In many industrial and scientific applications, accurate sensor measurements are crucial. Instruments such as nitrate sensors are vulnerable to environmental conditions, calibration drift, high maintenance costs, and degrading. Researchers have turned to advanced computational methods, including mathematical modeling, statistical analysis, and machine learning, to overcome these limitations. Deep learning techniques have shown promise in outperforming traditional methods in many applications by achieving higher accuracy, but they are often criticized as 'black-box' models due to their lack of transparency. This thesis presents a framework for deep learning-based soft sensors that can quantify the robustness of soft sensors by estimating predictive uncertainty and evaluating performance across various scenarios. The framework facilitates comparisons between hard and soft sensors. To validate the framework, I conduct experiments using data generated by AI and Cyber for Water and Ag (ACWA), a cyber-physical system water-controlled environment testbed. Afterwards, the framework is tested on real-world environment data from Alexandria Renew Enterprise (AlexRenew), establishing its applicability and effectiveness in practical settings. / Master of Science / Sensors are essential in various industrial systems and offer numerous advantages. Essential to measurement science and technology, it allows reliable high-resolution low-cost measurement and impacts areas such as environmental monitoring, medical applications and security. The importance of sensors extends to Internet of Things (IoT) and large-scale data analytics fields. In these areas, sensors are vital to the generation of data that is used in industries such as health care, transportation and surveillance. Big Data analytics processes this data for a variety of purposes, including health management and disease prediction, demonstrating the growing importance of sensors in data-driven decision making. In many industrial and scientific applications, precision and trustworthiness in measurements are crucial for informed decision-making and maintaining high-quality processes. Instruments such as nitrate sensors are particularly susceptible to environmental conditions, calibration drift, high maintenance costs, and a tendency to become less reliable over time due to aging. The lifespan of these instruments can be as short as two weeks, posing significant challenges. To overcome these limitations, researchers have turned to advanced computational methods, including mathematical modeling, statistical analysis, and machine learning. Traditional methods have had some success, but they often struggle to fully capture the complex dynamics of natural environments. This has led to increased interest in more sophisticated approaches, such as deep learning techniques. Deep learning-based soft sensors have shown promise in outperforming traditional methods in many applications by achieving higher accuracy. However, they are often criticized as "black-box" models due to their lack of transparency. This raises questions about their reliability and trustworthiness, making it critical to assess these aspects. This thesis presents a comprehensive framework for deep learning-based soft sensors. The framework will quantify the robustness of soft sensors by estimating predictive uncertainty and evaluating performance across a range of contextual scenarios, such as weather conditions, flood events, and water parameters. These evaluations will help define the trustworthiness of the soft sensor and facilitate comparisons between hard and soft sensors. To validate the framework, we will conduct experiments using data generated by ACWA, a cyber-physical system water-controlled environment testbed we developed. This will provide a controlled environment to test and refine our framework. Subsequently, we will test the framework on real-world environment data from AlexRenew. This will further establish its applicability and effectiveness in practical settings, providing a robust and reliable tool for sensor data analysis and prediction. Ultimately, this work aims to contribute to the broader field of sensor technology, enhancing our ability to make informed decisions based on reliable and accurate sensor data.

The following diploma thesis deals with those problems related to the emergency water supply in crisis situations in the South Bohemian Region and with working procedures related to protection of residents during preparation and application of the emergency water supply. The objective of this diploma thesis is to determine those special characteristics of the emergency water supply in crisis situations and to compare the possibilities of the emergency water supply in crisis situations in selected regions. The theoretical part provides a basic survey of legislation related to the topic, as well as that of other methodical documents which are necessary for solving this type of crisis. Furthermore, the theoretical part unifies selected specialised terminology and characterizes the system of the regular (non-emergency) water supply, which represents the basic pillar for the emergency water supply. Last but not least, the theoretical part summarises those problems related to the emergency water supply and risk factors that can cause or significantly influence it. The practical part deals with those characteristics and their comparison of the selected regions in the South Bohemian Region, by using those specific indicators that are related to the water supply. The quantitative research was carried out by using the definition of what the special characteristics of the emergency drinking water supply are, in 17 administration districts of municipalities with extended competence in the South Bohemian Region. The data provided by the Czech Statistical Office were also used. Furthermore, a description statistics of the differences between the individual administrative districts of these municipalities with extended competence in the South Bohemian Region was carried out, as well as the quantification of those identified special characteristics of the emergency water supply. Finally, a statistical investigation of the identified special characteristics was carried out, as well as a test of a distribution-free hypothesis about the division of statistical data. Based upon the research that has been carried out, the final part of this thesis confirms two stipulated hypotheses about the dependence of the emergency water supply in crisis situations, based upon specific local conditions and about preparedness of the crisis management authorities for situations which would require an emergency water supply.

