The study of information extraction and knowledge exploration in the urban environment is gaining popularity. Ubiquitous sensors and a plethora of statistical reports provide an immense amount of heterogeneous urban data, such as traffic data, crime activity statistics, social media messages, and street imagery. The development of methods for heterogeneous urban data-based event identification and impacts analysis for a variety of event topics and assumptions is the subject of this dissertation. A graph convolutional neural network for crime prediction, a multitask learning system for traffic incident prediction with spatiotemporal feature learning, social media-based transportation event detection, and a graph convolutional network-based cyberbullying detection algorithm are the four methods proposed. Additionally, based on the sensitivity of these urban sensor data, a comprehensive discussion on ethical issues of urban computing is presented. This work makes the following contributions in urban perception predictions: 1) Create a preference learning system for inferring crime rankings from street view images using a bidirectional convolutional neural network (bCNN). 2) Propose a graph convolutional networkbased solution to the current urban crime perception problem; 3) Develop street view image retrieval algorithms to demonstrate real city perception. This work also makes the following contributions in traffic incident effect analysis: 1) developing a novel machine learning system for predicting traffic incident duration using temporal features; 2) modeling traffic speed similarity among road segments using spatial connectivity in feature space; and 3) proposing a sparse feature learning method for identifying groups of temporal features at a higher level. In transportation-related incidents detection, this work makes the following contributions: 1) creating a real-time social media-based traffic incident detection platform; 2) proposing a query expansion algorithm for traffic-related tweets; and 3) developing a text summarization tool for redundant traffic-related tweets. Cyberbullying detection from social media platforms is one of the major focus of this work: 1) Developing an online Dynamic Query Expansion process using concatenated keyword search. 2) Formulating a graph structure of tweet embeddings and implementing a Graph Convolutional Network for fine-grained cyberbullying classification. 3) Curating a balanced multiclass cyberbullying dataset from DQE, and making it publicly available. Additionally, this work seeks to identify ethical vulnerabilities from three primary research directions of urban computing: urban safety analysis, urban transportation analysis, and social media analysis for urban events. Visions for future improvements in the perspective of ethics are addressed. / Doctor of Philosophy / The ubiquitously deployed urban sensors such as traffic speed meters, street-view cameras, and even smartphones in everybody's pockets are generating terabytes of data every hour. How do we refine the valuable intelligence out of such explosions of urban data and information became one of the profitable questions in the field of data mining and urban computing. In this dissertation, four innovative applications are proposed to solve real-world problems with big data of the urban sensors. In addition, the foreseeable ethical vulnerabilities in the research fields of urban computing and event predictions are addressed. The first work explores the connection between urban perception and crime inferences. StreetNet is proposed to learn crime rankings from street view images. This work presents the design of a street view images retrieval algorithm to improve the representation of urban perception. A data-driven, spatiotemporal algorithm is proposed to find unbiased label mappings between the street view images and the crime ranking records. The second work proposes a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. Such functionality provided by this model is helpful for the transportation operators and first responders to judge the influences of traffic incidents. In the third work, a social media-based traffic status monitoring system is established. The system is initiated by a transportation-related keyword generation process. A state-of-the-art tweets summarization algorithm is designed to eliminate the redundant tweets information. In addition, we show that the proposed tweets query expansion algorithm outperforms the previous methods. The fourth work aims to investigate the viability of an automatic multiclass cyberbullying detection model that is able to classify whether a cyberbully is targeting a victim's age, ethnicity, gender, religion, or other quality. This work represents a step forward for establishing an active anti-cyberbullying presence in social media and a step forward towards a future without cyberbullying. Finally, a discussion of the ethical issues in the urban computing community is addressed. This work seeks to identify ethical vulnerabilities from three primary research directions of urban computing: urban safety analysis, urban transportation analysis, and social media analysis for urban events. Visions for future improvements in the perspective of ethics are pointed out.

