Felipe David Georges Gomes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Felipe David Georges Gomes has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Ana Paula Marques Ramos
Faculty of Science and Technology, São Paulo State University (UNESP), R. Roberto Simonsen, 305, Presidente Prudente 19060-900, SP, Brazil
6 shared publications - Lucas Prado Osco
Universidade do Oeste Paulista
6 shared publications - José Marcato Junior
Federal University of Mato Grosso do Sul
5 shared publications - Wesley Nunes Gonçalves
Federal University of Mato Grosso do Sul
5 shared publications - Danielle Elis Garcia Furuya
Brazilian Agricultural Research Corporation, Embrapa Agricultura Digital, Campinas 13083-886, São Paulo, Brazil
4 shared publications - Lúcio André de Castro Jorge
Embrapa Instrumentação, Brazilian Agricultural Research Corporation, São Carlos 13560-970, SP, Brazil
3 shared publications
Latest Publications
- Open Access
- 12 August 2025
- Published by Universidade do Estado do Rio de Janeiro in Revista Tamoios
- Vol. 21 (2) , 165-185
MAPEAMENTO DE FRAGMENTOS ARBÓREOS URBANOS COM IMAGENS ORBITAIS E APRENDIZADO PROFUNDO
A vegetação é uma das principais componentes do meio ambiente, isso porque ela exerce grande influência positiva sobre a qualidade ambiental, o que torna um objeto de estudo muito relevante. Atualmente, o sensoriamento remoto é uma das melhores opções para estudar o comportamento espacial da vegetação, capaz de gerar um grande volume de dados. Entretanto, cria uma demanda adicional, esse grande volume de dados necessita de técnicas de processamento eficientes, para assim transforma-los em informações úteis. O objetivo desse trabalho foi realizar a segmentação de fragmentos arbóreos em contexto urbano utilizando duas redes de aprendizado profundo e um algoritmo de machine learning. Foram utilizados nesse trabalho as redes U-Net, DeepLabV3+ e o algoritmo Random Forest. Para o treinamento dessas redes, foi utilizado um conjunto de dados composto por imagens Planet Scope de áreas urbanas, de quatro datadas diferentes. Como resultado, foi observado que o modelo DeepLabV3+ teve desempenho superior aos demais quando treinada com um conjunto de dados multitemporal, obtendo assim Acurácia (0,936) Precisão (0,847), Recall (0,804) e F1-Score (0,799). Os resultados apontam que o treinamento das redes com conjunto de dados multitemporal promoveu o aumento das métricas além de resultados homogêneos entre as diferentes imagens segmentadas.
- 12 August 2025
- Published by Universidade do Estado do Rio de Janeiro in Revista Tamoios
- Vol. 21 (2) , 165-185
Open AccessMAPEAMENTO DE FRAGMENTOS ARBÓREOS URBANOS COM IMAGENS ORBITAIS E APRENDIZADO PROFUNDO
A vegetação é uma das principais componentes do meio ambiente, isso porque ela exerce grande influência positiva sobre a qualidade ambiental, o que torna um objeto de estudo muito relevante. Atualmente, o sensoriamento remoto é uma das melhores opções para estudar o comportamento espacial da vegetação, capaz de gerar um grande volume de dados. Entretanto, cria uma demanda adicional, esse grande volume de dados necessita de técnicas de processamento eficientes, para assim transforma-los em informações úteis. O objetivo desse trabalho foi realizar a segmentação de fragmentos arbóreos em contexto urbano utilizando duas redes de aprendizado profundo e um algoritmo de machine learning. Foram utilizados nesse trabalho as redes U-Net, DeepLabV3+ e o algoritmo Random Forest. Para o treinamento dessas redes, foi utilizado um conjunto de dados composto por imagens Planet Scope de áreas urbanas, de quatro datadas diferentes. Como resultado, foi observado que o modelo DeepLabV3+ teve desempenho superior aos demais quando treinada com um conjunto de dados multitemporal, obtendo assim Acurácia (0,936) Precisão (0,847), Recall (0,804) e F1-Score (0,799). Os resultados apontam que o treinamento das redes com conjunto de dados multitemporal promoveu o aumento das métricas além de resultados homogêneos entre as diferentes imagens segmentadas.