Trafikverket har genom en kapacitetsutredning och nationell plan fastslagit att de ska satsa på att möta framtida efterfrågeökning av transporter genom att effektivisera den befintliga infrastrukturen i första hand, eftersom utbyggnad är väldigt kostsamt och tar lång tid. För det allmänna nätet har begreppet och konceptet intelligenta elnät diskuterats sedan 2005 som ett sätt att effektivisera användningen av näten för att möta nya politiska krav som innebär en energiomställning samt ökad involvering från kunder. Då detta är ett vedertaget koncept för det allmänna nätet blev det relevant att undersöka hur förutsättningar och behov för ett liknande koncept till järnvägens banmatningssystem kunde tänkas se ut. Målet för studien är därför att identifiera potentialen i att utveckla ett liknande koncept för banmatningssystemet som intelligenta elnät är för det allmänna nätet, men också att föreslå lösningar från dagens tillgängliga intelligenta tekniker. För ÅF Infrastructure AB är målet med examensarbetet att utöka kunskapen på området. Av denna anledning blev syftet med examensarbetet att undersöka just förutsättningar och behov av intelligenta elnät till järnvägens banmatningssystem genom en jämförelse med det allmänna nätet samt en situationsanalys av norra malmbanan. Förutsättningarna beskrivs från en litteraturstudie av forskningen och marknaden samt intervjuer med representanter från systemägarna Trafikverket och Vattenfall. Behovet av intelligenta tekniker till banmatningssystemet beskrivs av en statistisk analys gjord på sträckan mellan Stenbacken och Tornehamn på norra malmbanan i Norrbotten. Resultatet från litteraturstudien visar att forskningen kring intelligenta banmatningssystem mestadels är applikationsinriktad och det beskrivs som ett kaos av applikationer som saknar en grundstomme i ett definierat ramverk. Det finns dock en studie som definierat funktioner till ett koncept kring intelligenta järnvägssystem som tar ett helhetsgrepp om järnvägssystemet och föreslår funktioner som forskningen kan tänkas fokusera på. På marknaden har det uppstått tvärvetenskapliga samarbeten mellan IT-bolag och järnvägsbolag för att ta fram integrerade intelligenta tekniker. Idag finns exempel på energieffektiva tåg, aktiv kompensering av övertoner och reaktiv effekt samt lagringsenheter som hanterar återmatning av effekt. Övertoner, reaktiv effekt och återmatning av effekt är alla parametrar som gör banmatningssystemet ineffektivt idag. Resultatet från intervjuerna visar att Vattenfall ser på intelligenta elnät som det framtida elnätet och har börjat implementera det. Trafikverket ser inte på det framtida banmatningssystemet inom ramen av ett koncept så som intelligenta elnät, men ökar informationsinsamlingen för att skapa förståelse kring systemet. Trafikverket var också del av ett europeiskt samarbete för att skapa ett intelligent energihanteringssystem med interoperabilitet mellan länderna och så har de infört överordnad styrning av effekt med goda resultat. De utvecklar alltså elnäten i samma riktning, där Vattenfall gör det inom ramen för intelligenta elnät medan Trafikverket inte har ett definierat koncept som framtidsscenario. Den statistiska analysen indikerar att den aktiva effekten mellan Stenbacken och Tornehamn slår i taket för maxgräns med dagens trafik, så om trafiken ska utökas som planerat behöver systemet effektiviseras eller byggas ut. Analysen visar också att återmatad effekt tas upp av andra tåg på sträckan, vilket leder till minskad utmatad effekt men högre ledningsförluster. Slutligen visar analysen hur viktigt det är att kvalitetssäkra insamlingen av data. Studien var svår att genomföra på grund av avsaknad av parametrar och osäkerheter kring hur de tagits fram. Sammanfattningsvis visar studien att det finns förutsättningar för ett intelligent banmatningssystem då forskningen efterfrågar ett konceptuellt ramverk i ett kaos av applikationsforskning, men som också börjat närma sig just detta. Dessutom finns intelligenta tekniker på marknaden samt en systemägare som utökar informationsinsamlingen och bidrar till utvecklingen via europeiskt samarbete. Den statistiska analysen visar att det finns ett behov av intelligenta tekniker för att kunna utöka trafiken på norra malmbanan samt ett behov av att kvalitetssäkra insamlingen av data. En föreslagen lösning återfinns