Governments all over the world are being challenged to develop Spatial Data Infrastructure (SDI), to improve the access and use of spatial data for decision support and sustainable development. Therefore, SDI is part of the basic infrastructure that needs to be efficiently implemented and managed in the interest of any nation. The aim of this study, therefore, is to assess the feasibility of SDI implementation in Rwanda, using the Land administration geospatial data sector as a case study, given time constraints of the research. To achieve this, the concept of SDI is firstly explained in order to provide a common understanding of the concept. The new trends in the new Land Administration System of Rwanda, with emphasis on spatial data management are also presented. This information is generated from various written materials. Field work was also conducted by means of questionnaires, interviews and observation in attempt to assess Land Administration geospatial data, related assets and gaps with reference to SDI framework requirements. A situational analysis is carried out from the field work results. The research sets the scene providing the major findings. The main spatial data providers are public and based on national level. Land use and cadastral related spatial data are the least developed, and Land Administration application data are quiet non-existent. Various users, mainly decision makers, exist but lack effective access to data. A number of challenges, such as a high duplication of data collection and maintenance, lack of appropriate ways of data sharing, a shortage of human resources in Geo-information, absence of policies and regulations, are also found in the Land Administration spatial data sector. Nevertheless, the new Land Administration System orientations and national priorities in terms of information technology, offer a favourable environment for the implementation of SDI. Having considered this, the research proceeds to propose a Land Administration SDI prototype with its main application of Spatial Data discovery Facility, and then highlights its benefits. The research ends with a conclusion and recommendations for future research. / Thesis (M.Env.Dev.)-University of KwaZulu-Natal, Pietermaritzburg, 2007.

Currently, existing devices for extracting electrical power from ocean waves all suffer from problems with low efficiency due to a lack of information about the incoming waves in advance. The complex dynamic nonlinear characteristics of the ocean make the prediction of these incoming waves a great challenge. This paper aims to investigate a deterministic short-term wave-by-wave prediction system, that can accurately predict the wave height and timing of the incoming waves, based on measurements from a submerged pressure sensor. The complete prediction process contains three steps, namely reconstruction, assimilation, and prediction. A nonlinear Weakly Dispersive Reconstruction method (WDM) is firstly employed to accurately calculate the surface elevation from the measured pressures. Afterwards, a variational assimilation method is used to convert the time series surface elevation to a spatial wavefield, to obtain initial conditions for the prediction. Lastly, a High Order Spectral Method (HOSM) deterministically predicts the evolution of the 2D irregular wavefield based on the acquired initial conditions. To verify the performance of this proposed prediction system, tests were conducted with data from irregular sea states with varying wave parameters, generated by simulations as well as model experiments in the controlled environment of a wave tank. The results show that the surface elevation can be predicted within 5% from the reference, for a future period of about 10 seconds for wavefields commonly experienced by a wave energy converter. Based on the results, a prediction is possible, but the accuracy heavily depends on the current sea state and the chosen prediction distance.The results have been compared against similar tests made using radar data and proven to be a viable alternative for certain sea states. In conclusion, pressure measurements, as a mean to sample an ocean wavefield, is shown to be a good option when combined with nonlinear reconstruction and prediction methods to assist the power harvesting capabilities of a wave energy converter. / Nuvarande enheter för att extrahera elektrisk energi från havsvågor lider av stora problem med låg effektivitet på grund av brist på information om de inkommande vågorna. Det komplexa ickelinjära dynamiska beteendet hos havsvågor gör förutsägelsen av dem till en stor utmaning. Det här arbetet syftar till att undersöka ett deterministiskt kortsiktigt system för att förutspå våg för våg, som noggrant kan förutspå våghöjd och tidpunkt för de inkommande vågorna, baserat på mätdata från en dränkbar trycksensor. Den kompletta förutsägelseprocessen innehåller tre steg, rekonstruktion, assimilering och förutsägelse. En ickelinjär weakly dispersive reconstruction method används först för att med hög noggrannhet beräkna ythöjningen från det uppmätta trycket. Därefter, används en variational assimilation method för att konvertera en tidsserie av ythöjningen till ett rumsligt vågfält, för att erhålla initialvillkor för förutsägelsen. Slutligen används en High Order Spectral Method för att deterministiskt förutspå utvecklingen av det tvådimensionella oregelbundna vågfältet baserat på de förvärvade initialvillkoren. För att verifiera prestandan av det föreslagna förutsägelsesystemet, så genomfördes tester med data från olika oregelbundna havstillstånd med varierande parametrar, genererade av simuleringar, såväl som modellexperiment utförda i en kontrollerad miljö i form av en vågtank. Resultaten från testerna visar att ythöjningen förutspås inom 5% från referensen, för en period på 10 sekunder framåt i tiden, för vågor som ett vågkraftverk vanligtvis utsätts för. Baserat på resultatet, så är det möjligt att förutspå inkommande vågor, men noggrannheten beror kraftigt på det aktuella havstillståndet och det valda avståndet för förutsägelsen. Resultaten har jämförts mot liknande tester gjorda med radardata och visat sig vara ett genomförbart alternativ för vissa havstillstånd. Sammanfattningsvis visas det att tryckmätningar, som ett medel för att mäta ett havsvågfält, är ett bra alternativ när de kombineras med ickelinjära rekonstruktions- och förutsägelsemetoder för att hjälpa till att öka ett vågkraftverks energigenerering.

