demonstrates that 3D sensing data can provide relevant information for the assessment of the crop height and, potentially, to consider it as an indicator of the field regions with distinct levels of production.

Sugarcane harvesters have a high level of embedded technology and the opportunity to expand applications to become an important high-density data collection machine. The acquired data, such as yield, losses, and quality, would provide valuable information for site-specific management of sugarcane. This review describes the current instrumentation used by sugarcane harvesters to map yield with the current technologies that have the highest potential applications for losses and quality mapping. In sugarcane cultivation, the harvester cuts and processes the product along a single or double row, which makes it easier to evaluate yield, losses, and quality at the row level. However, studies that explore the holistic potential of the sensors and data processing from the harvester for within-row detailed spatial information are scarce. Over the years, several studies focused on sugarcane yield mapping; however, yield monitors are far from being popular among sugarcane producers due to its low accuracy. Yield monitors need to be robust and accurate; the data generated from default factory-installed sensors is a potential alternative to improve data collection. Also, the integration of the current data available on the harvesters and the use of sensors to estimate sugarcane parameters (i.e., yield, losses, and quality) may represent an important advance in the agricultural operations. This article provides some information regarding the automation of the machines and the operational improvements, such as logistics planning and machine performance.

The vegetation index (VI) generated from orbital images are essential tools to identify the spatial variability of the crops. The objective of this study was to evaluate the spatial variability of sugarcane fields using imagery data. Also, to explore the ideal period to correlate the Normalized Difference Vegetation Index (NDVI), Normalized Difference Red-Edge Index (NDRE) and Wide Dynamic Range Vegetation Index (WDRVI) with sugarcane yield. Four fields were selected in the state of Sao Paulo (56.37 ha) during the 2017/2018 and 2018/2019 growing seasons, as well as five fields in the state of Goias (86.86 ha) during the 2019/2020 growing season. The VIs were calculated using orbital images from Sentinel-2 (spatial resolution of 10 m). The yield data were generated by a commercial sensor-system installed on the harvesters with a resolution of 0.20 Hz. Yield data were filtered and interpolated using the same resolution of the orbital images. Pearson's correlation was calculated between the yield and the VIs for each orbital image. The considered VIs were able to identify the spatial variability of sugarcane fields with coefficients of correlation of 0.95 and 0.96. The sugarcane stalks growth was the best period to correlate the VIs and the yield maps among the analyzed fields.

Monitoring the spatial variability of agricultural variables is a main step in implementing precision agriculture practices. Active optical sensors (AOS), with their instrumentation directly on agricultural machines, are suitable and make it possible to obtain high-frequency data. This study aimed to evaluate the potential of AOS to map the spatial and temporal variability of coffee crop yields, as well as to establish guidelines for the acquisition of AOS data for sensing the sides of a coffee plant, allowing the evaluation of large commercial fields. The study was conducted in a commercial coffee area of 10.24 ha, cultivated with the Catuaí 144 variety. Data collection was performed with six Crop Circle ACS 430 sensors (Holland Scientific, Lincoln, NE, USA) and two N-Sensor NG sensors (Yara International, Dülmen, Germany). Seven field expeditions were made to collect data using the optical sensors during 2019 and 2021, obtaining data during the flowering, fruit-filling and fruit maturation phases (pre-harvest), and post-harvest. The results showed that the different faces of the same plant present a different Pearson’s correlation coefficient (r) to its yield, obtained with a yield monitor on the harvester. The face with the highest exposure to solar radiation presented a slightly higher correlation to yield (−0.34 ≤ r ≤ −0.17) when compared with the face with less exposure (−0.27 ≤ r ≤ −0.15). In addition, it was observed that the vegetation indices measured at the beginning of the coffee cycle (before the rainy season that starts in October) present a positive correlation to the coffee yield of that same year (0.73 ≤ r ≤ 0.91). On the other hand, this relationship is changed after the beginning of the rain season, at which time the vegetation index increases abruptly, inverting the correlation with the yield after that (−0.93 ≤ r ≤ −0.77). Furthermore, it was observed that, due to the biennial nature of coffee production, the vegetation index acquired at a specific time has an inverted relationship when compared with the yield of that year and to the yield of the following (or previous) year.

