Erli Pinto dos Santos

Erli Pinto dos Santos
Universidade Federal de Viçosa (UFV) | UFV · Department of Agricultural Engineering

Agronomy Engineer - Master of Science and PhD candidate in Agricultural Engineering

About

18
Publications
5,996
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
10
Citations
Introduction
I'm an Agronomist Engineer and Ph.D. candidate in Agricultural Engineering at Universidade Federal de Viçosa, Brazil. The focus of my research is on the fields of Optical and Microwave Remote Sensing applied to better understand Hydrological processes, Geochemistry, Soil Science, and Precision Agriculture. Also, my interests are in Artificial Intelligence (main Machine Learning) and in Environmental Systems Modelling.
Education
August 2020 - February 2024
Universidade Federal de Viçosa (UFV)
Field of study
  • Agricultural Engineering
August 2018 - July 2020
Universidade Federal de Viçosa (UFV)
Field of study
  • Agricultural Engineering
March 2013 - July 2018
Universidade Estadual de Feira de Santana
Field of study
  • Agronomist Engineering

Publications

Publications (18)
Article
An approach to monitor vegetation without the influence of cloud cover and employing Synthetic Aperture Radar (SAR) data was developed by the DPSVI (Dual Polarization SAR Vegetation Index), based on Sentinel-1 mission data. However, DPSVI performance in areas of dense vegetation and variation in vegetation classes is unknown. Thus, this paper aimed...
Article
Water quality monitoring is fundamental for the maintenance and conservation of water resources. However, the conventional monitoring method, which uses point sampling, does not adequately represent the spatial variability of its parameters, besides being costly. As a result, remote sensing techniques with the use of orbital sensors have been appli...
Article
Full-text available
Missing data in historical rainfall series are common in Brazilian conditions, making unfeasible several hydrological studies that rely on these data. In this context, orbital sensor products represent a potential tool for estimating rainfall. As a result, this study aims to assess the applicability of data from the Tropical Rainfall Measurement Mi...
Article
A way to reconstruct optical sensor-derived images allowing cloud-free vegetation monitoring is proposed in this paper. The motivation is the influence that clouds have on optical remote sensing of tropical regions, which hinders Earth observation systems because their presence reduces imaging frequency. To circumvent that problem, a machine learni...
Article
Full-text available
Both water balance (WB) and rating curve (RC) are methods for estimating streamflow. The first is mostly used to estimate reservoir outflows, while the second is usually adopted in hydrometeorological network streamflow gauges. While WB uses hourly collected data, the RC estimates streamflow using current water level and extrapolation techniques. T...
Preprint
The water balance method is used, in Brazil, to estimate the outflow from the regularization reservoirs, based on hourly data. The the rating curve method, normally adopted in conventional streamflow gauge stations of the hydrometeorological network national, the values are estimated from the average of two daily readings of the water level elevati...
Data
Supplementary material of the article "A Machine Learning approach to reconstruct cloudy affected vegetation indices imagery via data fusion from Sentinel-1 and Landsat 8" (https://doi.org/10.1016/j.compag.2022.106753).
Code
Code wrote and devoted to sampling raster stacks, exemplifying with Sentinel-1 IW GRD scenes. The code uses the ReadDIM package function to read files originated in ESA (European Space Agency) SNAP (Sentinel Application Platform) Software. The sampling is performed using raster::extract (package::function) in the pixel of the image within the point...
Article
Full-text available
Monitoring water quality in water bodies is fundamental for their conservation. In this sense, large-scale monitoring methodologies are increasingly essential to monitor anthropic and natural actions that change the quality of these environments. Based on this premise, this paper proposes to use multispectral data from the MSI sensor (MultiSpectral...
Poster
Full-text available
RESUMO: A matéria orgânica presente no solo influencia nas suas propriedades físicas e químicas e concomitantemente apresenta forte relação com a resposta espectral do solo. Neste sentido, o objetivo do trabalho foi demostrar o potencial do sensoriamento remoto no estudo de solos, utilizando o método da espectrorradiometria, na caracterização do co...
Article
Full-text available
The objective of this work was to calibrate and to validate the methods of Camargo, Hargreaves and Samani, and Priestley and Taylor, according to the Penman-Monteith model, for the estimation of reference evapotranspiration (ETo), in the four seasons of the year for the municipality of Morro do Chapéu, Bahia. Climatological data from the convention...
Article
Full-text available
p>O comportamento espectral do solo é condicionado por todos os elementos que o constituem. A matéria orgânica atua de forma peculiar no solo, influenciando diretamente em suas propriedades físicas, químicas, biológicas, mineralógicas; portanto, apresenta forte relação com a sua resposta espectral. Neste sentido, o objetivo do trabalho foi demonstr...
Article
Full-text available
A redução da qualidade das águas dos rios, reservatórios, estuários e regiões costeiras, é uma preocupação mundial visto que resulta na restrição de seus múltiplos usos (CICERELLI; GALO, 2015) e nessa ótica a pesquisa tem analisado diversas substâncias e seres vivos presentes na água na busca de identificar padrões de qualidade para monitorar a pre...
Article
Full-text available
The goal of this study is distinguish on remote sensing data, different conservation stage from pasture areas, using laboratorial analysis, orbital images and field spectroscopy, comparing field and laboratory methods. Was studied two pasture areas with grass Brachiaria decumbens, the area 1 without degradation and the area 2 degraded. The orbital...
Chapter
Full-text available
Com o crescimento da população e consequente expansão urbana, o sistema lacustre da cidade de Feira de Santana foi comprometido, muitas lagoas perderam a potabilidade, enquanto outras foram aterradas e ocupadas indiscriminadamente pela população de baixa renda. Esse trabalho busca acompanhar a evolução da degradação da Lagoa da Pindoba, de caráter...
Article
Full-text available
O sensoriamento remoto da Terra tem fornecido a base para mapeamento de atividades humanas e naturais, mostrando-se eficaz no monitoramento de sistemas hídricos, pois, os dados recobrem extensas áreas e em diferentes faixas do espectro eletromagnético, fornecendo informações sobre composição de corpos hídricos. Desse modo o objetivo desse trabalho...
Article
Full-text available
The objective of this study was to estimate a reference evapotranspiration for the city of Feira de Santana (BA), since there is no research on the best method and it is a great need for estimation, mainly because it is a region with great agricultural potential in Bahia. Data from the meteorological station (conventional), located at the State Uni...

