Due to biodiversity loss being large as well as threatening ecosystem functions necessary for oursociety, the UN and EU have created regulations, strategies, and targets to improve biodiversity.Nationally in Sweden, and locally in Stockholm municipality, actions have also been taken. Oakhabitat is especially interesting for the municipality due to its high biodiversity values. This is whyin this study biodiversity connected to potential oak habitats was analysed by a GIS-basedconnectivity model; through which maps depicting possible movements by a model speciescomplex were created. An interview study was performed to investigate the use of GIS-basedplanning support tools for biodiversity, from the perspectives of professionals. Results suggestthat the methods for making choices regarding friction values need to be more transparent andbetter communicated, or standardised, both alternatives with the goal of facilitating interpretationof maps by physical planners. Also, depending on where in the planning process GIS-basedplanning support tools are used, they can be used in different ways. Early in the process, or evenbefore planning starts, they can act as decision support. After the implementation of a plan, theycan instead be beneficial for follow-up of biodiversity aspects. / Förlust av biologisk mångfald är problematisk och påverkar effektiviteten hos naturligaekosystem. De planetära gränserna för biologisk mångfald har sedan länge överskridits. Mål,lagar, och strategier från FN, EU och nationellt visar att frågor kopplade till biologisk mångfald ärbåde viktiga och aktuella. År 2020 antogs Stockholms stads första Handlingsplan för Biologisk Mångfald, vilken påverkarflertalet lokala åtgärder och mål. Ekar, som är en del av det svenska ädellövsbeståndet, ärprioriterade i Stockholms arbete med biologisk mångfald. I GIS-analyser har vissa skalbaggsarteranvänts som indikatorer för bedömning av naturvärden hos dessa bestånd. I denna studie genomfördes en litteraturstudie och fyra intervjuer för djupare insikt i relationenmellan GIS-baserade verktyg för planeringsstöd för biologisk mångfald, och fysisk planering, iStockholms stad. Ytterligare litteraturstudier genomfördes, inriktade på modellarter för biologiskmångfald i ekhabitat, samt tillvägagångssätt vid skapande av friktionsraster.Konnektivitetsanalyser av potentiella ekhabitat, i studieområdet Skarpnäck i södra Stockholm,genomfördes i ArcGIS och Linkage Mapper. Dessa fokuserade på analysens känslighet vidvariation av utvalda parametrar. Huvudsakliga resultat utgörs av kartor där korridorer och kostviktade avstånd beskrivermöjligheten till rörelse mellan habitat, samt hur dessa kan variera drastiskt av attparametervärden ändras. Den största skillnaden uppstod när större vägar betraktades sombarriärer. Det andra huvudsakliga resultatet består av en sammanställning av de intervjuer somutfördes. Där framgår att tidigt i planeringsprocessen, eller innan planprocessen påbörjas, kanGIS-baserade planeringsverktyg användas som beslutstöd. När planen genomförts kan de iställetvara användbara för uppföljning av konsekvenser för biologisk mångfald. Där dessa delar möts uppstår en diskussion om hur GIS-baserade verktyg kan utgöra ett stöd vidplanering för biologisk mångfald, hur det idag används på flertalet sätt och att användningen bådekan utökas och förbättras. Brister i transparens, och rättfärdigande av val av metod ochfriktionsvärden i konnektivitetsanalyser, ses i ljuset av möjligheten att som icke-professionellinom GIS kunna tolka kartor menade att användas som planeringsstöd.