inom ramen för intelligenta järnvägssystem med enheter som fångar upp återmatad effekt, vilket skulle minska överföringsförlusterna och osäkerheten kring vart i systemet effekten tar vägen och hur systemet påverkas av den. Om trafiken kunde optimeras med hänsyn till effekttoppar skulle trafiken på norra malmbanan kunna utökas utan att taket för maxgräns slås i då denna gräns endast nåddes, eller var nära att nås, vid några få tillfällen. / The aim of this thesis was to investigate the possibility and need of smart grids to the railway power supply system. The possibilities were investigated through a literature study and interviews, which resulted in a systems perspective of research, market and system, related to smart grids and intelligent transportation systems. The results then constituted a basis for a comparison between smart grids for the national grid and smart grids to the railway power supply system. The need of smart grids to the railway power supply system was investigated through a case study of statistical analysis. The case study was located to the most northern railway in Sweden between Stenbacken and Tornehamn. This thesis concludes that the research and market are focused on developing technical applications to create an intelligent railway transportation system but lacks a well-defined concept like the smart grid concept for the national grid. The owner of the railway power supply system, Trafikverket, is planning on increasing the amount of data collected from the system and has participated in a European collaboration to set standards for an interoperable energy management system. The case study indicates a need to make the railway power supply system more efficient or expand the power grid to be able to meet future requirements of more traffic. With regards to Trafikverkets method of making the system more efficient as a first option to increase capacity, this study suggests to do this with smart grids.

Undermarksanläggningars komplexa och unika design samt deras placering medför svårigheter vid räddningsinsatser. Även om det i lag krävs tillfredsställande brandskydd ges begränsad vägledning om hur detta ska uppnås, särskilt när det gäller räddningstjänstens möjlighet till släck- och livräddningsinsats. Detta kan leda till meningsskiljaktigheter mellan räddningstjänsten och projektörer avseende exempelvis val av vattenförsörjningssystem. Vattenförsörjningssystemet påverkar räddningstjänstens förflyttningshastighet och luftförbrukning, liksom förmågan att snabbt inleda brandbekämpning, men har också en viktig ekonomisk aspekt som måste beaktas. Syftet med detta examensarbete är att visa hur olika vattenförsörjningssystem påverkar räddningstjänstens insats i undermarksanläggningar, med fokus på förflyttningshastighet och luftförbrukning. Detta görs genom att använda information från tidigare utförda forskningsprojekt. Vidare undersöks tryckförlusterna i olika vattenförsörjningssystem, samt granskas dessa olika system ur ett ekonomiskt perspektiv. Även olika vattenförsörjningssystem som tillämpas i såväl nationella och internationella undermarksanläggningar presenteras. Det är framförallt mängden luft rökdykarna har tillgänglig som begränsar den tid rökdykarna kan vistas i undermarksanläggningen. Varje åtgärd som ger en lägre fysisk belastning på rökdykarna kan därför direkt omvandlas till aktionstid. Ett fast vattenförsörjningssystem möjliggör en snabbare förflyttningshastighet i tunnlar jämfört med traditionellt slangsystem, vilket ger mer tid för exempel brandbekämpning. Slangsystem kräver mer resurser för att nå långa sträckor, exempelvis mer manskap och tryckstegringspumpar eftersom tryckförlusten överstiger tankfordonens pumpkapacitet. I fasta vattenförsörjningssystem understiger tryckförlusten pumpkapaciteten. Den lokala räddningstjänstens kapacitet och resurser måste beaktas vid utformning av brandskydd och val av vattenförsörjningssystem, samtidigt som brandtekniska installationer och åtgärder måste bland annat beaktas, för att om möjligt underlätta räddningstjänstens insatsmöjligheter. Den ekonomiska kostnaden för brandskyddet och vattenförsörjningssystemet måste också vägas mot nyttan av brandskyddsinstallationer och den utrustning som kan underlätta räddningstjänstens släck- och livräddningsinsatser. / The complex and unique design of underground