Knowing the dynamics of spatial–temporal precipitation distribution is of vital significance for the management of water resources, in highlight, in the northeast region of Brazil (NEB). Several models of large-scale precipitation variability are based on the normal distribution, not taking into consideration the excess of null observations that are prevalent in the daily or even monthly precipitation information of the region under study. This research proposes a novel way of modeling the trend component by using an inflated gamma distribution of zeros. The residuals of this regression are generally space–time dependent and have been modeled by a space–time covariance function. The findings show that the new techniques have provided reliable and precise precipitation estimates, exceeding the techniques used previously. The modeling provided estimates of precipitation in nonsampled locations and unobserved periods, thus serving as a tool to assist the government in improving water management, anticipating society’s needs and preventing water crises.

The purpose of this study was to provide a detailed framework to use the spatiotemporal kriging to model the space-time variability of precipitation data in Paraíba, which is located in the northeastern region of Brazil (NEB). The NEB is characterized by an irregular, highly variable distribution of rainfall in space and time. In this region, it is common to find high rates of rainfall at locations adjacent to those with no record of rain. Paraíba experiences localized periods of drought within rainy seasons and distinct precipitation patterns among the state’s mesoregions. The mean precipitation values observed at several irregularly spaced rain gauge stations from 1994 to 2014 showed remarkable variations among the mesoregions in Paraíba throughout the year. As a consequence of this behavior, there is a need to model the rainfall distribution jointly with space and time. A spatiotemporal geostatistical methodology was applied to monthly total rainfall data from the state of Paraíba. The rainfall data indicate intense spatial and temporal variabilities that directly affect the water resources of the entire region. The results provide a detailed spatial analysis of sectors experiencing precipitation conditions ranging from a scarcity to an excess of rainfall. The present study should help drive future research into spatiotemporal rainfall patterns across all of NEB.

Abstract Precipitation is an important object of study and plays an important role in the dynamics of rainfall distribution in a region. This study investigated the spatial and temporal variation of precipitation in the São Francisco River Basin (SFRB). A historical series of data from 1989 to 2018 was analyzed, and a random function was decomposed into trend and residual components for analysis of precipitation. Interpolation techniques were used to analyze precipitation spatial behavior over time, using high-resolution precipitation maps. Our results showed that the exponential model prevailed in four periods. The findings also showed a high precipitation variability in the SFRB and enabled us to monitor precipitation behavior over the years, as well as in the different sub-regions in SFRB. Finally, important information was obtained, enabling, for instance, the identification of vulnerable areas suffering from lack of rainfall.

The objective of this paper was to investigate the patterns (trend and seasonality) of the levels of rainfall in the municipality of Aracaju, presenting a methodology to make adequate forecasts for short periods of time. It is known that the different Northeast Brazilian regions (NEB) have high temporal variability in rainfall. Specifically, NEB has been suffering from extreme weather, droughts and floods within the same year, and it is no different in the state of Sergipe, especially in its capital, Aracaju. For that, such predictions are used to anticipate the phenomena and organize mitigating actions. In this study, we opted to use the integrated autoregressive model of seasonal moving averages (SARIMA) which contains two parts: one non-seasonal and another seasonal. Accumulated monthly precipitation data in Aracaju, from 1986 to 2018, showed a decreasing trend and a twelve-month seasonality. Adjusting the class of SARIMA models to this historical series proved to be an adequate alternative for forecasting monthly rainfall in this city. Therefore, through the study of this manuscript, the selected model presented adequate estimates of precipitation, thus suggesting that models of the SARIMA class can be used as a tool for forecasting monthly levels of rainfall in the region under study. These estimates can be used to better manage water resources, anticipating society's future needs, such as long periods of drought, droughts and floods.