<p dir="ltr">In recent years, massive amounts of data have been generated from various types of devices or services. For these data, update-intensive workloads where the data update their status periodically and continuously are common. The Log-Structured-Merge (LSM, for short) is a widely-used indexing technique in various systems, where index structures buffer insert operations into the memory layer and flush them into disk when the data size in memory exceeds a threshold. Despite its noble ability to handle write-intensive (i.e., insert-intensive) workloads, LSM suffers from degraded query performance due to its inefficiency on index maintenance of secondary keys to handle update-intensive workloads.</p><p dir="ltr">This dissertation focuses on the efficient support of update-intensive workloads for LSM-based indexes. First, the focus is on the optimization of LSM secondary-key indexes and their support for update-intensive workloads. A mechanism to enable the LSM R-tree to handle update-intensive workloads efficiently is introduced. The new LSM indexing structure is termed the LSM RUM-tree, an LSM R-tree with Update Memo. The key insights are to reduce the maintenance cost of the LSM R-tree by leveraging an additional in-memory memo structure to control the size of the memo to fit in memory. In the experiments, the LSM RUM-tree achieves up to 9.6x speedup on update operations and up to 2400x speedup on query operations.</p><p dir="ltr">Second, the focus is to offer several significant advancements in the context of the LSM RUM-tree. We provide an extended examination of LSM-aware Update Memo (UM) cleaning strategies, elucidating how effectively each strategy reduces UM size and contributes to performance enhancements. Moreover, in recognition of the imperative need to facilitate concurrent activities within the LSM RUM-Tree, particularly in multi-threaded/multi-core environments, we introduce a pivotal feature of concurrency control for the update memo. The novel atomic operation known as Compare and If Less than Swap (CILS) is introduced to enable seamless concurrent operations on the Update Memo. Experimental results attest to a notable 4.5x improvement in the speed of concurrent update operations when compared to existing and baseline implementations.</p><p dir="ltr">Finally, we present a novel technique designed to improve query processing performance and optimize storage management in any secondary LSM tree. Our proposed approach introduces a new framework and mechanisms aimed at addressing the specific challenges associated with secondary indexing in the structure of the LSM tree, especially in the context of secondary LSM B+-tree (LSM BUM-tree). Experimental results show that the LSM BUM-tree achieves up to 5.1x speedup on update-intensive workloads and 107x speedup on update and query mixed workloads over existing LSM B+-tree implementations.</p>

This thesis consists of three chapters, each dealing with a different aspect of the impact of climate change on agriculture: the analysis of past evidence, the possible new solutions and the anticipation of future problems. The topics chosen are different but complementary and reflect the complex and multifaceted impact of this phenomenon on agriculture. This work uses global spatial data and information from the literature, combines weather forecast with a crop model, and uses an economic model coupled with robust econometric estimation approaches. The findings indicate that major crop yields in tropical and subtropical regions will likely suffer adverse effects, while temperate and continental areas, historically less favourable for agriculture, may experience mainly positive impacts. Under a medium development scenario, global crop production is projected to remain largely unaffected, masking a compensatory mechanism between tropical and temperate regions. Adaptation covers a significant positive role, and short- and medium-range weather forecasting can be an important and affordable tool for farmers to adapt their agricultural practices, if they know how to use it. The adoption of such meteorological information can enable rural households in developing countries to increase yields of staple crops, although the potential contribution of it may be hampered by social and economic barriers. However, adaptation in agriculture can have negative externalities, potentially creating a vicious circle, and the livestock sector is particularly vulnerable. Indeed, changing climate conditions may induce farmers to adjust the distribution of grazing livestock per unit of land in order to maximise profits. Temperate and continental countries may increase the number of grazing livestock per unit of land as climatic conditions improve for agricultural purposes, thereby increasing carbon dioxide emissions. On the other hand, tropical areas, mainly populated by developing countries, will see a deterioration of agricultural conditions and less livestock can be raised on rangelands and pasturelands. Once again, countries with pressing agricultural productivity needs bear a disproportionate burden of climate change effects, exacerbating already precarious living conditions. Conversely, northern countries, primarily developed, are likely to experience more beneficial effects.