facilities, as well as their location, make fire and rescue operations difficult. Even if regulations require adequate fire protection, very little guidance is given on how to achieve this, especially regarding firefighting. This can lead to disagreements between emergency services and contractors, for example on the choice of water supply system. The water supply system affects the rescuers’ moving speed and air consumption, as well as the ability to quickly initiate firefighting, but also has an important economical aspect. The purpose of this degree project is to show how different water supply systems affect the rescue services in underground facilities, with focus on the moving speeds and air consumption. This is done by using information from previously performed research projects. Furthermore, the pressure losses in different water supply systems are investigated, and water supply system are examined from an economical point of view. Some solutions of water supply systems applied in both national and international underground facilities are also presented. It appears that a fixed water supply system allows a faster moving speed in a tunnel compared with a traditional hose system, therefore leaving more time for other actions, such as firefighting. Hose systems also require more resources to reach long distances, for example booster pumps because pressure losses exceeds the fire trucks’ pump capacity. The local rescue services assets and capabilities must be taken into account when designing the fire protection. The safety equipment of an underground facility is a key component of any fire and rescue operation, and must, for example, be thoroughly analyzed and taken into consideration to facilitate the rescue services capabilities. The benefits and economic cost of each water supply system must as well be considered in the process regarding the level of fire protection and facilitating installations for the emergency services.

Increasing population, diminishing supplies and variable climatic conditions can cause difficulties in meeting water demands. When this long range water supply plan is developed to cope with future water demand changes, accuracy and reliability are the two most important factors. To develop an accurate model, the water supply system has become more complicated and comprehensive structures. Future uncertainty also has been considered to improve system reliability as well as economic feasibility.In this study, a general large-scale water supply system that is comprised of modular components was developed in a dynamic simulation environment. Several possible scenarios were simulated in a realistic hypothetical system. In addition to water balances and quality analyses, construction and operation of system components costs were estimated for each scenario. One set of results demonstrates that construction of small-cluster decentralized wastewater treatment systems could be more economical than a centralized plant when communities are spatially scattered or located in steep areas.The Shuffled Frog Leaping Algorithm (SFLA), then, is used to minimize the total system cost of the general water supply system. Decisions are comprised of sizing decisions - pipe diameter, pump design capacity and head, canal capacity, and water/wastewater treatment capabilities - and flow allocations over the water supply network. An explicit representation of energy consumption cost for the operation is incorporated into the system in the optimization process of overall system cost. Although the study water supply systems included highly nonlinear terms in the objective function and constraints, a stochastic search algorithm was applied successfully to find optimal solutions that satisfied all the constraints for the study networks.Finally, a robust optimization approach was introduced into the design process of a water supply system as a framework to consider uncertainties of the correlated future data. The approach allows for the control of the degree of conservatism which is a crucial factor for the system reliabilities and economical feasibilities. The system stability is guaranteed under the most uncertain condition and it was found that the water supply system with uncertainty can be a useful tool to assist decision makers to develop future water supply schemes.

