Mailson Freire de Oliveira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mailson Freire de Oliveira has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Rouverson Pereira da Silva
Department of Agricultural Sciences, School of Agricultural and Veterinary Studies, São Paulo State University, Jaboticabal 14884-900, SP, Brazil
7 shared publications - Franciele Morlin Carneiro
Department of Agriculture, Federal Technological University of Paraná (UTFPR), Santa Helena 85892-000, Paraná, Brazil
4 shared publications - Adão Felipe dos Santos
Universidade Federal de Lavras, Brasil
3 shared publications Antonio Tassio Santana Ormond
2 shared publications- Brenda V. Ortiz
Auburn University, Department of Crop Soil and Environmental Sciences, Auburn, AL, United States
2 shared publications Carlos Eduardo Angeli Furlani
2 shared publications
Latest Publications
- 25 January 2024
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 218, 108647
Predicting below and above-ground peanut biomass and maturity using multi-target regression
- 25 January 2024
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 218, 108647
Predicting below and above-ground peanut biomass and maturity using multi-target regression
- Open Access
Identifying Nematode Damage on Soybean through Remote Sensing and Machine Learning Techniques
Identifying nematode damage in large soybean areas is not always achievable in a practical way. Multispectral reflectance sensors have not been thoroughly evaluated to detect nematode damage in soybeans (Glycine max L.). The main research aims of this study were to: (i) determine the bivariate relationship between individual spectral bands and vegetation indices (VIs) relative to soybean conditions (symptomatic versus asymptomatic), and (ii) to select the best model for identifying plant conditions using three algorithms (logistic regression—LR, random forest—RF, conditional inference tree—CIT) and three options for data input using bands, vegetation indices (VIs), and bands plus VIs. The trial was conducted in Brazil on three on-farm soybean fields presenting different species of nematode infestation. Multispectral imagery was obtained using a drone-mounted MicaSense RedEdge® sensor. At each sampling, georeferenced point nematode infestation and spectral measurements of soybean plants were retrieved for the classification of symptomatic and asymptomatic areas, according to the threshold level adopted. Bivariate analysis of variance (ANOVA), LR, RF, and CIT were used to select the multispectral bands/VIs that discriminated among symptomatic and asymptomatic plants, assessing the best model via their respective parameters for accuracy, sensitivity, and specificity. The greatest classification accuracy (>0.70) was achieved when using the CIT algorithm with the spectral bands only, with green (560 ± 20 nm) and near-infrared (840 ± 40 nm) included as the main spectral input variables in the model. These results demonstrate the potential of combining remotely sensed data and machine learning to distinguish nematode-symptomatic and asymptomatic soybean plants.
Open AccessIdentifying Nematode Damage on Soybean through Remote Sensing and Machine Learning Techniques
Identifying nematode damage in large soybean areas is not always achievable in a practical way. Multispectral reflectance sensors have not been thoroughly evaluated to detect nematode damage in soybeans (Glycine max L.). The main research aims of this study were to: (i) determine the bivariate relationship between individual spectral bands and vegetation indices (VIs) relative to soybean conditions (symptomatic versus asymptomatic), and (ii) to select the best model for identifying plant conditions using three algorithms (logistic regression—LR, random forest—RF, conditional inference tree—CIT) and three options for data input using bands, vegetation indices (VIs), and bands plus VIs. The trial was conducted in Brazil on three on-farm soybean fields presenting different species of nematode infestation. Multispectral imagery was obtained using a drone-mounted MicaSense RedEdge® sensor. At each sampling, georeferenced point nematode infestation and spectral measurements of soybean plants were retrieved for the classification of symptomatic and asymptomatic areas, according to the threshold level adopted. Bivariate analysis of variance (ANOVA), LR, RF, and CIT were used to select the multispectral bands/VIs that discriminated among symptomatic and asymptomatic plants, assessing the best model via their respective parameters for accuracy, sensitivity, and specificity. The greatest classification accuracy (>0.70) was achieved when using the CIT algorithm with the spectral bands only, with green (560 ± 20 nm) and near-infrared (840 ± 40 nm) included as the main spectral input variables in the model. These results demonstrate the potential of combining remotely sensed data and machine learning to distinguish nematode-symptomatic and asymptomatic soybean plants.