This thesis explores the use of spatiotemporal data mining in the air quality domain to understand causes of PM2.5 air pollution. PM2.5 refers to fine particulate matter less than 2.5 microns in diameter and is a major threat to human and environmental health. A review of air quality modeling methods is provided, emphasizing data-driven modeling techniques. While data mining methods have been applied to air quality data, including temporal sequence mining algorithms, spatiotemporal sequence mining methods have not been broadly applied to study air pollution. However, air pollution is highly spatial in nature, so such methods can offer new insights into air quality. This thesis applies one such method, the Spatiotemporal Sequence Miner (STS Miner) algorithm, to air quality data from a low-cost sensor network to explore causes and trends related to PM2.5. To facilitate the use of this method, an open-source library called OpenSTSMiner is developed to implement this algorithm. Various domain results are found; for instance, low temperature and low relative humidity are strongly associated with worsening levels of air quality. Lastly, to highlight the utility of the STS Miner algorithm, a comparison is presented between STS Miner and spatial Markov chains, another spatiotemporal modeling method used in the air quality domain.

Soil is one of the most precious resources on Earth because of its role in storing and recycling water and nutrients essential for life, providing a variety of ecosystem services. This vulnerable resource is at risk from degradation by erosion, salinity, contamination and other effects of mismanagement. Information from soil is therefore crucial for its sustainable management. While the demand for soil information is growing, the quantity of data collected in the field is reducing due to financial constraints. Digital Soil Mapping (DSM) supports the creation of geographically referenced soil databases generated by using field observations or legacy data coupled, through quantitative relationships, with environmental covariates. This enables the creation of soil maps at unexplored locations at reduced costs. The selection of an optimal scale for environmental covariates is still an unsolved issue affecting the accuracy of DSM. The overall aim of this research was to explore the effect of spatial scale alterations of environmental covariates in DSM. Three main targets were identified: assessing the impact of spatial scale alterations on classifying soil taxonomic units; investigating existing approaches from related scientific fields for the detection of scale patterns and finally enabling practitioners to find a suitable scale for environmental covariates by developing a new methodology for spatial scale analysis in DSM. Three study areas, covered by detailed reconnaissance soil survey, were identified in the Republic of Ireland. Their different pedological and geomorphological characteristics allowed to test scale behaviours across the spectrum of conditions present in the Irish landscape. The investigation started by examining the effects of scale alteration of the finest resolution environmental covariate, the Digital Elevation Model (DEM), on the classification of soil taxonomic units. Empirical approaches from related scientific fields were subsequently selected from the literature, applied to the study areas and compared with the experimental methodology. Wavelet analysis was also employed to decompose the DEMs into a series of independent components at varying scales and then used in DSM analysis of soil taxonomic units. Finally, a new multiscale methodology was developed and evaluated against the previously presented experimental results. The results obtained by the experimental methodology have proved the significant role of scale alterations in the classification accuracy of soil taxonomic units, challenging the common practice of using the finest available resolution of DEM in DSM analysis. The set of eight empirical approaches selected in the literature have been proved to have a detrimental effect on the selection of an optimal DEM scale for DSM applications. Wavelet analysis was shown effective in removing DEM sources of variation, increasing DSM model performance by spatially decomposing the DEM. Finally, my main contribution to knowledge has been developing a new multiscale methodology for DSM applications by combining a DEM segmentation technique performed by k-means clustering of local variograms parameters calculated in a moving window with an experimental methodology altering DEM scales. The newly developed multiscale methodology offers a way to significantly improve classification accuracy of soil taxonomic units in DSM. In conclusion, this research has shown that spatial scale analysis of environmental covariates significantly enhances the practice of DSM, improving overall classification accuracy of soil taxonomic units. The newly developed multiscale methodology can be successfully integrated in current DSM analysis of soil taxonomic units performed with data mining techniques, so advancing the practice of soil mapping. The future of DSM, as it successfully progresses from the early pioneering years into an established discipline, will have to include scale and in particular multiscale investigations in its methodology. DSM will have to move from a methodology of spatial data with scale to a spatial scale methodology. It is now time to consider scale as a key soil and modelling attribute in DSM.