O presente trabalho apresenta a previsão de demanda de água em sistemas urbanos de abastecimento através de Rede Neural Artificial (RNA) utilizando dados de consumo de água e variáveis meteorológicas e socioambientais. A RNA utilizada foi uma de três camadas chamada de rede de múltiplas camadas alimentadas adiante com o algoritmo de treinamento LLSSIM (Hsu et al., 1996). Neste estudo, foram utilizados os dados de consumo de água (SABESP) e meteorológicos (IAG/USP) para o período de 2001 a 2005 para Região Metropolitana de São Paulo (RMSP). As variáveis socioambientais e meteorológicas que podem afetar o consumo de água foram analisadas. A ETA Cantareira e o setor Itaim Paulista foram utilizados para avaliar a relação entre o consumo e as variáveis antrópicas e meteorológicas para o ano de 2005. Esses conjuntos de dados foram utilizados para o treinamento, o teste e a previsão da RNA. Para a ETA Cantareira, foram criados 8 modelos e para o setor Itaim Paulista 57, sendo que os modelos 9 a 57 correspondem à previsão ideal. O desempenho dos modelos foi avaliado pelo o erro médio, erro médio absoluto, erro médio quadrático, o coeficiente de correlação, exatidão, viés, POD, FAR, CSI e POFD. Para a ETA Cantareira o melhor desempenho ocorreu para a média de 12 horas e para o Itaim Paulista a média de 6 horas. Na previsão ideal observou-se que a memória do sistema é um fator importante, principalmente quando se tem dois intervalos de tempo anterior. Os resultados mostraram a importância da memória, pois ela ajuda a melhorar o desempenho da previsão A previsão horária foi obtida com níveis de erros aceitáveis. Comparando os resultados de todas as configurações dos modelos, observou-se que há uma tendência para pequenos erros. Finalmente, conclui-se que o método proposto pode ser utilizado para previsão de consumo obtendo uma boa previsão. / This work is concerned with the prediction of water demand in urban water supply systems using water consumption, meteorological and socioenvironmental variables in an Artificial Neural Network (ANN) system. The ANN is a three layer feed-forward network with the LLSSIM training algorithm (Hsu et. al., 1996). In this study, water consumption (SABESP) and meteorological (IAG USP) data sets between 2001 and 2005 were used for studying the Metropolitan Area São Paulo (MASP). Possible socio-environmental and meteorological conditions affecting water consumption in the MASP were analyzed. Two water treatment stations (ETA), namely, Cantareira and the Itaim Paulista were used to evaluate the relationship between water consumption against anthropic and meteorological conditions for the year 2005. These data sets were also used for training, testing and forecasting of the water consumption model with the ANN. For the Cantareira ETA, 8 model configurations were tested and 57 for the Itaim Paulista ETA. In this late case, configurations 9 to 57 were for ideal forecasts. The various model configurations were evaluated by the mean error, mean absolute error and mean square root error, correlation coefficient, bias, POD, FAR, CSI e POFD. The best performance for the Cantareira ETA was obtained for a 12-hour average of the input variables, and for the Itaim Paulista ETA, for the 6-hour average. The ANN model configurations fed with variables of previous three times steps (memory) performed best, followed by two previous time steps. The results indicate the importance of these memory to improving the performance of the forecasting. The hourly forecasting was obtained with acceptable error levels. Comparing the results of all model configurations, there is an overall tendency for minor errors. The proposed method can be used to demand forecast a good prediction.