Data-driven decisions can be performed based on crop yield values, essential information for precision agriculture practices. Technical solutions for yield mapping have been increasing for the sugarcane crop. However, the adoption of a yield monitor is low among farmers. An alternative is associating the amount of sugarcane harvested with the yield. The objective of this study was to evaluate the accuracy of the sugarcane mass prediction by a hydraulic oil pressure sensor installed in the chopper of the harvester. A commercial sugarcane field was used for the field trial with four harvesters and an in-field wagon instrumented with the load cells. All equipment at the harvesting front were equipped with ZigBee technology for data transfer to the sugar mill's Remote control center. The redistribution of the total weight of sugarcane harvested within each field was based on the chopper hydraulic pressure variation. The yield monitor had a low prediction error (4.5%) compared to the total measured by the in-field wagon. The results suggest enhancing the frequency of data collection by the harvester improves the spatial variability detection of sugarcane yield at the field level. The distribution of the total mass of sugarcane harvested indicated that neither empirical model nor sensors calibration is required to estimate yield regardless of the harvester. In future, the application of telemetry and distribution of the total harvest within the field should be studied for other crops, e.g., grains, which already use this technology for the management of equipment in the field.

The sugarcane production sector is one of the most adept at adopting technology to manage equipment and sugarcane fields. Developing new technologies and optimizing the use of the technologies already used in other production systems is essential for successful field management. The optimized use of technologies will help in the localized management to increase viability, maximize profitability, and minimize the environmental impacts of sugarcane production. Technologies to detect, measure, and spatialize plants can be one of the solutions for the row level management. Moreover, this data can be used to temporally follow the development of sugarcane fields, being essential data for localized field management. The spatialization of plants and plant spacing can help in the investigation of factors that influence sugarcane yield. In this context, the overall objective of the thesis was to explore tools and methods for detecting plants at row level to improve and support localized management of sugarcane plantations. An approach to sugarcane plant detection using photoelectric and ultrasonic sensors was developed and evaluated. Aerial image and ground sensors have been tested to detect and measure sugarcane plant spacing. Temporal evaluation of sensors and aerial images during four different stages of sugarcane development was made to propose the best time to detect sugarcane plants and measure the plant spacing. High-resolution images were used to map plant population and plant spacing. These two data were used to check the relationship between slope, path angle, and the plant population, furthermore, map regions with higher susceptibility to plant reduction over the years. At last, a spatio-temporal analysis of yield and plant spacing was performed to verify the relationship between these two variables in regions with different yield potentials in commercial crops. Results show that ultrasonic and photoelectric sensor fusion associated with the machine learning model has accuracy above 95%. These two sensors and high-resolution images had the best accuracy and precision in detecting and measuring plant spacing at 31 and 47 days after harvest. Spatial and temporal analysis showed that regions with a terrain slope of 5-8% and greater than 8% with curved paths have an inferior number of plants compared to other regions. The local analysis identified that regions with steeper slopes and curved paths have high susceptibility of plant reduction over the years compared to other regions. Finally, yield loss within the sugarcane row occurs with increasing plant spacing. Regions with different yield potentials require different optimum populations to maximize yield. Low-yielding regions require a larger plant population and are more susceptible to lose in yield within the row with increasing plant spacing. O setor de produção de cana-de-açúcar é um dos mais aptos a adotar tecnologia para gerenciar equipamentos e as lavouras de cana-de-açúcar. Desenvolver novas tecnologias e otimizar o uso das tecnologias já utilizadas em outros sistemas de produção é essencial para o sucesso da gestão das lavouras. O uso otimizado de tecnologias ajudará na gestão localizada a aumentar a viabilidade, maximizar a rentabilidade e minimizar os impactos ambientais da produção de cana-de-açúcar. Tecnologias para detectar, medir e espacializar plantas podem ser uma das soluções para o gerenciamento a nível de fileira. Além disso, estes dados podem ser usados para acompanhar temporariamente o desenvolvimento das lavouras de cana-de-açúcar, sendo dados essenciais para o gerenciamento localizado da lavoura. A espacialização das plantas e o espaçamento entre plantas podem ajudar na investigação dos fatores que influenciam a produtividade da cana-de-açúcar. Neste contexto, o objetivo geral da tese foi explorar ferramentas e métodos de detecção de plantas em nível de fileira para melhorar e apoiar o gerenciamento localizado de plantações de cana-de-açúcar. Uma abordagem para a detecção de plantas de cana-de-açúcar usando sensores fotoelétricos e ultrassônicos foi desenvolvida e avaliada. A imagem aérea e os sensores terrestres foram testados para detectar e medir o espaçamento entre plantas de cana-de-açúcar. A avaliação temporal dos sensores e imagens aéreas durante quatro estágios diferentes de desenvolvimento da cana-de-açúcar foi feita para propor o melhor momento para detectar plantas de cana-de-açúcar e medir o espaçamento entre as plantas. Imagens de alta resolução foram usadas para mapear a população e o espaçamento das plantas. Estes dois dados foram utilizados para verificar a relação entre declividade, ângulo do percurso e a população de plantas, além disso, mapear regiões com maior suscetibilidade à redução de plantas ao longo dos anos. Finalmente, foi realizada a análise espacial-temporal da produtividade e espaçamento de plantas para verificar a relação entre estas duas variáveis em regiões com diferentes potenciais produtivos em lavouras comerciais. Os resultados mostram que a fusão de sensores ultrassônico e fotoelétrico associada ao modelo de aprendizagem da máquina tem precisão acima de 95%. Estes dois sensores e imagens de alta resolução tiveram a melhor precisão e acurácia para detectar e medir o espaçamento das plantas em 31 e 47 dias após a colheita. A análise espacial e temporal mostrou que regiões com uma declive do terreno de 5-8% e maior que 8% com percursos curvos têm um número inferior de plantas em comparação com outras regiões. A análise local identificou que regiões com declives mais acentuados e caminhos curvos têm alta suscetibilidade de redução da planta ao longo dos anos, em comparação com outras regiões. Finalmente, a perda de produtividade dentro da fileira da cana de açúcar ocorre com o aumento do espaçamento entre as plantas. Regiões com diferentes potenciais produtivos requerem diferentes populações ótimas para maximizar a produtividade. Regiões de baixa produtividade requerem uma população de plantas maior e são mais suscetíveis a perder produtividade dentro da fileira com o aumento do espaçamento entre plantas.