- 31 August 2021
- Published by Springer Nature in Precision Agriculture
- Vol. 23 (2) , 470-491
Detecting the attack of the fall armyworm (Spodoptera frugiperda) in cotton plants with machine learning and spectral measurements
- 31 August 2021
- Published by Springer Nature in Precision Agriculture
- Vol. 23 (2) , 470-491
Detecting the attack of the fall armyworm (Spodoptera frugiperda) in cotton plants with machine learning and spectral measurements
- Open Access
- 4 August 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (16) , 3054
Semantic Segmentation of Tree-Canopy in Urban Environment with Pixel-Wise Deep Learning
Urban forests are an important part of any city, given that they provide several environmental benefits, such as improving urban drainage, climate regulation, public health, biodiversity, and others. However, tree detection in cities is challenging, given the irregular shape, size, occlusion, and complexity of urban areas. With the advance of environmental technologies, deep learning segmentation mapping methods can map urban forests accurately. We applied a region-based CNN object instance segmentation algorithm for the semantic segmentation of tree canopies in urban environments based on aerial RGB imagery. To the best of our knowledge, no study investigated the performance of deep learning-based methods for segmentation tasks inside the Cerrado biome, specifically for urban tree segmentation. Five state-of-the-art architectures were evaluated, namely: Fully Convolutional Network; U-Net; SegNet; Dynamic Dilated Convolution Network and DeepLabV3+. The experimental analysis showed the effectiveness of these methods reporting results such as pixel accuracy of 96,35%, an average accuracy of 91.25%, F1-score of 91.40%, Kappa of 82.80% and IoU of 73.89%. We also determined the inference time needed per area, and the deep learning methods investigated after the training proved to be suitable to solve this task, providing fast and effective solutions with inference time varying from 0.042 to 0.153 minutes per hectare. We conclude that the semantic segmentation of trees inside urban environments is highly achievable with deep neural networks. This information could be of high importance to decision-making and may contribute to the management of urban systems. It should be also important to mention that the dataset used in this work is available on our website.
- 4 August 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (16) , 3054
Open AccessSemantic Segmentation of Tree-Canopy in Urban Environment with Pixel-Wise Deep Learning
Urban forests are an important part of any city, given that they provide several environmental benefits, such as improving urban drainage, climate regulation, public health, biodiversity, and others. However, tree detection in cities is challenging, given the irregular shape, size, occlusion, and complexity of urban areas. With the advance of environmental technologies, deep learning segmentation mapping methods can map urban forests accurately. We applied a region-based CNN object instance segmentation algorithm for the semantic segmentation of tree canopies in urban environments based on aerial RGB imagery. To the best of our knowledge, no study investigated the performance of deep learning-based methods for segmentation tasks inside the Cerrado biome, specifically for urban tree segmentation. Five state-of-the-art architectures were evaluated, namely: Fully Convolutional Network; U-Net; SegNet; Dynamic Dilated Convolution Network and DeepLabV3+. The experimental analysis showed the effectiveness of these methods reporting results such as pixel accuracy of 96,35%, an average accuracy of 91.25%, F1-score of 91.40%, Kappa of 82.80% and IoU of 73.89%. We also determined the inference time needed per area, and the deep learning methods investigated after the training proved to be suitable to solve this task, providing fast and effective solutions with inference time varying from 0.042 to 0.153 minutes per hectare. We conclude that the semantic segmentation of trees inside urban environments is highly achievable with deep neural networks. This information could be of high importance to decision-making and may contribute to the management of urban systems. It should be also important to mention that the dataset used in this work is available on our website.