- Open Access
Integrating Satellite and UAV Data to Predict Peanut Maturity upon Artificial Neural Networks
The monitoring and determination of peanut maturity are fundamental to reducing losses during digging operation. However, the methods currently used are laborious and subjective. To solve this problem, we developed models to access peanut maturity using images from unmanned aerial vehicles (UAV) and satellites. We evaluated an area of approximately 8 hectares in which a regular grid of 30 points was determined with weekly evaluations starting at 90 days after sowing. Two Artificial Neural Networking (ANN) were used with Radial Basis Function (RBF) and Multilayer Perceptron (MLP) to predict the Peanut Maturity Index (PMI) with the spectral bands available from each sensor. Several vegetation indices were used as input to the ANN, with the data being split 80/20 for training and validation, respectively. The vegetation index, Normalized Difference Red Edge Index (NDRE), was the most precise coefficient of determination (R2 = 0.88) and accurate mean absolute error (MAE = 0.06) for estimating PMI, regardless of the type of ANN used. The satellite with Normalized Difference Vegetation Index (NDVI) could also determine PMI with better accuracy (MAE = 0.05) than the NDRE. The performance evaluation indicates that the RBF and MLP networks are similar in predicting peanut maturity. We concluded that satellite and UAV images can predict the maturity index with good accuracy and precision.
Open AccessIntegrating Satellite and UAV Data to Predict Peanut Maturity upon Artificial Neural Networks
The monitoring and determination of peanut maturity are fundamental to reducing losses during digging operation. However, the methods currently used are laborious and subjective. To solve this problem, we developed models to access peanut maturity using images from unmanned aerial vehicles (UAV) and satellites. We evaluated an area of approximately 8 hectares in which a regular grid of 30 points was determined with weekly evaluations starting at 90 days after sowing. Two Artificial Neural Networking (ANN) were used with Radial Basis Function (RBF) and Multilayer Perceptron (MLP) to predict the Peanut Maturity Index (PMI) with the spectral bands available from each sensor. Several vegetation indices were used as input to the ANN, with the data being split 80/20 for training and validation, respectively. The vegetation index, Normalized Difference Red Edge Index (NDRE), was the most precise coefficient of determination (R2 = 0.88) and accurate mean absolute error (MAE = 0.06) for estimating PMI, regardless of the type of ANN used. The satellite with Normalized Difference Vegetation Index (NDVI) could also determine PMI with better accuracy (MAE = 0.05) than the NDRE. The performance evaluation indicates that the RBF and MLP networks are similar in predicting peanut maturity. We concluded that satellite and UAV images can predict the maturity index with good accuracy and precision.
- Open Access
- 31 March 2022
- Published by Portal de Periódicos UFU - Universidade Federal de Uberlandia in Bioscience Journal
- Vol. 38, e38024
Biophysical characteristics of soybean estimated by remote sensing associated with artificial intelligence
The biophysical characteristics of vegetative canopies, such as biomass, height, and canopy diameter, are of paramount importance for the study of the development and productive behavior of crops. Faced with a scarcity of studies aimed at estimating these parameters, the objective of this study was to evaluate the performance of artificial neural networks (ANNs) applied to Proximal Remote Sensing (PRS) to estimate biophysical characteristics of soybean culture. The data used to train and validate the ANNs came from an experiment composed of 65 plots with 30 x 30 m mesh, its development was carried out in the 2016/2017 crop in the Brazilian agricultural area. The evaluations were carried out at 30, 45, 60, and 75 days after sowing (DAS), monitoring the spatial and temporal variability of the biophysical characteristics of the soybean crop. Vegetation indexes were collected using canopy sensors. The accuracy and precision were determined by the coefficient of determination (R2) and the error of the forecasts by MAPE (Mean Absolute Percentage Error). PRS and ANNs showed high potential for application in agriculture, since they obtained good performance in the estimation of height (R2 = 0.89) and canopy diameter (R2 = 0.96), being fresh biomass (R2 =0.98) and dry biomass (R2 = 0.97) were the best-estimated variables.