Measuring the mass flow of sugarcane in real-time is essential for harvester automation and crop monitoring. Data integration from multiple sensors should be an alternative to receive more reliable, accurate, and valuable predictions than data delivered by a single sensor. In this sense, the objective was to evaluate if the fusion of different sensors installed in a sugarcane harvester improves the mass flow prediction accuracy. A harvester was experimentally instrumented, and neural network models integrated sensor data along the harvester to perform the self-calibration of these sensors and estimate the mass flow. Nonlinear autoregressive networks with exogenous input (NARX) and multiple linear regression (MLR) models were compared to predict the mass flow. The prediction with the NARX showed a significant superiority over MLR. MLR decreases the estimated mass flow variability in the harvester. NARX with multi-sensor data has an RMSE of 0.3 kg s−1, representing a MAPE of 0.7%. The fusion of sensor signals improves prediction accuracy, with higher performance than studies with approaches that used a single sensor. The mass flow approach with multiple sensors is a potential approach to replace conventional yield monitors. The system generates accurate data with high sample density within sugarcane rows.

Yield maps provide essential information to guide precision agriculture (PA) practices. Yet, on-board yield monitoring for sugarcane can be challenging. At the same time, orbital images have been widely used for indirect crop yield estimation for many crops like wheat, corn, and rice, but not for sugarcane. Due to this, the objective of this study is to explore the potential of multi-temporal imagery data as an alternative for sugarcane yield mapping. The study was based on developing predictive sugarcane yield models integrating time-series orbital imaging and a machine learning technique. A commercial sugarcane site was selected, and Sentinel-2 images were acquired from the beginning of the ratoon sprouting until harvesting of two consecutive cropping seasons. The predictive yield models RF (Random forest) and MLR (Multiple Linear Regression) were developed using orbital images and yield maps generated by a commercial sensor-system on harvesting. Original yield data were filtered and interpolated with the same spatial resolution of the orbital images. The entire dataset was divided into training and testing datasets. Spectral bands, especially the near-infrared at tillering crop stage showed greater contribution to predicting sugarcane yield than the use of derived spectral vegetation indices. The Root Mean Squared Error (RMSE) obtained for the RF regression based on multiple spectral bands was 4.63 Mg ha−1 with an R2 of 0.70 for the testing dataset. Overall, the RF regression had better performance than the MLR to predict sugarcane yield.