Doctor of Philosophy / Department of Biological & Agricultural Engineering / Kyle R. Douglas-Mankin / Water quality trading (WQT) is a market-based approach to improve water quality. It is an innovative, voluntary program that connects point source (PS) dischargers who need to reduce their pollutant loads with land managers who could offset those loads with nonpoint source (NPS) reductions to economically achieve water quality improvements in a watershed. The potential issues impeding WQT are its inability to address trading risks and quantify the uncertainty of potential load reduction in trades between PS and NPS. Recent research has also shown that trading information level and transaction costs cause problems in implementing WQT. Therefore, the goals of this study were to quantify the uncertainties of pollutant load reduction and delivery effect for potential trades, to estimate their spatiotemporal variations, and to provide information for stakeholders to reduce intangible costs of WQT. This study simulated agricultural cropland with more than 225 alternative land management practices to identify trends among these scenarios. Both total nitrogen and total phosphorus loads were modeled with SWAT and EUTROMOD for 36 years to analyze the potential load reduction, in-field uncertainty ratio, in-stream delivery ratio, and overall trading ratio (TR) in Lower Kansas watershed, Kansas. The analyses of site-specific effects in both geospatial and temporal aspects were also applied on subbasin level. The variant loading patterns and time distributions of each subbasin showed strong site-specific phenomena. The ANOVA of in-field nutrient load showed significant differences among the design criteria of scenarios. The results also showed a significant delivery and lake effects within the subbasins. The overall TR ranged from 1 to 2.2 or more in different scenarios. The advanced cluster analysis presented a potential method to eliminate the problems involved in fixed TRs while keeping the method simpler than finer-resolution floating TR system. Based on WQT geospatial data model, a three-tier GIS-based web interface Water Quality Trading Information Platform System (WQTIPS) was then developed for WQT information and assessment. A case study demonstrated WQTIPS can provide systematic, spatially information for stakeholders to assess the potential environmental benefit changes from the land management shifts using a simple interface. This study demonstrated that it is possible to automate water-quality trades, use watershed models to minimize trading risk and maximize water-quality benefits, and prioritize among possible trades both spatially and by BMP.

<p>U radu su prikazani Open Geospatial Consortium (OGC) web servisi, iz aspekta serverskih i klijentskih aplikacija. Analizirani su problemi razmene prostornih podataka u složenim sistemima sa naglaskom na komunalne službe gradova. Na osnovu analize razmene podataka, predložen je model koji unapređuje komunikaciju i pospešuje napredak celokupnog sistema implementacijom distribuiranih OGC web servisa. Predloženi model distribucije prostornih podataka može se primenjivati na sve složene sisteme, ali i unutar manjih sistema kao što su kompanije koje se sastoje iz više sektora ili podsistema</p> / <p> The short review of the Open Geospatial Consortium (OGC) web services have been given in this work from the perspective of server and client applications. The problems of the exchange of spatial data in the complex systems as municipal service have been analysed. Based on analysis of data exchange, the model has been proposed to improve communication and progress of the whole system by implementing OGC web services. Described model of spatial data distribution can be applied to all complex systems, but also within smaller systems such as companies which consist of more<br /> sectors or subsystems.</p>

It turns out that for most users of spatial data presents a harmonization of data (as an elimination of heterogeneity) as the greatest problem - a transformation their own data sets to the data specifications produced by the INSPIRE Directive so as not to limit current processes processing, management, sharing and presentation of data. Therefore, they need the widest possible description of spatial data, because it will only eliminate the problems of heterogeneity. The author of this Ph.D. thesis dealt with the opportunities which ontologies bring to the process of data modelling. The aim was to describe using ontologies the selected part (classification systems) of data models of spatial data themes "Land Cover" and "Land Use" which are defined in Annexes II and III of the INSPIRE directive. Developed ontologies serve as a source of information on classification systems. Their evaluation (so-called reasoning) will provide new information (relationships between taxonomy elements) that play an important role in the transformation process of classification systems as part of the harmonization of spatial data. Creating of ontologies consisted of three main steps - selection of appropriate methodology, development of a basic ontology structure and iterative process of populating and specification of...