ABSTRACT Crop pests have negative impacts on yield. This paper proposes a spatiotemporal geostatistical modeling to compare data of adult Syrphidae fly count and corn leaf aphid Rhopalosiphum maidis (Fitch, 1856) colonies in corn crops. The use of a geostatistical model that allows the space-time variation makes the approach more interesting because it is a more complete model. Multiple regression was used to model the trend component for the variable response adult Syrphidae fly count and corn leaf aphid colonies, with the coordinates serving as covariates and the spatiotemporal variations around the deviation are described by a random spacetime residual field. Finally, the prediction map obtained by kriging may be a biological indicator of possible corn leaf aphid colonies in the corn crop. It was possible to verify that the occurrence of the pest provided a significant increase in adult predators and seminatural habitats may favor populations of natural enemies.

The analysis of data sets from multienvironmental trials is of fundamental importance in the final stages of plant breeding programs. In this context, the Additive Main Effects and Multiplicative Interaction (AMMI) model has become a popular method for evaluating genotype responses in different environments. In the present work, the AMMI model was applied, under the bayesian approach, to a set of data from a randomized block experiment with 12 mustard genotypes (varieties) in 6 different environments. The objective was to analyze genotypic stability and adaptability through the AMMI-2 biplot representation, highlighting differences in this approach in relation to the classical AMMI analysis. The results showed the great flexibility of the bayesian method to incorporate a random effect for genotypes, as well as inference to the biplot through regions of credibility for genotypic and environmental scores that describe the effect of the interaction between genotypes by environments (GEI). The regions of credibility built for main effects and bilinear parameters allowed to identify more productive genotypes and to visualize homogeneous subgroups of genotypes and environments in relation to the effect of GEI. The more productive genotypes were G8 and G10 and only G2 was considered statistically stable.

Reliability analysis is the conversion of survival analysis techniques applied in the production department. To perform the reliability analysis, the data set under study must meet the necessary conditions so that it is possible to make reasonable estimates of the risk and reliability functions. The objective of this work is to use the reliability analysis, using non-parametric, semi-parametric and parametric techniques, to explore and model the time of the 11.00R22 tire. A study was carried out with the 11.00R22, and the time in kilometers traveled was calculated using an on-board computer attached to trucks. The data sets have a total of 552 tires, which differed between the three types of lifespan. In carrying out this work, the Kaplan-Meier product limit estimator was applied for the three life groups, and the log-rank test to verify the existence of a significant difference between the survival curves, both non-parametric methods, and in sequence, the parametric approach with the use of the regression model to verify which distribution suited the tire life and also the Cox model to model the risk semi-parametric approach. In the application of the methods, software R was used through the survival package. The Weibull model was best suited to model the life span of 11.00R22 tires.

Resumo O Nordeste Brasileiro (NEB) apresenta, como característica marcante, a irregularidade em acumulados de precipitações, o que é decorrência de vários fatores, tais como as características ambientais e de sistemas atmosféricos. Análises estatísticas adequadas são necessárias para ter conhecimento dos níveis de retorno da precipitação em uma região e são muito importantes para auxiliar ações para prevenção de desastres naturais causados por chuvas máximas. O objetivo dessa pesquisa consistiu em apresentar os níveis de retorno da precipitação máxima diária (PMD) em todo o estado da Paraíba, o qual está localizado na NEB. O conjunto de dados foi composto por 238 estações pluviométricas, abrangendo o período de 1994 a 2020. Para a modelagem estatística foi ajustada a distribuição Gumbel, por meio do método da máxima verossimilhança. Os resultados indicaram que o Sertão Paraibano apresentou as maiores estimadas da PMD nos meses de janeiro a março, com volumes superiores a 75 mm. A Mata Paraibana apresentou as maiores estimativas da PMD nos meses de abril a junho, com valores superiores a 125 mm no mês de junho em regiões litorâneas. As informações obtidas sobre os níveis de retorno da PMD são relevantes e podem ser de grande auxílio na implementação de políticas públicas, visando a diminuição dos impactos causados pelas chuvas intensas.