- Open Access
- 23 February 2021
- Published by MDPI AG in Preprints.org
Detecting the Attack of the Fall Armyworm (Spodoptera Frugiperda) in Cotton Plants with Machine Learning and Spectral Measurements
In cotton cultivars, an insect that causes irreversible damage is the Spodoptera frugiperda, known as the fall armyworm. Since the visual detection of plants is a burdensome task for human inspection, the spectral information related to plant damage, registered on a spectral scale, can be useful. These measurements, associated with machine learning techniques, produce useful information for a rapid and non-invasive inspection method development. To contribute to this gap fulfillment, this paper proposes a machine learning framework to model the spectral response of cotton plants under the attack of the fall armyworm. Additionally, a theoretical model is presented, built from the results of the machine learning analysis, to infer this damage with up-to-date orbital sensors. The data was composed of the reflectance measurements collected at a cotton field with control plants and plants submitted to Spodoptera frugiperda damage. Their spectral response was recorded with a hand-held spectroradiometer ranging from 350 to 2,500 nm, for eight consecutive days. Different machine learning models were evaluated and the overall best model was defined by accuracies comparisons on a testing-set. A ranking approach was adopted based on the model accuracy, returning the most contributive wavelengths for the classification. Sequentially, an unsupervised neural network (Self-Organizing Map - SOM) was implemented to reduce data-dimensionality and assist in the definition of important spectral regions. The regions were associated with the spectral bands of the two sensors (OLI and MSI) and a theoretical model using a band simulation process with the overall best machine learning model was proposed. The results indicated that the Random Forest (RF) algorithm is the most suitable to predict cotton-plants damaged by insects and that the last day of analysis (8th day) was better to separate it, with F-measure equals 0.912. The ranking approach combined with the SOM method indicated the spectral regions at the red to near-infrared (650 to 1,350 nm) and shortwave infrared (1,570 to 1,640 nm) as the most important regions to the analysis. The proposed theoretical model simulated with the OLI and MSI sensor-bands returned an F-Measure of 0.865 and 0.886, respectively. In conclusion, this framework can be used to map cotton-plants under insect-attack. The theoretical model presents high accuracy to infer the insect-damaged on cotton plants based on multispectral bands from other sensors, being a useful tool for future research that intends to evaluate it in other areas and at different field scales.
- 23 February 2021
- Published by MDPI AG in Preprints.org
Open AccessDetecting the Attack of the Fall Armyworm (Spodoptera Frugiperda) in Cotton Plants with Machine Learning and Spectral Measurements
In cotton cultivars, an insect that causes irreversible damage is the Spodoptera frugiperda, known as the fall armyworm. Since the visual detection of plants is a burdensome task for human inspection, the spectral information related to plant damage, registered on a spectral scale, can be useful. These measurements, associated with machine learning techniques, produce useful information for a rapid and non-invasive inspection method development. To contribute to this gap fulfillment, this paper proposes a machine learning framework to model the spectral response of cotton plants under the attack of the fall armyworm. Additionally, a theoretical model is presented, built from the results of the machine learning analysis, to infer this damage with up-to-date orbital sensors. The data was composed of the reflectance measurements collected at a cotton field with control plants and plants submitted to Spodoptera frugiperda damage. Their spectral response was recorded with a hand-held spectroradiometer ranging from 350 to 2,500 nm, for eight consecutive days. Different machine learning models were evaluated and the overall best model was defined by accuracies comparisons on a testing-set. A ranking approach was adopted based on the model accuracy, returning the most contributive wavelengths for the classification. Sequentially, an unsupervised neural network (Self-Organizing Map - SOM) was implemented to reduce data-dimensionality and assist in the definition of important spectral regions. The regions were associated with the spectral bands of the two sensors (OLI and MSI) and a theoretical model using a band simulation process with the overall best machine learning model was proposed. The results indicated that the Random Forest (RF) algorithm is the most suitable to predict cotton-plants damaged by insects and that the last day of analysis (8th day) was better to separate it, with F-measure equals 0.912. The ranking approach combined with the SOM method indicated the spectral regions at the red to near-infrared (650 to 1,350 nm) and shortwave infrared (1,570 to 1,640 nm) as the most important regions to the analysis. The proposed theoretical model simulated with the OLI and MSI sensor-bands returned an F-Measure of 0.865 and 0.886, respectively. In conclusion, this framework can be used to map cotton-plants under insect-attack. The theoretical model presents high accuracy to infer the insect-damaged on cotton plants based on multispectral bands from other sensors, being a useful tool for future research that intends to evaluate it in other areas and at different field scales.