Spatial data warehouses (SDW) and spatial online analytical processing (SOLAP) enhance decision making by enabling spatial analysis combined with multidimensional analytical queries. A SDW is an integrated and voluminous multidimensional database containing both conventional and spatial data. SOLAP allows querying SDWs with multidimensional queries that select spatial data that satisfy a given topological relationship and that aggregate spatial data. Existing SDW and SOLAP applications mostly consider phenomena represented by spatial data having exact locations and sharp boundaries. They neglect the fact that spatial data may be affected by imperfections, such as spatial vagueness, which prevents distinguishing an object from its neighborhood. A vague spatial object does not have a precisely defined boundary and/or interior. Thus, it may have a broad boundary and a blurred interior, and is composed of parts that certainly belong to it and parts that possibly belong to it. Although several real-world phenomena are characterized by spatial vagueness, no approach in the literature addresses both spatial vagueness and the design of SDWs nor provides multidimensional analysis over vague spatial data. These shortcomings motivated the elaboration of this doctoral thesis, which addresses both vague spatial data warehouses (vague SDWs) and vague spatial online analytical processing (vague SOLAP). A vague SDW is a SDW that comprises vague spatial data, while vague SOLAP allows querying vague SDWs. The major contributions of this doctoral thesis are: (i) the Vague Spatial Cube (VSCube) conceptual model, which enables the creation of conceptual schemata for vague SDWs using data cubes; (ii) the Vague Spatial MultiDim (VSMultiDim) conceptual model, which enables the creation of conceptual schemata for vague SDWs using diagrams; (iii) guidelines for designing relational schemata and integrity constraints for vague SDWs, and for extending the SQL language to enable vague SOLAP; (iv) the Vague Spatial Bitmap Index (VSB-index), which improves the performance to process queries against vague SDWs. The applicability of these contributions is demonstrated in two applications of the agricultural domain, by creating conceptual schemata for vague SDWs, transforming these conceptual schemata into logical schemata for vague SDWs, and efficiently processing queries over vague SDWs. / Les entrepôts de données spatiales (EDS) et l'analyse en ligne spatiale (ALS) améliorent la prise de décision en permettant l'analyse spatiale combinée avec des requêtes analytiques multidimensionnelles. Un EDS est une base de données multidimensionnelle intégrée et volumineuse qui contient des données classiques et des données spatiales. L'ALS permet l'interrogation des EDS avec des requêtes multidimensionnelles qui sélectionnent des données spatiales qui satisfont une relation topologique donnée et qui agrègent les données spatiales. Les EDS et l'ALS considèrent essentiellement des phénomènes représentés par des données spatiales ayant une localisation exacte et des frontières précises. Ils négligent que les données spatiales peuvent être affectées par des imperfections, comme l'imprécision spatiale, ce qui empêche de distinguer précisément un objet de son entourage. Un objet spatial vague n'a pas de frontière et/ou un intérieur précisément définis. Ainsi, il peut avoir une frontière large et un intérieur flou, et est composé de parties qui lui appartiennent certainement et des parties qui lui appartiennent éventuellement. Bien que plusieurs phénomènes du monde réel sont caractérisés par l'imprécision spatiale, il n'y a pas dans la littérature des approches qui adressent en même temps l'imprécision spatiale et la conception d'EDS ni qui fournissent une analyse multidimensionnelle des données spatiales vagues. Ces lacunes ont motivé l'élaboration de cette thèse de doctorat, qui adresse à la fois les entrepôts de données spatiales vagues (EDS vagues) et l'analyse en ligne spatiale vague (ALS vague). Un EDS vague est un EDS qui comprend des données spatiales vagues, tandis que l'ALS vague permet d'interroger des EDS vagues. Les contributions majeures de cette thèse de doctorat sont: (i) le modèle conceptuel Vague Spatial Cube (VSCube), qui permet la création de schémas conceptuels pour des EDS vagues à l'aide de cubes de données; (ii) le modèle conceptuel Vague Spatial MultiDim (VSMultiDim), qui permet la création de schémas conceptuels pour des EDS vagues à l'aide de diagrammes; (iii) des directives pour la conception de schémas relationnels et des contraintes d'intégrité pour des EDS vagues, et pour l'extension du langage SQL pour permettre l'ALS vague; (iv) l'indice Vague Spatial Bitmap (VSB-index) qui améliore la performance pour traiter les requêtes adressées à des EDS vagues. L'applicabilité de ces contributions est démontrée dans deux applications dans le domaine agricole, en créant des schémas conceptuels des EDS vagues, la