This thesis addresses the multi-body assembly (MBA) problem in the context of protein assemblies. [...] In this thesis, we chose the protein assembly domain because accurate and reliable computational modeling, simulation and prediction of such assemblies would clearly accelerate discoveries in understanding of the complexities of metabolic pathways, identifying the molecular basis for normal health and diseases, and in the designing of new drugs and other therapeutics. [...] [We developed] F²Dock (Fast Fourier Docking) which includes a multi-term function which includes both a statistical thermodynamic approximation of molecular free energy as well as several of knowledge-based terms. Parameters of the scoring model were learned based on a large set of positive/negative examples, and when tested on 176 protein complexes of various types, showed excellent accuracy in ranking correct configurations higher (F² Dock ranks the correcti solution as the top ranked one in 22/176 cases, which is better than other unsupervised prediction software on the same benchmark). Most of the protein-protein interaction scoring terms can be expressed as integrals over the occupied volume, boundary, or a set of discrete points (atom locations), of distance dependent decaying kernels. We developed a dynamic adaptive grid (DAG) data structure which computes smooth surface and volumetric representations of a protein complex in O(m log m) time, where m is the number of atoms assuming that the smallest feature size h is [theta](r[subscript max]) where r[subscript max] is the radius of the largest atom; updates in O(log m) time; and uses O(m)memory. We also developed the dynamic packing grids (DPG) data structure which supports quasi-constant time updates (O(log w)) and spherical neighborhood queries (O(log log w)), where w is the word-size in the RAM. DPG and DAG together results in O(k) time approximation of scoring terms where k << m is the size of the contact region between proteins. [...] [W]e consider the symmetric spherical shell assembly case, where multiple copies of identical proteins tile the surface of a sphere. Though this is a restricted subclass of MBA, it is an important one since it would accelerate development of drugs and antibodies to prevent viruses from forming capsids, which have such spherical symmetry in nature. We proved that it is possible to characterize the space of possible symmetric spherical layouts using a small number of representative local arrangements (called tiles), and their global configurations (tiling). We further show that the tilings, and the mapping of proteins to tilings on arbitrary sized shells is parameterized by 3 discrete parameters and 6 continuous degrees of freedom; and the 3 discrete DOF can be restricted to a constant number of cases if the size of the shell is known (in terms of the number of protein n). We also consider the case where a coarse model of the whole complex of proteins are available. We show that even when such coarse models do not show atomic positions, they can be sufficient to identify a general location for each protein and its neighbors, and thereby restricts the configurational space. We developed an iterative refinement search protocol that leverages such multi-resolution structural data to predict accurate high resolution model of protein complexes, and successfully applied the protocol to model gp120, a protein on the spike of HIV and currently the most feasible target for anti-HIV drug design. / text

Decision support systems are interactive, computer-based information systems that provide data and analysis tools in order to better assist managers on different levels of organization in the process of decision making. Data warehouses (DWs) have been developed and deployed as an integral part of decision support systems. A data warehouse is a database that allows to store high volume of historical data required for analytical purposes. This data is extracted from operational databases, transformed into a coherent whole, and loaded into a DW during the extraction-transformation-loading (ETL) process. DW data can be dynamically manipulated using on-line analytical processing (OLAP) systems. DW and OLAP systems rely on a multidimensional model that includes measures, dimensions, and hierarchies. Measures are usually numeric additive values that are used for quantitative evaluation of different aspects about organization. Dimensions provide different analysis perspectives while hierarchies allow to analyze measures on different levels of detail. Nevertheless, currently, designers as well as users find difficult to specify multidimensional elements required for analysis. One reason for that is the lack of conceptual models for DW and OLAP system design, which would allow to express data requirements on an abstract level without considering implementation details. Another problem is that many kinds of complex hierarchies arising in real-world situations are not addressed by current DW and OLAP systems. In order to help designers to build conceptual models for decision-support systems and to help users in better understanding