- 31 March 2022
- Published by Portal de Periódicos UFU - Universidade Federal de Uberlandia in Bioscience Journal
- Vol. 38, e38024
Open AccessBiophysical characteristics of soybean estimated by remote sensing associated with artificial intelligence
The biophysical characteristics of vegetative canopies, such as biomass, height, and canopy diameter, are of paramount importance for the study of the development and productive behavior of crops. Faced with a scarcity of studies aimed at estimating these parameters, the objective of this study was to evaluate the performance of artificial neural networks (ANNs) applied to Proximal Remote Sensing (PRS) to estimate biophysical characteristics of soybean culture. The data used to train and validate the ANNs came from an experiment composed of 65 plots with 30 x 30 m mesh, its development was carried out in the 2016/2017 crop in the Brazilian agricultural area. The evaluations were carried out at 30, 45, 60, and 75 days after sowing (DAS), monitoring the spatial and temporal variability of the biophysical characteristics of the soybean crop. Vegetation indexes were collected using canopy sensors. The accuracy and precision were determined by the coefficient of determination (R2) and the error of the forecasts by MAPE (Mean Absolute Percentage Error). PRS and ANNs showed high potential for application in agriculture, since they obtained good performance in the estimation of height (R2 = 0.89) and canopy diameter (R2 = 0.96), being fresh biomass (R2 =0.98) and dry biomass (R2 = 0.97) were the best-estimated variables.
- Open Access
- 25 December 2021
- Published by MDPI AG in Remote Sensing
- Vol. 14 (1) , 93
Using UAV and Multispectral Images to Estimate Peanut Maturity Variability on Irrigated and Rainfed Fields Applying Linear Models and Artificial Neural Networks
Using UAV and multispectral images has contributed to identifying field variability and improving crop management through different data modeling methods. However, knowledge on application of these tools to manage peanut maturity variability is still lacking. Therefore, the objective of this study was to compare and validate linear and multiple linear regression with models using artificial neural networks (ANN) for estimating peanut maturity under irrigated and rainfed conditions. The models were trained (80% dataset) and tested (20% dataset) using results from the 2018 and 2019 growing seasons from irrigated and rainfed fields. In each field, plant reflectance was collected weekly from 90 days after planting using a UAV-mounted multispectral camera. Images were used to develop vegetation indices (VIs). Peanut pods were collected on the same dates as the UAV flights for maturity assessment using the peanut maturity index (PMI). The precision and accuracy of the linear models to estimate PMI using VIs were, in general, greater in irrigated fields with R2 > 0.40 than in rainfed areas, which had a maximum R2 value of 0.21. Multiple linear regressions combining adjusted growing degree days (aGDD) and VIs resulted in decreased RMSE for both irrigated and rainfed conditions and increased R2 in irrigated areas. However, these models did not perform successfully in the test process. On the other hand, ANN models that included VIs and aGDD showed accuracy of R2 = 0.91 in irrigated areas, regardless of using Multilayer Perceptron (MLP; RMSE = 0.062) or Radial Basis Function (RBF; RMSE = 0.065), as well as low tendency (1:1 line). These results indicated that, regardless of the ANN architecture used to predict complex and non-linear variables, peanut maturity can be estimated accurately through models with multiple inputs using VIs and aGDD. Although the accuracy of the MLP or RBF models for irrigated and rainfed areas separately was high, the overall ANN models using both irrigated and rainfed areas can be used to predict peanut maturity with the same precision.
- 25 December 2021
- Published by MDPI AG in Remote Sensing
- Vol. 14 (1) , 93
Open AccessUsing UAV and Multispectral Images to Estimate Peanut Maturity Variability on Irrigated and Rainfed Fields Applying Linear Models and Artificial Neural Networks
Using UAV and multispectral images has contributed to identifying field variability and improving crop management through different data modeling methods. However, knowledge on application of these tools to manage peanut maturity variability is still lacking. Therefore, the objective of this study was to compare and validate linear and multiple linear regression with models using artificial neural networks (ANN) for estimating peanut maturity under irrigated and rainfed conditions. The models were trained (80% dataset) and tested (20% dataset) using results from the 2018 and 2019 growing seasons from irrigated and rainfed fields. In each field, plant reflectance was collected weekly from 90 days after planting using a UAV-mounted multispectral camera. Images were used to develop vegetation indices (VIs). Peanut pods were collected on the same dates as the UAV flights for maturity assessment using the peanut maturity index (PMI). The precision and accuracy of the linear models to estimate PMI using VIs were, in general, greater in irrigated fields with R2 > 0.40 than in rainfed areas, which had a maximum R2 value of 0.21. Multiple linear regressions combining adjusted growing degree days (aGDD) and VIs resulted in decreased RMSE for both irrigated and rainfed conditions and increased R2 in irrigated areas. However, these models did not perform successfully in the test process. On the other hand, ANN models that included VIs and aGDD showed accuracy of R2 = 0.91 in irrigated areas, regardless of using Multilayer Perceptron (MLP; RMSE = 0.062) or Radial Basis Function (RBF; RMSE = 0.065), as well as low tendency (1:1 line). These results indicated that, regardless of the ANN architecture used to predict complex and non-linear variables, peanut maturity can be estimated accurately through models with multiple inputs using VIs and aGDD. Although the accuracy of the MLP or RBF models for irrigated and rainfed areas separately was high, the overall ANN models using both irrigated and rainfed areas can be used to predict peanut maturity with the same precision.
