TCC - Bacharelado em Sistemas da Informação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/427
Navegar
2 resultados
Resultados da Pesquisa
Item Serviço computacional para interpolação espacial de dados meteorológicos(2019) Antonio, Wellington Luiz; Gonçalves, Glauco Estácio; Medeiros, Victor Wanderley Costa de; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/6157118581200722; http://lattes.cnpq.br/6454060359445906The spatial interpolation is an essential technique for several fields, such as meteorology, hydrology, agricultural zoning, characterization of health risk areas, sociodemo-graphic, among others. Through interpolation, it is possible to model a surface of a spatially distributed variable from a finite set of known data points. In the case of weather data for agriculture, for instance, interpolation allows us to observe how weather variables behave on a given rural property, which could serve as input for irrigation management on this property. Due to the increasing demand for the use of spatial interpolation,this work proposed the development of a scalable service based on technologies and standards of state-of-the-art in distributed systems, for spatial interpolation of meteorological data associated with agriculture. In order to achieve this goal, we developed a web service based on three different reference evapotranspiration interpolation algorithms, namely: Inverse distance weighted (IDW), Ordinary Kriging (OK) and RandomForest (RF). The first two are widely used algorithms in the spatialization of reference evapotranspiration and they are known to produce low interpolation errors. The third algorithm is originated from Machine Learning. It has been used in recent studies as an alternative for spatial interpolation of environmental variables. This last algorithmhas also been obtaining promising results in the estimation of evapotranspiration. The spatial interpolation web service proposed was developed and its performace was evaluated through measurement. This service was deployed on a production enviromentusing Docker container and a mobile application was developed to integrate and show the main functionalities of the web service. The developed service can be applied inseveral areas. However, in this work more attention was paid to the agricultural sector,as this one is the sector to which this study is focused on. The main beneficiaries of the web service are researchers and developers, which, in turn, are able to develop studies that will benefit the farmer from the application of the service. During this work,we also sought to evaluate how the developed service could be useful for the promotion of the performance and the scalability with respect to spatial interpolation calculus and generation of spatial models. We also highlighted the importance of this software as a support tool for other researches or even for other software, such as Aquaprev, which uses, among other parameters, evapotranspiration and spatial interpolation to estimate the irrigation time of a given crop.Item Avaliação de métodos para interpolação espacial de dados de precipitação(2019) Neris, Airton Martins; Gonçalves, Glauco Estácio; Medeiros, Victor Wanderley Costa de; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/6157118581200722; http://lattes.cnpq.br/7254010025661115AbstractInformation on the amount of rainfall is essential for the most varied sectors, such asagriculture and agroforestry. Despite this importance many areas are still not coveredby meteorological stations, which causes the lack of data. To meet this need there aremethods of spatial interpolation, which use the information of correlated points to esti-mate the value that does not exist in a certain area. Thus, this work aims to evaluatemethods for the interpolation of daily precipitation data. The interpolation techniquesused in the experiments were the methods: Inverse Distance Weighting; Ordinary Krig-ing; Random Forest. For the Random Forest two different configurations were used, onethat receives as input the coordinates, and another that receives thebufferdistance,which is one of the most recent pre-processing used in the literature for the RandomForest to estimate its values based on geographical reference. We used rainfall datafrom the 46 meteorological stations from the state of Pernambuco in the period from2013 to 2018, and to compare the precision of the generalization of the methods, weused theleave-one-outcross validation. In the results, the Inverse Distance Weightingpresented a better performance in its estimates, for all the metrics, and the RandomForest using coordinates obtained the second best result. Random Forest usingbufferdistance had a lower result in terms of its metrics, but the quality of visual spatializationproved to be superior by offering a visually smoother result than offered by RandomForest using coordinates.