- Open Access
- 22 February 2021
- Published by MDPI AG in Preprints.org
Machine Learning-Based Approach to Predict Insect-Herbivory-Damage and Insect-Type Attack in Maize Plants Using Hyperspectral Data
A strategy to reduce qualitative and quantitative losses in crop-yields refers to early and accurate detection of insect-damage caused in plants. Remote sensing systems like hyperspectral proximal sensors are a promising strategy for managing crops. In this aspect, machine learning predictions associated with clustering techniques may be an interesting approach mainly because of its robustness to evaluate high dimensional data. In this paper, we model the spectral response of insect-herbivory-damage in maize plants and propose an approach based on machine learning and a clustering method to predict whether the plant is herbivore-attacked or not using leaf reflectance measurements. We differentiate insect-type damage based on the spectral response and indicate the most contributive wavelengths to perform it. For this, we used a maize experiment in semi-field conditions. The maize plants were submitted to three different treatments: control (health plants); plants submitted to Spodoptera frugiperda herbivory-damage, and; plants submitted to Dichelops melacanthus herbivory-damage. The leaf spectral response of all plants (controlled and submitted to herbivory) was measured with a FieldSpec 3.0 Spectroradiometer from 350 to 2500 nm for eight consecutive days. We evaluated the performance of different learners like random forest (RF), support vector machine (SVM), extreme gradient boost (XGB), neural networks (MLP), and measured the impact of a day-by-day analysis into the prediction. We proposed a novel framework with a ranking strategy, based on the accuracy returned by predictions, and a clusterization method based on a self-organizing map (SOM) to identify important regions in the reflectance measurement. Our results indicated that the RF-based framework algorithm is the overall best learner to deal with this type of data. After the 5th day of analysis, the accuracy of the algorithm improved substantially. It separated the three treatments into different groups with an F-measure equal to 0.967, 0.917, and 0.881, respectively. We also verified that the most contributive spectral regions are situated in the near-infrared domain. We conclude that the proposed approach with machine learning methods is adequate to monitor herbivory-damage of S. frugiperda and stink bugs like Dichelops melacanthus in maize, differentiating the types of insect-attack early on. We also demonstrate that the framework proposed for the analysis of the most contributive wavelengths is suitable to highlight spectral regions of interest.
