| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 6.86 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Nos últimos anos, a geoestatística tem sidomuito utilizada em vários estudos de diferentes
áreas de pesquisa, a atividade pesqueira é uma dessas áreas de interesse, principalmente
quando se pretende estudar fenómenos relacionados com a distribuição espacial da quantidade
do pescado das diferentes espécies e as infrações associadas a pesca. A modelação
geoestatistica tradicional baseada em técnicas de krigagem é frequentemente utilizada
como uma abordagem não paramétrica na modelação de dados georreferenciados Gaussianos.
Em relação a dados binários são utilizados modelos de regressão logística como
padrão. Têm-se usado modelos espaciais Bayesianos para analisar dados geoestatísticos
binários, incorporando a componente espacial de forma hierárquica como um campo aleatório
latente. Os tradicionais métodos de Monte Carlo via Cadeia de Markov (MCMC)
para estimação destes modelos, podem ser substituídos pela abordagem Integrated Nested
Laplace Approximation (INLA), computacionalmente menos exigente sem problemas de
convergência, permitindo fazer inferência Bayesiana aproximada em modelos gaussianos
latentes, como os modelos lineares generalizados mistos. Conjugada com esta metodologia,
a recente abordagem Stochastic Partial Differential Equation (SPDE), estima facilmente
o campo aleatório, resolvendo problemas de grande dimensão. Em relação ao delineamento
de amostragem para dados geoestatísticos binários são propostos dois critérios
de seleção de delineamentos de amostragem, o de maximização do risco estimado e maximização
da variabilidade associada ao risco estimado, que depois foram comparados
ao delineamento aleatório simples. O principal objetivo deste trabalho é apresentar a
modelação geoestatística baseada em técnicas de krigagem e a modelação de dados geoestatísticos
com resposta binária usando a combinação das abordagens INLA-SPDE, e
propor critérios de delineamento de amostragem baseados em geoestatística para dados
binários. Posteriormente, fez-se uma aplicação desta metodologia para estimar a quantidade
do pescado de lulas, inspecionado em ações de fiscalização da Marinha Portuguesa
no ano 2015 na região costeira do Algarve. Os modelos baseados em técnicas de krigagem
foram usados para calcular a variância da quantidade do pescado de lulas, inspecionado
em ações de fiscalização da Marinha Portuguesa no ano 2015 na região costeira do Algarve.
Adicionalmente, aplicou-se os modelos espaciais Bayesianos para analisar dados geoestatísticos binários a um conjunto de dados reais de fiscalização marítima da costa
Portuguesa, para produzir mapas de médias e erro padrão do efeito espacial subjacente
e dos mapas de riscos. As análises foram feitas com recurso ao pacote geoR do software
R e o pacote R-INLA, e fez-se a comparação dos delineamentos de amostragem em diferentes
tamanhos de amostra e escolheu-se o melhor delineamento para cada um destes
tamanhos.
In recent years, geostatistics has been widely used in several studies of different research areas, the fishing activity is one of these areas of interest, especially when one wants to study phenomena related to the spatial distribution of the amount of fish of different species and the infractions associated with fishing. Traditional geostatistical modelling based on kriging techniques is often used as a non-parametric approach in modelling Gaussian georeferenced data. For binary data, logistic regression models are used as standard. Bayesian spatial models have been used to analyse binary geostatistical data, incorporating the spatial component in a hierarchical way as a latent random field. Traditional Markov Chain Monte Carlo (MCMC) methods for estimating these models can be replaced by the Integrated Nested Laplace Approximation (INLA) approach, which is computationally less demanding without convergence problems, allowing approximate Bayesian inference in latent Gaussian models, such as generalized linear mixed models. Conjugated with this methodology, the recent Stochastic Partial Differential Equation (SPDE) approach, easily estimates the random field, solving high dimensional problems. Regarding the sampling design for binary geostatistical data, two criteria for selecting sampling designs are proposed, maximizing the estimated risk and maximizing the variability associated with the estimated risk, which were then compared to the simple random design. The main objective of this work is to present geostatistical modeling based on kriging techniques, modeling geostatistical data with binary response using the combination of INLA-SPDE approaches and propose geostatistics-based sampling design criteria for binary data. Subsequently, an application of this methodology was made to estimate the quantity of squid fish, inspected in enforcement actions of the Portuguese Navy in the year 2015 in the coastal region of Algarve. The models based on kriging techniques were used to calculate the variance of the quantity of squid fish, inspected in surveillance actions of the Portuguese Navy in the year 2015 in the coastal region of the Algarve. Additionally, Bayesian spatial models were applied to analyse binary geostatistical data to a real marine surveillance dataset of the Portuguese coast, to produce mean and standard error maps of the underlying spatial effect and risk maps. The analyses were done using the geoR package of the R software and the R-INLA package, and the sampling designs were compared at different sample sizes and the best design was chosen for each of these sizes.
In recent years, geostatistics has been widely used in several studies of different research areas, the fishing activity is one of these areas of interest, especially when one wants to study phenomena related to the spatial distribution of the amount of fish of different species and the infractions associated with fishing. Traditional geostatistical modelling based on kriging techniques is often used as a non-parametric approach in modelling Gaussian georeferenced data. For binary data, logistic regression models are used as standard. Bayesian spatial models have been used to analyse binary geostatistical data, incorporating the spatial component in a hierarchical way as a latent random field. Traditional Markov Chain Monte Carlo (MCMC) methods for estimating these models can be replaced by the Integrated Nested Laplace Approximation (INLA) approach, which is computationally less demanding without convergence problems, allowing approximate Bayesian inference in latent Gaussian models, such as generalized linear mixed models. Conjugated with this methodology, the recent Stochastic Partial Differential Equation (SPDE) approach, easily estimates the random field, solving high dimensional problems. Regarding the sampling design for binary geostatistical data, two criteria for selecting sampling designs are proposed, maximizing the estimated risk and maximizing the variability associated with the estimated risk, which were then compared to the simple random design. The main objective of this work is to present geostatistical modeling based on kriging techniques, modeling geostatistical data with binary response using the combination of INLA-SPDE approaches and propose geostatistics-based sampling design criteria for binary data. Subsequently, an application of this methodology was made to estimate the quantity of squid fish, inspected in enforcement actions of the Portuguese Navy in the year 2015 in the coastal region of Algarve. The models based on kriging techniques were used to calculate the variance of the quantity of squid fish, inspected in surveillance actions of the Portuguese Navy in the year 2015 in the coastal region of the Algarve. Additionally, Bayesian spatial models were applied to analyse binary geostatistical data to a real marine surveillance dataset of the Portuguese coast, to produce mean and standard error maps of the underlying spatial effect and risk maps. The analyses were done using the geoR package of the R software and the R-INLA package, and the sampling designs were compared at different sample sizes and the best design was chosen for each of these sizes.
Descrição
Palavras-chave
Modelação geoestatística semivariograma e krigagem Presumíveis infrações pesqueiras INLA-SPDE Dados espaciais binários Delineamento amostral