- 1 September 2021
- Published by Elsevier in European Journal of Agronomy
- Vol. 129
Use of remote sensing to characterize the phenological development and to predict sweet potato yield in two growing seasons
- 1 September 2021
- Published by Elsevier in European Journal of Agronomy
- Vol. 129
Use of remote sensing to characterize the phenological development and to predict sweet potato yield in two growing seasons
- Open Access
- 1 August 2019
- Published by FapUNIFESP (SciELO) in Revista Brasileira de Engenharia Agrícola E Ambiental
- Vol. 23 (8) , 630-637
Quality of mechanical peanut sowing and digging using autopilot
Over the past decade, automatic guidance of agricultural machinery via Global Navigation Satellite System (GNSS) signals has been increasingly adopted by the farming community. Peanut farmers are adopting such technology in order to improve the parallelism of operations to address difficulties that occur in mechanical digging, where losses are a big problem. This study aimed to evaluate mechanized operations of peanut sowing and digging controlled manually and by autopilot, along with their quality. The treatments consisted of two digging operations, with and without autopilot, and two displacement speeds (4.5 and 6.0 km h-1). The experiment was conducted in a medium-textured soil in a completely randomized design arranged in bands, using the analyzed variables as quality indicators. At sowing, parallelism between passes of the tractor-sower set, was evaluated at 120 points of each system (manual and automatic routing). The digging losses were evaluated in the two guidance systems, under two displacement speeds (4.5 to 6.0 km h-1) at 15 points per treatment. It was verified that the parallelism between the passes of the tractor-sower set was better when using the autopilot, which improved the operation quality. Displacement speed did not influence the digging loss. There were no differences in the visible digging loss, but higher quality was obtained when the operation was performed using autopilot. Minor invisible and total digging losses were obtained when the digging was performed with automatic routing, and superior quality was found at a speed of 4.5 km h-1; however, quality was adversely affected under manual operation. Thus, the use of autopilot is effective for improving the accuracy and the quality of the operations.
- 1 August 2019
- Published by FapUNIFESP (SciELO) in Revista Brasileira de Engenharia Agrícola E Ambiental
- Vol. 23 (8) , 630-637
Open AccessQuality of mechanical peanut sowing and digging using autopilot
Over the past decade, automatic guidance of agricultural machinery via Global Navigation Satellite System (GNSS) signals has been increasingly adopted by the farming community. Peanut farmers are adopting such technology in order to improve the parallelism of operations to address difficulties that occur in mechanical digging, where losses are a big problem. This study aimed to evaluate mechanized operations of peanut sowing and digging controlled manually and by autopilot, along with their quality. The treatments consisted of two digging operations, with and without autopilot, and two displacement speeds (4.5 and 6.0 km h-1). The experiment was conducted in a medium-textured soil in a completely randomized design arranged in bands, using the analyzed variables as quality indicators. At sowing, parallelism between passes of the tractor-sower set, was evaluated at 120 points of each system (manual and automatic routing). The digging losses were evaluated in the two guidance systems, under two displacement speeds (4.5 to 6.0 km h-1) at 15 points per treatment. It was verified that the parallelism between the passes of the tractor-sower set was better when using the autopilot, which improved the operation quality. Displacement speed did not influence the digging loss. There were no differences in the visible digging loss, but higher quality was obtained when the operation was performed using autopilot. Minor invisible and total digging losses were obtained when the digging was performed with automatic routing, and superior quality was found at a speed of 4.5 km h-1; however, quality was adversely affected under manual operation. Thus, the use of autopilot is effective for improving the accuracy and the quality of the operations.