O uso do cloro como desinfetante em sistemas de água para abastecimento é prática comum nas estações de tratamento de água. Introduzido durante o processo de tratamento, o cloro participa de diversas reações com compostos de naturezas orgânicos e inorgânicos no interior das tubulações. Tais reações ocorrem na massa líquida e junto às paredes das tubulações e são responsáveis pelo decaimento do cloro ao longo das redes. Visualizando a modelagem como uma ferramenta eficiente para gerenciar o cloro residual em sistemas de distribuição de água, muitos estudos foram realizados e reportados pela literatura, assumindo que os efeitos de decaimento de cloro podem ser bem representados pelos coeficientes kb e kw. Entretanto, a determinação de valores para parâmetros em questão não é uma tarefa fácil, devido à complexidade dos sistemas enfocados em termos da diversidade de materiais das tubulações e mananciais (superficiais e subterrâneos). No Brasil, apesar de legislação recente estabelecer limites restritivos para o cloro na água potável (após desinfecção, a concentração de cloro deve observar a concentração mínima de 0,5 mg/L, sendo o mínimo nível aceito em sistemas de distribuição de 0,2 mg/L e o máximo de 2,0 mg/L), poucos estudos enfocam a avaliação dos parâmetros de decaimento. Esta pesquisa apresenta a aplicação de um modelo inverso elaborado para determinar a ordem para o modelo de decaimento do cloro e os valores globais e/ou locais para o kb e o kw. Sendo programado com o suporte do simulador de EPANET 2 (toolkit) e os algoritmos genéticos como ferramenta de otimização, implementado através da biblioteca de GAlib C++. Os estudos foram realizados em dois sistemas reais da distribuição da água em que foram considerados parâmetros globais e parâmetros específicos da qualidade. Para a investigação da determinação de parâmetros de decaimento de cloro em sistemas de distribuição com vazamento em função da pressão, foi adotada uma rede hipotética com três fontes de cloro. Esse sistema permitiu a calibração e a validação do modelo, assim como a avaliação da influência hidráulica na determinação dos resultados de qualidade de água. / The use of chlorine as disinfectant in water supply systems has been a common practice adopted by the water industry. Introduced during the treatment process, chlorine participates in several reactions with compounds of organic and inorganic nature inside the pipes. Such reactions that occur in the bulk and the wall of the pipes are responsible for chlorine decay along the networks. Visualizing the modeling as an efficient tool to manage the chlorine residual in water distribution systems, many studies have been conducted and reported by the literature, assuming that the chlorine decay effects can be well represented by the decay coefficients kb and kw. However, the determination of values for theses parameters is not an easy task, due to the complexity of the focused systems in terms of pipe materials and water supply sources diversity (surface water and groundwater). In Brazil, instead of recent legislation stating more strict limits for chlorine in drinking water (after disinfection, chlorine concentration has to observe the minimum concentration of 0.5 mg/L, being the minimum accepted level in the distribution system of 0.2 mg/L and the maximum of 2.0 mg/L), few studies focus on the evaluation of the decay parameters. This research reports the application of an inverse model built to determine the order for chlorine decay model and the global and/or local values for kb and kw. It is codified with the support of EPANET 2 (Toolkit) simulator and technology of genetic algorithms as optimization tool, which is implemented by using the GAlib C++ library. The studies were conducted on two real water distribution systems considering both global and specific quality parameters. A hypothetical network with three sources of chlorine was studied too, admitting leakage as pressure function. This system permitted both calibration and validation of the model as well as the evaluation of hydraulic calibration influence on the water quality results.

O presente trabalho tem como área de estudo o Sistema Cantareira de abastecimento de água. Considerando a importância da gestão ambiental para este sistema e a discussão sobre a problemática relacionada aos recursos hídricos, diversas alternativas foram criadas visando incentivar e orientar o gerenciamento participativo nesta área. Tais inciativas contam com instrumentos governamentais estabelecidos pela política nacional para a proteção ambiental e gestão os recursos hídricos. Como exemplos, pode-se se citar a Política Nacional de Recursos Hídricos, que instaurou os Comitês de Bacias Hidrográficas, e o Sistema Nacional das Unidades de Conservação, que fomentou a criação dos conselhos. Em especial no Sistema Cantareira foram identificados nesta pesquisa três Comitês de Bacias Hidrográficas e 5 Conselhos de Unidades de Conservação. Existe uma sobreposição destes Organismos Consultivos/Gestores na área de estudo deste trabalho. Diante desta realidade apresenta-se a governança e o diálogo de