- 22 February 2021
- Published by MDPI AG in Preprints.org
Open AccessMachine Learning-Based Approach to Predict Insect-Herbivory-Damage and Insect-Type Attack in Maize Plants Using Hyperspectral Data
A strategy to reduce qualitative and quantitative losses in crop-yields refers to early and accurate detection of insect-damage caused in plants. Remote sensing systems like hyperspectral proximal sensors are a promising strategy for managing crops. In this aspect, machine learning predictions associated with clustering techniques may be an interesting approach mainly because of its robustness to evaluate high dimensional data. In this paper, we model the spectral response of insect-herbivory-damage in maize plants and propose an approach based on machine learning and a clustering method to predict whether the plant is herbivore-attacked or not using leaf reflectance measurements. We differentiate insect-type damage based on the spectral response and indicate the most contributive wavelengths to perform it. For this, we used a maize experiment in semi-field conditions. The maize plants were submitted to three different treatments: control (health plants); plants submitted to Spodoptera frugiperda herbivory-damage, and; plants submitted to Dichelops melacanthus herbivory-damage. The leaf spectral response of all plants (controlled and submitted to herbivory) was measured with a FieldSpec 3.0 Spectroradiometer from 350 to 2500 nm for eight consecutive days. We evaluated the performance of different learners like random forest (RF), support vector machine (SVM), extreme gradient boost (XGB), neural networks (MLP), and measured the impact of a day-by-day analysis into the prediction. We proposed a novel framework with a ranking strategy, based on the accuracy returned by predictions, and a clusterization method based on a self-organizing map (SOM) to identify important regions in the reflectance measurement. Our results indicated that the RF-based framework algorithm is the overall best learner to deal with this type of data. After the 5th day of analysis, the accuracy of the algorithm improved substantially. It separated the three treatments into different groups with an F-measure equal to 0.967, 0.917, and 0.881, respectively. We also verified that the most contributive spectral regions are situated in the near-infrared domain. We conclude that the proposed approach with machine learning methods is adequate to monitor herbivory-damage of S. frugiperda and stink bugs like Dichelops melacanthus in maize, differentiating the types of insect-attack early on. We also demonstrate that the framework proposed for the analysis of the most contributive wavelengths is suitable to highlight spectral regions of interest.
- 23 May 2020
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 27 (24) , 30034-30049
Climatic seasonality and water quality in watersheds: a study case in Limoeiro River watershed in the western region of São Paulo State, Brazil
Applying the climatological water balance (WB) concept to describe the relationship between climatic seasonality and surface water quality according to different forms of land use and land cover (LULC) is an important issue, but little explored in the literature. In this paper, we evaluate the influence of WB on surface water quality and its impacts when interacting with LULC. We monitored 11 sampling points during the four seasons of the year, from which we estimate WQI (water quality index) and TSI (trophic state index). We found an effect of the seasonality factor on both WQI values (F(3,30) = 12.472; p < 0.01) and in TSI values (F(3,30) = 6.967; p < 0.01). We noticed that LULC interferes in the way that the water balance influences the WQI and TSI values since in sampling points closest to higher urban density, with little or no riparian protection, the correlation between water balance and water quality was lower. In the stations that had the lowest water surplus and deficit, there was positive linearity between water balance and WQI. However, in the seasons when the surplus and water deficit recorded were extreme, there was no linearity. We conclude that water deficiency impairs the quality of surface water. In the extreme surplus water season, the homogeneity of WQI samples was lower, suggesting a higher interaction between rainwater and LULC. This study contributes to design management strategies of water resources, considering the climatic seasonality for optimization.
- 23 May 2020
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 27 (24) , 30034-30049
Climatic seasonality and water quality in watersheds: a study case in Limoeiro River watershed in the western region of São Paulo State, Brazil
Applying the climatological water balance (WB) concept to describe the relationship between climatic seasonality and surface water quality according to different forms of land use and land cover (LULC) is an important issue, but little explored in the literature. In this paper, we evaluate the influence of WB on surface water quality and its impacts when interacting with LULC. We monitored 11 sampling points during the four seasons of the year, from which we estimate WQI (water quality index) and TSI (trophic state index). We found an effect of the seasonality factor on both WQI values (F(3,30) = 12.472; p < 0.01) and in TSI values (F(3,30) = 6.967; p < 0.01). We noticed that LULC interferes in the way that the water balance influences the WQI and TSI values since in sampling points closest to higher urban density, with little or no riparian protection, the correlation between water balance and water quality was lower. In the stations that had the lowest water surplus and deficit, there was positive linearity between water balance and WQI. However, in the seasons when the surplus and water deficit recorded were extreme, there was no linearity. We conclude that water deficiency impairs the quality of surface water. In the extreme surplus water season, the homogeneity of WQI samples was lower, suggesting a higher interaction between rainwater and LULC. This study contributes to design management strategies of water resources, considering the climatic seasonality for optimization.