the data to be analyzed, in this thesis we propose the MultiDimER model - a conceptual model used for representing multidimensional data for DW and OLAP applications. Our model is mainly based on the existing ER constructs, for example, entity types, attributes, relationship types with their usual semantics, allowing to represent the common concepts of dimensions, hierarchies, and measures. It also includes a conceptual classification of different kinds of hierarchies existing in real-world situations and proposes graphical notations for them. On the other hand, currently users of DW and OLAP systems demand also the inclusion of spatial data, visualization of which allows to reveal patterns that are difficult to discover otherwise. The advantage of using spatial data in the analysis process is widely recognized since it allows to reveal patterns that are difficult to discover otherwise. However, although DWs typically include a spatial or a location dimension, this dimension is usually represented in an alphanumeric format. Furthermore, there is still a lack of a systematic study that analyze the inclusion as well as the management of hierarchies and measures that are represented using spatial data. With the aim of satisfying the growing requirements of decision-making users, we extend the MultiDimER model by allowing to include spatial data in the different elements composing the multidimensional model. The novelty of our contribution lays in the fact that a multidimensional model is seldom used for representing spatial data. To succeed with our proposal, we applied the research achievements in the field of spatial databases to the specific features of a multidimensional model. The spatial extension of a multidimensional model raises several issues, to which we refer in this thesis, such as the influence of different topological relationships between spatial objects forming a hierarchy on the procedures required for measure aggregations, aggregations of spatial measures, the inclusion of spatial measures without the presence of spatial dimensions, among others. Moreover, one of the important characteristics of multidimensional models is the presence of a time dimension for keeping track of changes in measures. However, this dimension cannot be used to model changes in other dimensions. Therefore, usual multidimensional models are not symmetric in the way of representing changes for measures and dimensions. Further, there is still a lack of analysis indicating which concepts already developed for providing temporal support in conventional databases can be applied and be useful for different elements composing a multidimensional model. In order to handle in a similar manner temporal changes to all elements of a multidimensional model, we introduce a temporal extension for the MultiDimER model. This extension is based on the research in the area of temporal databases, which have been successfully used for modeling time-varying information for several decades. We propose the inclusion of different temporal types, such as valid and transaction time, which are obtained from source systems, in addition to the DW loading time generated in DWs. We use this temporal support for a conceptual representation of time-varying dimensions, hierarchies, and measures. We also refer to specific constraints that should be imposed on time-varying hierarchies and to the problem of handling multiple time granularities between source systems and DWs. Furthermore, the design of DWs is not an easy task. It requires to consider all phases from the requirements specification to the final implementation including the ETL process. It should also take into account that the inclusion of different data items in a DW depends on both, users' needs and data availability in source systems. However, currently, designers must rely on their experience due to the lack of a methodological framework that considers above-mentioned aspects. In order to assist developers during the DW design process, we propose a methodology for the design of conventional, spatial, and temporal DWs. We refer to different phases, such as requirements specification, conceptual, logical, and physical modeling. We include three different methods for requirements specification depending on whether users, operational data sources, or both are the driving force in the process of requirement gathering. We show how each method leads to the creation of a conceptual multidimensional model. We also present logical and physical design phases that refer to DW structures and the ETL process. To ensure the correctness of the proposed conceptual models, i.e., with conventional data, with the spatial data, and with time-varying data, we formally define them providing their syntax and semantics. With the aim of assessing the usability of our conceptual model including representation of different kinds of hierarchies as well as spatial and temporal support, we present real-world examples. Pursuing the goal that the proposed conceptual solutions can be implemented, we include their logical representations using relational and object-relational databases.

