A5014490169- Remote Sensing in Agriculture
- Spectroscopy and Chemometric Analyses
- Remote Sensing and LiDAR Applications
- Geography and Environmental Studies
- Water Quality and Pollution Assessment
- Insect and Pesticide Research
- Smart Agriculture and AI
- Land Use and Ecosystem Services
- Environmental and biological studies
- Groundwater and Watershed Analysis
- Leaf Properties and Growth Measurement
- Aquatic Ecosystems and Phytoplankton Dynamics
- Soil erosion and sediment transport
- Fire effects on ecosystems
- Urban Heat Island Mitigation
- Fire Detection and Safety Systems
Universidade do Oeste Paulista
2020-2022
Hospital Regional de Presidente Prudente
2018
Águas de Portugal (Portugal)
2018
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, the irregular shape, size, occlusion, complexity areas. With advance technologies, deep learning segmentation mapping methods can map accurately. We applied a region-based CNN object instance algorithm for semantic canopies environments based on...
Pantanal is the largest continuous wetland in world, but its biodiversity currently endangered by catastrophic wildfires that occurred last three years. The information available for area only refers to location and extent of burned areas based on medium low-spatial resolution imagery, ranging from 30 m up 1 km. However, improve measurements assist environmental actions, robust methods are required provide a detailed mapping higher-spatial scale areas, such as PlanetScope imagery with 3–5...
Accurately detecting the insect damage caused in plants might reduce losses crop yields. Hyperspectral data is a well-accepted source to attend this issue. However, due their high dimensional, both robust and intelligent methods are required extract information from these datasets. Therefore, we explore processing of hyperspectral with artificial intelligence joined clustering techniques detect herbivory maize plants. We measured leaf spectral response three different groups plants: control...
The urban climate changes, caused by intense densities, result in loss life quality. Therefore, it becomes increasingly necessary to know the dynamics climatic of a given region search strategies promote socio-environmental present work aimed analyze temporal space variations and implications water availability NDVI heat islands. For this purpose, we adopt as case study municipality Palmas - Tocantins. In first moment, climatological characterization area through balance proposed...
In cotton cultivars, an insect that causes irreversible damage is the Spodoptera frugiperda, known as fall armyworm. Since visual detection of plants a burdensome task for human inspection, spectral information related to plant damage, registered on scale, can be useful. These measurements, associated with machine learning techniques, produce useful rapid and non-invasive inspection method development. To contribute this gap fulfillment, paper proposes framework model response under attack...
This work aimed was describe a workflow from the process defining sampling points up to water samples collection and conservation for evaluation monitoring in sub-basins. The methodological procedures they were based on literature review illustrate application, case study carried Limoeiro stream, located municipalities of Presidente Prudente Álvares Machado, São Paulo state. As result, we obtained location Recebido em: 17/08/2018Revisado 27/08/2018Aprovado 29/08/2018 79maps area, land use...
Despite the fact that deep neural networks performed well in arboreous urban vegetation semantic segmentation, they fell short of expectations. As a result, we evaluate performance SegFormer, vision transformer-based learning. We compare evaluation metrics SegFormer with learning architecture DeepLabv3+. Two sets image data, each having different GSD, were employed (0.2 m and 0.5 m). In segmentation tree environments outperforms state-of-the-art convolutional network, proving its capacity to...
A strategy to reduce qualitative and quantitative losses in crop-yields refers early accurate detection of insect-damage caused plants. Remote sensing systems like hyperspectral proximal sensors are a promising for managing crops. In this aspect, machine learning predictions associated with clustering techniques may be an interesting approach mainly because its robustness evaluate high dimensional data. paper, we model the spectral response insect-herbivory-damage maize plants propose based...