Questions

Questions (3)
Question
Dear all,
Some papers have discussed different strategies for testing the generability of trained models. Some have used stratified sampling when splitting datasets (into training and testing datasets), or even random sampling when splitting. Besides that, when seeking for assessing the extrapolation power of models, some have used quantile splitting (for example, selecting a part of the largest values to test models).
Do you know more strategies for testing? Which ones?
Question
Looking around is noticeable the interpretation of a lot of knowledge fields either as a set of methods or a scientific discipline. Considering the vast areas of remote sensing, which may be clustered by operating spectral region (from X-ray to microwave remote sensing), can we consider it as a scientific discipline or only the study of methods for data collecting "without" physical contact?
Question
Dear all,
I’m working with SAR data from Sentinel-1 in my research project. Due to the necessity to use a lot of Sentinel-1 scenes over a region in Brazil, we did decided to use the Google Earth Engine platform. But in the preprocessing of all images, we need apply a filter to remove speckle noise following the same critters of S1TBX in SNAP. Anyone of you know any code in Google Earth Engine that has applied any filter (like Lee, Sigma Lee, Frost, etc.)?
Thank you guys for attention!

Network

Cited By

Projects

Projects (2)
Project
The goal of the project was to develop an analysis system to monitor vegetation cover over hydrographic basins in a tropical region and with mountainous relief by using data from the Sentinel-1 radar mission.
Project
Os impactos dos diferentes elementos do clima na produção agrícola. Métodos de análise climatica Agricultura do Semi-árido