Repositórios com volumes de dados cada vez maiores foram viabilizados pelo desenvolvimento tecnológico, criando importantes fontes de informação em diversas áreas da atividade humana. Esses repositórios freqüentemente incluem informação sobre o comportamento temporal e o posicionamento espacial dos itens neles representados, os quais são extremamente relevantes para a análise dos dados. O processo de descoberta de conhecimento a partir de grandes volumes de dados tem sido objeto de estudo em diversas disciplinas, dentre elas a Visualização de Informação, cujas técnicas podem apoiar diversas etapas desse processo. Esta tese versa sobre o uso da Visualização Exploratória em conjuntos de dados com atributos temporais e espaciais, empregando a estratégia de múltiplas visualizações coordenadas para apoiar o tratamento de dados em estágios iniciais de processos de descoberta de conhecimento. São propostas duas novas representações visuais temporais – denominadas ‘Variação Temporal Uni-escala’ e ‘Variação Temporal Multi-escala’ – para apoiar a análise exploratória de dados temporais. Adicionalmente, é proposto um modelo de arquitetura de software – AdaptaVis, que permite a integração dessas e outras representações visuais em uma plataforma de visualização de informação flexível, extensível e adaptável às necessidades de diferentes usuários, tarefas e domínios de aplicação – a plataforma InfoVis. Sessões de uso realizadas com dados e usuários reais dos domínios de Climatologia e Negócios permitiram validar empiricamente as representações visuais e o modelo. O modelo AdaptaVis e a plataforma InfoVis estabelecem bases para a continuidade de diversas pesquisas em Visualização de Informação, particularmente o estudo de aspectos relacionados ao uso coordenado de múltiplas visualizações, à modelagem do processo de coordenação, e à integração entre múltiplas técnicas visuais e analíticas. / Data repositories with ever increasing volumes have been made possible by the evolution in data collection technologies, creating important sources of information in several fields of human activity. Such data repositories often include information about both the temporal behavior and the spatial positioning of data items that will be relevant in future data analysis tasks. The process of discovering knowledge embedded in great volumes of data is a topic of study in several disciplines, including Information Visualization, which offers a range of techniques to support different stages of a discovery process. This thesis addresses the application of Exploratory Visualization techniques on datasets with temporal and spatial attributes, using the strategy of coordinating multiple data views, to assist data treatment on early stages of knowledge discovery processes. Two temporal visual representations are proposed – ‘Uni-scale Temporal Behavior’ and ‘Multi-scale Temporal Behavior’ – that support the exploratory analysis of temporal data. Moreover, a software architecture model is introduced – AdaptaVis, that allows the integration of these and other visualization techniques into a flexible, extensible and adaptable information visualization platform – called InfoVis – that may be tailored to meet the requirements of different users, tasks and application domains. Sessions conducted with real data and users from the Climatology and Business application domains allowed an empirical validation of both the visual representations and the model. The AdaptaVis model and the InfoVis platform establish the basis for further research on issues related to the coordinated use of multiple data views, the modeling of the coordination process and the integration amongst multiple visual and analytical techniques.

Submitted by Angela Maria de Oliveira (amolivei@uepg.br) on 2018-05-08T17:08:26Z No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) Antonio David Viniski.pdf: 3962317 bytes, checksum: f5afcd11e4083b0ae065ae21490ac77f (MD5) / Made available in DSpace on 2018-05-08T17:08:26Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) Antonio David Viniski.pdf: 3962317 bytes, checksum: f5afcd11e4083b0ae065ae21490ac77f (MD5) Previous issue date: 2018-03-16 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / O sensoriamento remoto agrícola tem fornecido um volumoso conjunto de dados espaciais, os quais podem ser utilizados em diferentes segmentos, como na estimativa de produtividade de grãos. Dentre as tecnologias empregadas no SR, a utilização de aeronaves remotamente pilotadas (RPA) na agricultura vêm crescendo, sendo uma alternativa na obtenção de dados para a estimativa de produtividade. Porém, esses conjuntos de dados gerados demandam métodos e técnicas capazes de extrair informações úteis e relevantes dos mesmos. Algumas técnicas de geoestatística, como a krigagem, têm sido empregadas, mas a utilização da mineração de dados (MD), assim como da mineração de dados espaciais (MDE), podem ser alternativas