Identifying gaps within sugarcane rows is an effective strategy to optimise inputs using site-specific approaches. This work aimed to compare four different sensor-based techniques to identify and measure sugarcane gaps.Specifically, it was analysed three strategies with sensors (vegetative index, ultrasonic, photoelectric) mounted on a tractor, and one strategy using an RGB camera on-boarded to a remotely piloted aircraft (RPA); the latter being the current commercial method. Field trials were performed during four crop stages of development: 19, 31, 47, and 59 days after harvest (DAH). The successful gap identification was evaluated by accuracy, precision, and recall. We use the root-mean-square error (RMSE) to evaluate sensors in measuring the length of the gaps. All sensor-based techniques had accuracy between 80% and 92% in identifying the gaps at 31 and 47 DAH. At 19 DAH, the sensor-based methods overestimate the number of gaps, and at 59 DAH, there was an underestimation of gaps. The photoelectric sensor has the best performance in measuring the length of the gaps (RMSE ≤ 0.18 m) with the least variation in RMSE over the stage of sugarcane development. The vegetative index sensor (VIS) and RPA images had similar performance, with the RMSE ranging between 0.11 and 0.40 m. The canopy of the plants in the 47 and 59 DAH affected these two methodologies. The larger is the plant canopy, the lower is their ability to identify and measure the gaps.

Proximal sensing for assessing sugarcane quality information during harvest can be affected by various factors, including the type of sample preparation. The objective of this study was to determine the best sugarcane sample type and analyze the spectral response for the prediction of quality parameters of sugarcane from visible and near-infrared (vis-NIR) spectroscopy. The sampling and spectral data acquisition were performed during the analysis of samples by conventional methods in a sugar mill laboratory. Samples of billets were collected and four modes of scanning and sample preparation were evaluated: outer-surface (‘skin’) (SS), cross-sectional scanning (CSS), defibrated cane (DF), and raw juice (RJ) to analyze the parameters soluble solids content (Brix), saccharose (Pol), fibre, pol of cane and total recoverable sugars (TRS). Predictive models based on Partial Least Square Regression (PLSR) were built with the vis-NIR spectral measurements. There was no significant difference (p-value &gt, 0.05) between the accuracy SS and CSS samples compared to DF and RJ samples for all prediction models. However, DF samples presented the best predictive performance values for the main sugarcane quality parameters, and required only minimal sample preparation. The results contribute to advancing the development of on-board quality monitoring in sugarcane, indicating better sampling strategies.

The adaptation of the Global Navigation Satellite Systems (GNSS) technology to fit the needs of farmers requires knowledge of the accuracy level delivered by a GNSS receiver in working conditions. To date, no methodology indicates the minimum number of replications to perform a statistical comparison. This study aims to advance knowledge on the methodological approach for evaluating the static and dynamic performance of GNSS receivers commonly used in agricultural operations. For the static test, a supporting frame in the ground carried all the receivers with coordinates properly transported. In the dynamic test, a circular rail with a 9.55 m radius was installed at ground level with a platform driven by an electric motor to carry the receivers at a constant speed. The transversal error of the receiver to the circular reference line was measured. The error with 95 % probability (E95) to receivers without differential correction ranged between 4.22 m and 0.85 m in the static test, and 2.25 m and 0.98 m in the dynamic test. Receivers with differential correction had E95 values below 0.10 m in the static test and 0.16 m in the dynamic test. Receivers with C/A code require five replications at minimum and 13 replications are needed for L1/L2 with differential correction signals in the dynamic test. The static test needs nine replications for C/A and five for L1/L2 with differential correction signals.

