Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ LAReferencia - Red F...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

Fusão de dados e aprendizagem de máquina aplicados a pedometria

Authors: Almeida, Gabriela Mourão de;

Fusão de dados e aprendizagem de máquina aplicados a pedometria

Abstract

Como nos mais diversos setores, a agricultura vem passando por uma revolução nos últimos anos e para os países que são grandes produtores de alimento como o Brasil a adoção de tecnologias inovadoras vem se tornando cada dia mais essencial para alcançar os resultados de produção esperados. Como resultado desta revolução ocorreu um grande aumento na disponibilidade de dados, ampliação da capacidade de processamento computacional e assim os antigos modelos de regressão simples passaram a dar espaço a técnicas mais robustas de análise de dados e assim a aprendizagem de máquina (AM) começou a sair da área de sistema da informação e adentrar nos sistemas agrícolas. A AM é atualmente uma das linhas de pesquisa mais vigoras na agricultura, pois diferente dos modelos clássicos esta tem a capacidade de trabalhar com toda a complexidade que envolve o sistema agrícola, Dentre as variáveis ambientais, o solo é a que mais implica em complexidade, diante disso foi criado uma linha de pesquisa dedicada ao estudo da sua variabilidade que é a pedometria que consiste na aplicação de métodos matemáticos e estatísticos no estudo da distribuição, caracterização e gênese dos solos. Pesquisadores atrelados a essa linha de pesquisa vem afirmando a nova linha de estudo crescente é a utilização de sensores e a aplicação de técnicas de AM, principalmente em países de clima tropical e grande extensão territorial como o Brasil, que tem como característica solos altamente intemperizados e devido a isso demandam uma maior quantidade de amostras para caracterização. Este tipo de solo frequentemente apresenta o ferro na composição de seus minerais e este é um importante indicador analítico do solo, pois ele nos permite a compreender a gênese, classificação e variabilidade do solo.

As in the most diverse sectors, agriculture has been undergoing a revolution in recent years and for countries that are large food producers like Brazil, the adoption of innovative technologies is becoming more and more essential to achieve the expected production results. As a result of this revolution, there was a large increase in data availability, expansion of computational processing capacity and so the old simple regression models began to give way to more robust data analysis techniques and thus machine learning (ML) began to leaving the information system area and entering agricultural systems. AM is currently one of the most vigorous lines of research in agriculture, as unlike classic models it has the ability to work with all the complexity that involves the agricultural system. Among the environmental variables, the soil is the one that most implies complexity, in view of this, a line of research was created dedicated to the study of its variability, which is pedometrics, which consists of the application of mathematical and statistical methods in the study of the distribution, characterization and genesis of soils. Researchers linked to this line of research have been affirming that the new growing line of study is the use of sensors and the application of AM techniques, mainly in countries with a tropical climate and large territorial extension such as Brazil, which is characterized by highly weathered soils and due to this, they demand a larger number of samples for characterization. This type of soil often presents iron in the composition of its minerals and this is an important analytical indicator of the soil, as it allows us to understand the genesis, classification and variability of the soil.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Pós-graduação em Agronomia (Produção Vegetal) - FCAV

001

Keywords

Mineralogia do solo, Banco de dados amplos, Agricultura, Ciência de Dados, Inteligência artificial, Agricultura digital

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green