viáveis para suprir essa demanda. Este trabalho teve como objetivo avaliar o uso de técnicas de MD e MDE na estimativa da produtividade de grãos de soja e trigo, utilizando dados de imagens obtidas por meio de RPA. A área de estudo localiza-se no município de Piraí do Sul, Paraná. Foi utilizada uma RPA de asa fixa para o acompanhamento das culturas de soja e trigo. No imageamento do trigo foram utilizadas duas câmeras, uma com a captura de imagens no espectro visível (RGB), e outra no infravermelho próximo (NIR), tendo sendo analisadas também as resoluções espaciais de 10 e 20 cm/pixel para cada câmera. Para a soja apenas a câmera RGB foi utilizada e as resoluções espaciais sobrevoadas foram 10, 20 e 26 cm/pixel. Os dados do atributo meta, a produtividade das culturas, foram obtidos por meio de colhedoras de precisão. Os atributos de predição, correspondendo aos valores das bandas espectrais e altitude do terreno, foram submetidos aos algoritmos de MD empregando as técnicas de regressão linear múltipla (RLM), redes neurais artificiais (RNA) e máquina de vetores de suporte para regressão (SVR). Para a MDE, foi utilizado o modelo aditivo generalizado (GAM). Para fins de comparação, os dados foram também analisados pelo método tradicional de krigagem. As técnicas foram testadas considerando duas abordagens principais: (i) utilizando apenas as bandas espectrais para estimativa e, (ii) utilizando as bandas espectrais e os valores de altitude do terreno. Para a MD clássica, os melhores resultados foram obtidos com a técnica SVR, utilizando o kernel Laplacian. Na MDE, o método GAM com a função de ajuste gaussiana apresentou os melhores resultados. Tanto para as técnicas clássicas de MD como para a MDE, a incorporação da altitude nos modelos de regressão possibilitou aumento considerável nos coeficientes de correlação e determinação, com consequente diminuição no erro (RMSE). Os valores de correlação obtidos com a MDE foram semelhantes aos obtidos com o método de krigagem, porém a MDE foi mais eficiente em avaliar o impacto dos atributos de predição (valores das bandas espectrais e altitude) na estimativa do atributo meta. Com isso, conclui-se que a MDE mostra-se viável de ser utilizada como ferramenta na geração de modelos para estimativa de produtividade de grãos com base em dados de imagens de RPA. / Agricultural remote sensing (RS) has provided a massive set of spatial data which can be used in different segments, such as in grain yield estimation. Among the technologies applied in RS, the use of remotely piloted aircraft (RPA) in agriculture is growing as an alternative to obtain data for estimating productivity. However, these generated data sets require methods and techniques capable of extracting useful and relevant information from them. Some geostatistics techniques have been applied, such as kriging, but the use of data mining (DM) as well as spatial data mining (SDM) can be viable alternatives to meet that demand. The goal of this work was to evaluate the use of DM and SDM techniques for estimating soybean and wheat grain yield using image data obtained by RPA. The study area is located in Piraí do Sul, Paraná State. A fixed wing RPA was used to monitor soybean and wheat crops. In wheat crop imaging two cameras were used, one to capture images in the visible spectrum (RGB), and the other one using the near infrared (NIR) spectrum. Also, it was analyzed the spatial resolutions of 10 and 20 cm / pixel for each camera. For soybean only the RGB camera was used and the overhead spatial resolutions were 10, 20 and 26 cm / pixel. The goal attribute data (crop yield), was obtained by precision harvester. The prediction attributes, corresponding to the values of spectral bands and terrain altitude, were submitted to DM algorithms using the multiple linear regression (MLR), artificial neural networks (ANN) and support vector regression (SVR) techniques. For SDM, the generalized additive model (GAM) was used. For comparison purposes, data were also analyzed by the traditional kriging method. The techniques were tested using two main approaches: (i) using only spectral bands for estimation and, (ii) using spectral bands and terrain altitude values. For classical DM, the best results were obtained with SVR technique, using the Laplacian kernel. The GAM method with the Gaussian fit function presented the best results for SDM. For both classical DM and SDM techniques, adding altitude in the regression models allowed a considerable increase in correlation and determination coefficients, with consequent decrease in error (RMSE). The correlation values obtained with SDM were similar to those obtained with kriging method, but SDM was more efficient in evaluating the impact of the prediction attributes (spectral bands and altitude) in the estimation of the goal attribute. Thus, it is concluded that SDM can be useful as a tool for estimating grain yield based on RPA image data.