Carrot yield maps are an essential tool in supporting decision makers in improving their agricultural practices, but they are unconventional and not easy to obtain. The objective was to develop a method to generate a carrot yield map applying a random forest (RF) regression algorithm on a database composed of satellite spectral data and carrot ground-truth yield sampling. Georeferenced carrot yield sampling was carried out and satellite imagery was obtained during crop development. The entire dataset was split into training and test sets. The Gini index was used to find the five most important predictor variables of the model. Statistical parameters used to evaluate model performance were the root mean squared error (RMSE), coefficient of determination (R2) and mean absolute error (MAE). The five most important predictor variables were the near-infrared spectral band at 92 and 79 days after sowing (DAS), green spectral band at 50 DAS and blue spectral band at 92 and 81 DAS. The RF algorithm applied to the entire dataset presented R2, RMSE and MAE values of 0.82, 2.64 Mg ha&minus, 1 and 1.74 Mg ha&minus, 1, respectively. The method based on RF regression applied to a database composed of spectral bands proved to be accurate and suitable to predict carrot yield.

There is a need for new precision agriculture approaches that allow real-time intervention within sugarcane rows to reduce costs and minimize negative environmental impacts. Therefore, our goal was to test an alternative system for detection within rows of sugarcane plants. The objective was to determine the errors of an alternative system to detect targets of different sizes at different travel speeds. A system with a photoelectric sensor, ultrasonic sensor, and encoder was developed to detect and map the plants within the sugarcane row. The use of sensors separately and simultaneously for plant detection was compared. To improve the accuracy of plant detection, decision tree (DT), random forest (RF), and support vector machine (SVM) models were tested. The three machine learning (ML) models used data generated by the photoelectric and ultrasonic sensors along with the displacement sensor. The models were compared in terms of their precision in detecting plants within sugarcane rows. The approach with the two sensors and the DT model had the best precision (>90%) in plant detection. The sensors have the ability to detect 91% of the total plants (recall = 0.91). The travel speed influenced the performance of the sensors in detecting the targets, especially at 2 m s−1. The accuracy and precision of the plant detection system at different speeds indicate the possibility of the sensors being used in integrating systems for real-time interventions. In addition, the system generates data to plant and gap maps, which are useful information to support the site-specific management of sugarcane fields.

The mapping of sugarcane yield is still not as widely available as it is for grain crops. Sugarcane harvesters cut and process the cane in a single or maximum of two rows, facilitating the monitoring of cane yield and its behavior on a small scale. This study tested a method for sugarcane yield data cleaning, investigating if the data recording frequency influences the characterization of yield variations in mapping high-resolution spatial data within a single row. Four data sets from yield monitors of single row harvesting were used. A cleaning process with global and anisotropic filtering in a single sugarcane row was applied. The local outlier cleaner compares the yield value of a point with its nearest neighbors within the same row. Even after the elimination of outliers, there is great variation in yield between the rows, and this variation is much smaller in a single row. A frequency of 2 Hz was required for identifying and characterizing small yield variations within the sugarcane rows whilst other frequencies tried (0.2 and 0.1 Hz) resulted in loss of information on yield variability within the row. The difference between the root mean square error (RMSE) of ordinary kriging (OK) and inverse distance weighting (IDW) techniques is large enough to suggest the use of an individual yield line. Individual yield lines saved information in the data generated by the yield monitor unlike IDW and OK interpolation methods which omitted information over short distances within the rows and compromised the quality of high-resolution maps.

Information regarding sugarcane yield is the starting point for the application of Precision Agriculture (PA) strategies to the management of sugarcane fields. Over the years, many sugarcane yield monitoring approaches have been developed and tested, but its use is still limited. One option is to use data generated by the sugarcane harvester provided in the controller area network (CAN), which allows getting the messages related to the harvester operation. Our goal was to train and to test random forest (RF), multiple linear regression (MLR), and artificial neural network (ANN) using CAN data available on the on-board computer of the harvester. All predictive models were trained and tested using the main engine parameters: fuel consumption, engine rotation, engine power, and specific fuel consumption (SFC) as data input. A scale yield monitor was installed on the harvester elevator to provide the georeferenced yield data. The yield prediction accuracy of the predictive models using the four parameters was compared. All models followed the observed sugarcane yield and recognized the changes over the time of data collection. The MLR and ANN models have a higher error of prediction in the extreme values of yield. Over the testing time, the ANN underestimated the sugarcane yield, and the RF prediction by the engine parameters of the harvester was coming closest to the observed yield. The best results for predicting sugarcane yield by engine parameters were obtained from the RF model with a mean absolute percent error (MAPE) of 5.6%, and root mean square error (RMSE) of 7.0 Mg ha−1. The MLR and ANN models have a MAPE of 7.8% and 5.6%, respectively. All the variables were necessary for a better performance of the models; however, SFC was the most important variable for predicting sugarcane yield.