transformation de ces schémas conceptuels en schémas logiques pour des EDS vagues, et le traitement efficace des requêtes sur des EDS vagues. / O data warehouse espacial (DWE) é um banco de dados multidimensional integrado e volumoso que armazena dados espaciais e dados convencionais. Já o processamento analítico-espacial online (SOLAP) permite consultar o DWE, tanto pela seleção de dados espaciais que satisfazem um relacionamento topológico, quanto pela agregação dos dados espaciais. Deste modo, DWE e SOLAP beneficiam o suporte a tomada de decisão. As aplicações de DWE e SOLAP abordam majoritarimente fenômenos representados por dados espaciais exatos, ou seja, que assumem localizações e fronteiras bem definidas. Contudo, tais aplicações negligenciam dados espaciais afetados por imperfeições, tais como a vagueza espacial, a qual interfere na identificação precisa de um objeto e de seus vizinhos. Um objeto espacial vago não tem sua fronteira ou seu interior precisamente definidos. Além disso, é composto por partes que certamente pertencem a ele e partes que possivelmente pertencem a ele. Apesar de inúmeros fenômenos do mundo real serem caracterizados pela vagueza espacial, na literatura consultada não se identificaram trabalhos que considerassem a vagueza espacial no projeto de DWE e nem para consultar o DWE. Tal limitação motivou a elaboração desta tese de doutorado, a qual introduz os conceitos de DWE vago e de SOLAP vago. Um DWE vago é um DWE que armazena dados espaciais vagos, enquanto que SOLAP vago provê os meios para consultar o DWE vago. Nesta tese, o projeto de DWE vago é abordado e as principais contribuições providas são: (i) o modelo conceitual VSCube que viabiliza a criação de um cubos de dados multidimensional para representar o esquema conceitual de um DWE vago; (ii) o modelo conceitual VSMultiDim que permite criar um diagrama para representar o esquema conceitual de um DWE vago; (iii) diretrizes para o projeto lógico do DWE vago e de suas restrições de integridade, e para estender a linguagem SQL visando processar as consultas de SOLAP vago no DWE vago; e (iv) o índice VSB-index que aprimora o desempenho do processamento de consultas no DWE vago. A aplicabilidade dessas contribuições é demonstrada em dois estudos de caso no domínio da agricultura, por meio da criação de esquemas conceituais de DWE vago, da transformação dos esquemas conceituais em esquemas lógicos de DWE vago, e do processamento de consultas envolvendo as regiões vagas do DWE vago. / Doctorat en Sciences de l'ingénieur et technologie / Location of the public defense: Universidade Federal de São Carlos, São Carlos, SP, Brazil. / info:eu-repo/semantics/nonPublished

A falta de padronização de dados pode resultar em perda de informações de suma importância nas diversas áreas do conhecimento, impossibilitando a integração de dados entre diferentes sistemas ou de diferentes bancos de dados, ou seja, os dados podem não ser interoperáveis. A solução para a integração de dados pode ser chamada de interoperabilidade, que são convenções e normas de formatos (extensões) e ontologias (padrões comuns) instituídos para que os sistemas possam dialogar. Um banco de dados de biodiversidade é um instrumento muito importante para as iniciativas de sua conservação, sendo útil para o seu conhecimento, registro histórico entre outros. Este trabalho desenvolveu uma metodologia para interoperar dados modelados no padrão Taxonomic Data Working Group (TDWG) e tags do OpenStreetMap (OSM) sobre a espécie Sotalia guianensis, conhecida como Boto Cinza. Dentro deste escopo, este trabalho se justifica pelo cenário de ameaça de extinção do Boto Cinza, pela necessidade no desenvolvimento de metodologias para a disponibilização de dados de ocorrência de Boto Cinza em bancos de dados de biodiversidade e pela necessidade de se desenvolver metodologia que permita a interoperabilidade entre bancos de dados de biodiversidade e outros Sistemas de Informação Geográfica (SIG). Este estudo propõe uma metodologia de baixo custo, com a utilização de plataformas livres, para que dados espaciais de Biodiversidade sejam modelados de maneira a evitar problemas taxonômicos, além de serem disponibilizados para conhecimento geral da população. O trabalho se mostra inovador por integrar dados do Global Diversity Information Facility (GBIF) com as Tags do OSM, possibilitando o cadastro padronizado e gratuito em uma plataforma livre e de alcance mundial através da criação de uma etiqueta interoperável de equivalência entre o padrão TDWG e as etiquetas do OSM. O resultado deste trabalho é a metodologia para a modelagem e publicação de dados de Boto Cinza no GBIF e OSM de forma interoperável, que foi implementada, testada e cujos resultados são positivos / The absence of data standardization may result in loss of information of major importance through several areas of knowledge, hindering data integration among different information systems or databases, that is, the