Made available in DSpace on 2017-07-10T19:24:09Z (GMT). No. of bitstreams: 1 tese__fabiana.pdf: 3413093 bytes, checksum: 69eef866f8ca47e7714ae83768804879 (MD5) Previous issue date: 2016-02-02 / Understanding the spatial distribution knowledge regarding georeferenced data has been essencial to various areas including agriculture. Thus, several trials have been carried out. However, most of these studies assume that the underlying stochastic process is Gaussian. When the data associated with this process do not present normality, data transformations are applied. And though the use of these transformations has presented satisfactory results, it is important to consider models which take into account the characteristics of such phenomenon. It may be more appropriate than using a normal model. So, this trial aimed at proposing a spatial model based on the Birnbaum-Saunders distribution (BS). This distribution has been shown effective to model data that take positive values and whose behavior presents positive asymmetry and unimodality. Thefore, this trial has proposed a methodology that includes the formulation of the spatial Birnbaum-Saunders model , estimation of its parameters using maximum likelihood (ML), and application of diagnostic techniques which can detect the sensitivity of the model to atypical data and evaluate the proposed model through a simulation study and studies using real data sets of agricultural engineering. These data were obtadined in a 167.35-ha commercial area for grain production, in Cascavel city, to validate the studied model. In the study with simulated data and large samples, estimation parameters and diagnostic analysis showed a good performance. According to the study with real data, calculations of AIC (Akaike s information criterion) and BIC (Bayesian information criterion) indexes, Bayes factor as well as Q-Q plots constrution have shown that the proposed model is appropriate to fit the obtained data. Influential cases were detected, and their removal from data set caused a considerable change in contour maps. It is therefore concluided that Birnbaum-Saunders spatial model is adequate to carry out studies with spatially correlated data. Is is also an alternative model to the normal model when the data set present positive asymmetrical distribution / O conhecimento da distribuição espacial de dados georrefenciados é de interesse de diversas áreas do conhecimento, incluindo a área agrícola. Neste sentido, diversos trabalhos já foram realizados; no entanto, a maioria destes trabalhos assumem que o processo estocástico subjacente é gaussiano. Quando os dados associados com este processo não apresentam normalidade, transformações de dados são usadas. E ainda que o uso dessas transformações tenha apresentado resultados satisfatórios, considerar modelos que levem em conta as características do fenômeno pode ser mais adequado do que a utilização do modelo normal. O objetivo deste trabalho é propor um modelo espacial baseado na distribuição Birnbaum-Saunders (BS). Esta distribuição tem se mostrado eficiente para modelar conjuntos de dados formados por valores estritamente positivos e cujo comportamento apresenta assimetria positiva e unimodalidade. A metodologia proposta neste trabalho inclui a formulação do modelo espacial Birnbaum-Saunders, a estimação de seus parâmetros utilizando o método de máxima verossimilhança (ML), a aplicação de técnicas de diagnóstico que permitem detectar a sensibilidade do modelo a dados atípicos, a avaliação do modelo proposto por um estudo de simulação e aplicação da metodologia desenvolvida em análise de dados reais da área agrícola. Os dados utilizados para validação do modelo estudado foram obtidos em uma área comercial de produção de grãos de 167,35 ha de Cascavel. No estudo com dados simulados, para amostras grandes, a estimação dos parâmetros e a análise de diagnóstico apresentaram boa performance. No estudo com dados reais, os cálculos dos índices AIC, BIC e fator Bayes bem como a construção de Q-Q plots mostraram que o modelo proposto é adequado para ajustar os dados. Casos influentes foram detectados e suas retiradas do conjunto de dados causaram uma mudança considerável nos mapas de contorno. Conclui-se portanto, que o modelo espacial Birnbaum-Saunders é adequado para realização de estudos com dados espacialmente correlacionados, e é um modelo alternativo ao modelo normal quando o conjunto de dados apresenta distribuição assimétrica positiva