Na cultura da cana-de-açúcar, a colheita é realizada por uma colhedora que efetua o corte e processamento do produto colhido ao longo de uma (ou duas) fileira (s) da cultura estabelecida. Neste processo, dados obtidos por monitor de produtividade, quando existentes, fornecem informações com diferentes utilidades. Métodos existentes para o processamento de dados de produtividade utlizados atualmente foram desenvolvidos para conjuntos de dados de produtividade de grãos e quando aplicados a um conjunto de dados de produtividade de cana-de-açúcar podem eliminar dados com variações reais de produtividade dentro da fileira. O objetivo deste trabalho é desenvolver métodos que busquem identificar e remover dados errôneos, em pós-processamento, do conjunto de dados gerados por monitor de produtividade para caracterização das pequenas variações de produtividade dentro de uma fileira de cana-de-açúcar. A identificação de dados discrepantes do conjunto de dados utilizando método estatístico por quartis e uma filtragem comparando valores de produtividade usando somente dados de uma única passada da colhedora foi proposto. Foram utlizados quatro conjunto de dados de produtividade gerados por dois monitores. O monitor de produtividade 1 registrou os dados a uma frequência de 0,5 Hz e o monitor de produtividade 2 a uma frequência de 1 Hz. Foram encontrados dados errôneos gerados devido ao tempo de sincronização entre a colhedora e o conjunto transbordo durante as manobras de cabeceira e durante a troca do conjunto de transbordo. Também foram encontrados dados durante a manobras da colhedora, onde o monitor registrou dados com produtividade zero e nulas. Foram simuladas diferentes frequência de registro de dados com objetivo de verificar se a densidade de dados fornecida pelo monitor influência na caracterização de pequenas variações nos valores de produtividade dentro da passada. Os conjuntos de dados de produtividade gerados por diferentes tipos de monitores demostraram a necessidade de pós-processamento para remoção devalores de produtividades discrepantes. A metodologia desenvolvida neste trabalho foi capaz de identificar e eliminar os dados errôneos dos conjuntos de dados analisados. A metodologia de filtragem de dados considerando somente dados dentro de uma única passada da colhedora de cana-de-açúcar proporcionou a caracterização da variação de valores de produtividade em pequenas distâncias. In the sugarcane crop, a harvest is performed by a harvester who cuts and processes the product harvested along one (or two) row (s) of the established crop. In this process, data from yield monitor, when applicable, provide information with different utilities. Existing methods for processing yield data currently used have been developed for datasets of yield grain and when applied to a sugarcane yield dataset can eliminate data with actual variations of yield within the row. The objective of this work is to develop methods that seek to identify and remove erroneous data, in post-processing, from the data set generated by yield monitor to characterize the small variations of yield within a row of sugarcane. The identification of outliers from the data set using statistical method for comparing quartiles and filtering yield values using only data from a single past the harvester has been proposed. Assay were utilized four yield dataset generated by two monitors. The yield monitor 1 recorded data at a frequency of 0.5 Hz and the yield monitor 2 at a frequency of 1 Hz. Erroneous data were found in the data set generated due to the time of synchronization between the sugarcane harvester and the transportation of chopped sugarcane during the headland turns and during the exchange of the transportation of chopped sugarcane during harvest. Were also found during the headland turns of the sugarcane harvester, where the yield monitor recorded data with values of yield zero and void. It was simulated different frequency of recording data with the objective of verifying if density of data provided by the monitor influences in the characterization of small variations in the yield values within the path. The yield data sets generated by different types of displays have demonstrated the need for post-processing to remove outliers in the yield dataset. The methodology developed in this study was able to identify and eliminate erroneous data sets analyzed data. Data filtering methodology considering only data within a single pass of the sugarcane harvester provided to characterize the variation in yield values over short distances.