data may not be interoperable. The solution for data integration may be called interoperability, which is comprised of conventions, data format standards (file extensions) and ontologies (standards), empowering the communication among information systems. A biodiversity database is a very important tool for biodiversity conservation initiatives, being useful for knowledge transfer, historical data storage among other activities. This work developed a methodology for interoperate data between the Taxonomic Data Working Group (TWDG) standard and OpenStreetMap (OSM) tags on Sotalia guianensis species, as known as Guiana dolphin. This work has its motivation scenario on the fact that the Guiana dolphin is under threat of extinction. This scenario demands the development of methodologies for the publication of the locations where the Guiana dolphin is being spotted over the biodiversity databases and the development of a methodology for interoperability among biodiversity databases as well as Geographic Information Systems (SIG). This study proposes a low cost methodology, which uses open-source platforms and focuses on two main goals: avoidance of taxonomical problems on biodiversity spatial data modelling and to provide the biodiversity spatial data to the population in general. This work proves itself innovative by integrating Global Diversity Information Facility (GBIF) data with OSM tags, allowing a free and standardized registry of data in an open-source global-scale platform by using an interoperable tag of equivalence data between the TDWG standard and OSM tags. The result of this study is the methodology for data modelling and publication of the Guiana dolphin on GBIF and OSM in an interoperable manner, which has been implemented, tested and gave positive results

Os sistemas de Informações Geográficas foram desenvolvidos com os avanços das Ciências da Computação, com base nos conceitos das Ciências Geodésicas, para serem aplicados em áreas onde os dados espaciais são utilizados. Procura-se obter uma otimização desta tecnologia, possibilitando o desenvolvimento de sistemas aplicativos interativos. Abordam-se conceitos relativos a modelagem de dados espaciais. Analisam-se a aplicação no mundo real e no modelo conceitual decorrentes. Formula-se um modelo físico com base na Emergência Médica, obtendo-se um sistema que integra programas de saúde para localização de pacientes. / The Geographic Information Systems has been developed based on the progress of the computer sciences, using concepts of the geodesic sciences, to by applied where spatial data are need. This technology is optimized and interactive systems are made. Concepts relative to spatial data modeling are discussed. The application on the real world and the conceptual model is analyzed. The physical model is formulated based on the medical emergency, to obtain a system that integrates health programs to find patients.

Esse trabalho apresenta uma proposta de Infraestrutura de Dados Espaciais de nível organizacional para o Parque Estadual de Intervales-SP, que visa compartilhar suas informações geográficas com a sociedade em geral. Nos processos de elaboração da IDE são discutidas questões como interoperabilidade, padronização, metadados, especificação de serviços geográficos e o relacionamento dos nós das Infraestrutura de Dados Espaciais que vão permitir a disseminação da informação geográfica de fácil acesso a usuários externos. Os procedimentos, benefícios e limitações são listados e problematizados de forma que demonstrem as etapas necessárias na elaboração da Infraestrutura de Dados Espaciais de nível organizacional para uma Unidade de Conservação. Conclui-se que uma Infraestrutura de Dados Espaciais depende de variáveis administrativas, culturais, técnicas e financeiras, o que leva a uma proposta de implementação por estágios. Também são elaboradas críticas aos recursos existentes e sugestões para melhorias e estudos futuros. / This paper presents a proposal about Spatial Data Infrastructure in organizational level to the Parque Estadual de Intervales-SP, in order to promote the sharing of geographic information with the society. In the elaboration process of the SDI are discussed issues such as interoperability, standardization, metadata, specifying geographic services and relationship of the Spatial Data Infrastructure nodes that will enable the dissemination of geographic information easily and accessible to external users. The process steps, benefits and limitations are listed and discussed in order to demonstrate the necessary steps to prepare the Spatial Data Infrastructure in organizational level to a protected area. As results we observe a spatial data infrastructure that depends of others variables like management, culture, technical and financial company aspects, which leads to a proposal of implementation in stages, as well as discussions about the capabilities and suggestions for improvements and future studies.