- Open Access
- 29 April 2019
- Published by Canadian Center of Science and Education in Journal of Agricultural Science
- Vol. 11 (6) , p493
Prediction Models of Corn Yield by NDVI in Function of the Spacing Arrangement
There is a need for the use of tools to estimate productive potential during corn crop development. Thus, the assistence by means of active optical sensors for the generating of vegetation indexes can provide significant information for the knowledge of the behavior and temporal relation of this index with productive parameters of the agricultural crops. It was aimed to evaluate the temporal behavior of NDVI and its relation with yield of corn in order to generate yield prediction models in plant populations (55, 60 and 65 thousand plants ha-1) in spacing of conventional seeding and twin rows. A factorial 2 × 3 was utilized with four replicates, with a total of 24 experimental plots of 10 m2 in randomized blocks, performing reading NDVI at 5 seasons (30, 45, 60, 75 and 90 days after emergence of the plants DAE). The spacing in twin rows at 30 and 90 DAE for populations of 55 and 60 thousand plants ha-1, respectively, allowed to generate models for the prediction of productivity based on corn NDVI, while the population of 65 thousand plants ha-1 at 45 and 60 DAE there was no adjustment by the prediction model of yield by values close to NDVI for different productivities. In the conventional spacing generating models for the prediction of yield was possible in the populations of 55 and 60 thousand plants ha-1 respectively at 30 and 90 DAE.
- 29 April 2019
- Published by Canadian Center of Science and Education in Journal of Agricultural Science
- Vol. 11 (6) , p493
Open AccessPrediction Models of Corn Yield by NDVI in Function of the Spacing Arrangement
There is a need for the use of tools to estimate productive potential during corn crop development. Thus, the assistence by means of active optical sensors for the generating of vegetation indexes can provide significant information for the knowledge of the behavior and temporal relation of this index with productive parameters of the agricultural crops. It was aimed to evaluate the temporal behavior of NDVI and its relation with yield of corn in order to generate yield prediction models in plant populations (55, 60 and 65 thousand plants ha-1) in spacing of conventional seeding and twin rows. A factorial 2 × 3 was utilized with four replicates, with a total of 24 experimental plots of 10 m2 in randomized blocks, performing reading NDVI at 5 seasons (30, 45, 60, 75 and 90 days after emergence of the plants DAE). The spacing in twin rows at 30 and 90 DAE for populations of 55 and 60 thousand plants ha-1, respectively, allowed to generate models for the prediction of productivity based on corn NDVI, while the population of 65 thousand plants ha-1 at 45 and 60 DAE there was no adjustment by the prediction model of yield by values close to NDVI for different productivities. In the conventional spacing generating models for the prediction of yield was possible in the populations of 55 and 60 thousand plants ha-1 respectively at 30 and 90 DAE.
- Open Access
- 1 October 2018
- Published by FapUNIFESP (SciELO) in Revista Brasileira de Engenharia Agrícola E Ambiental
- Vol. 22 (10) , 732-738
Can combine headers and travel speeds affect the quality of soybean harvesting operations?
Assuring the quality of mechanical soybean harvesting is crucial to ensure that investment in other stages of crop production is converted into profit for the farmer. Because the quality of this operation is related to decreased losses, which may be affected by the combine header used and by the harvesting speed, the aim of the present study was to assess the quality of mechanical soybean harvesting in the Southern Cone of Rondônia, using harvesters with different combine headers and travel speeds via statistical process control. The experiment was performed during the 2015/16 harvest in an agricultural area of the municipality of Cabixi, RO, located at the geographical coordinates 13° 27’ S and 60° 41’ W. The study was designed based on the premises of the statistical process control, sampling 80 points 100 m apart. Combine header, internal, total, and cutting height losses were assessed. Quality of the harvesting process was assessed using the draper header. Travel speed had little effect on process quality. Crop losses were higher than the acceptable limit, indicating the need to improve the process.
- 1 October 2018
- Published by FapUNIFESP (SciELO) in Revista Brasileira de Engenharia Agrícola E Ambiental
- Vol. 22 (10) , 732-738
Open AccessCan combine headers and travel speeds affect the quality of soybean harvesting operations?
Assuring the quality of mechanical soybean harvesting is crucial to ensure that investment in other stages of crop production is converted into profit for the farmer. Because the quality of this operation is related to decreased losses, which may be affected by the combine header used and by the harvesting speed, the aim of the present study was to assess the quality of mechanical soybean harvesting in the Southern Cone of Rondônia, using harvesters with different combine headers and travel speeds via statistical process control. The experiment was performed during the 2015/16 harvest in an agricultural area of the municipality of Cabixi, RO, located at the geographical coordinates 13° 27’ S and 60° 41’ W. The study was designed based on the premises of the statistical process control, sampling 80 points 100 m apart. Combine header, internal, total, and cutting height losses were assessed. Quality of the harvesting process was assessed using the draper header. Travel speed had little effect on process quality. Crop losses were higher than the acceptable limit, indicating the need to improve the process.