saberes como meios para a gestão no Sistema Cantareira possa ser mais articulada. A governança propõe que novos caminhos teóricos e práticos sejam apresentados e adotados visando estabelecer uma relação alternativa entre o nível governamental e a sociedade civil, o que diante de realidade do Sistema Canteira é importante e necessário. Neste contexto diversos atores com conhecimentos e experiências diversificadas precisam estar envolvidos, e o diálogo de saberes torna-se uma via para que estes conhecimentos dialoguem entre si e sejam confrontados estabelecendo o interconhecimento. Buscando verificar a existência da governança e do diálogo de saberes no Sistema Cantareira adotou-se como metodologia a pesquisa qualitativa realizada em três fases: exploratória que neste trabalho envolveu a pesquisa bibliográfica e a aplicação questionários com perguntas abertas para os representantes de todos os Organismos Consultivos/Gestores presentes no Sistema Cantareira, participaram deste levantamento 79 representantes; a fase do trabalho de campo na qual foram realizadas 18 entrevistas com representantes do Conselho da APA Fernão Dias em Minas Gerais, do Conselho Unificado Gestor Unificado das APAs Piracicaba/Juqueri-Mirim Área II, Sistema Cantareira e Represa Bairro da Usina em São Paulo e do Comitê Federal de Bacias Hidrográficas dos Rios Piracicaba, Capivari e Jundiaí; e por fim a fase de análise dos resultados possibilitou a apresentação de um mapa que demonstra a sobreposição das Unidades de Conservação e dos Comitês de Bacias Hidrográficas no Sistema Canteira e a apresentação e sistematização dos dados obtidos das fases anteriores. Por meio dos resultados obtidos foi possível verificar a necessidade de elaboração de estratégias que ampliem a participação e a mobilização social e que trabalhem o diálogo de saberes nos processos de discussão e decisórios, visando uma articulação das propostas presentes na área de estudos. A pesquisa revelou também que existe potencial para que a governança e o diálogo de saberes aconteçam, tendo em vista a existência dos fóruns de debates existentes e de instrumentos que buscam garantir a participação de diversos atores sociais nas discussões de temáticas relacionadas ao Sistema Canteira. Por fim pode-se concluir que a governança e o diálogo de saberes são importantes elementos para a gestão ambiental e dos recursos hídricos no Sistema Cantareira. / The present work has as study area the Cantareira Water Supply System. Considering the importance of environmental management for this system and the current discussion related to water resources, various alternatives were created aiming to encourage and guide a participatory management in this area. Such initiatives are related to government apparatus established by National Policies for environmental protection and management of water resources. As examples, can be mentioned the National Water Resources Policy, which established the Watershed Committees, and the National System of Protected Areas, which fostered the creation of the councils. For the Cantareira Water Supply System were identified, in this research, three Hydrographic Basin Committees and five Conservation Areas Councils. There is thus an overlap of these Advisory/Management Committees in the study area of this research. Given this reality, this research presents the governance and the dialogue of knowledge as strategies for managing the Cantareira Water Supply System in a more articulate way. The Governance proposes that new theoretical and practical ways are presented and adopted to establish an alternative relationship between government and civil society level which considering the Cantareira Water Supply System reality is important and necessary. In this context, many actors with diverse knowledge and experiences need to be involved, and the dialogue of knowledge becomes a pathway that allows discussions, confront different knowledge\'s, establishing the inter-knowledge. Seeking to verify the existence of governance and dialogue of knowledge in the Cantareira Water Supply System, a qualitative research methodology was adopted, and conducted in three phases. An exploratory work, which involved a literature research and questionnaires, with open questions, application to representatives of all Advisory/Management Committees present in the Cantareira Water Supply System. In this phase and 79 representatives participated in this survey. The phase of fieldwork in which 18 interviews were performed with representatives of the Fernão Dias EPA Council, located in Minas Gerais State, of the Unified Council of the Piracicaba/Juqueri-Mirim area II, the Cantareira System and the Usina Neighborhood EPA\'s, all located in São Paulo State and the Federal Committee of the Piracicaba, Capivari and Jundiaí River Basins. Finally, the stage of results analysis that allowed the presentation of a map that shows the overlap of Protected Areas and Watershed Committees in the Cantareira Water Supply System and presentation data obtained in previous stages. Through the results, it was possible to verify the necessity to develop strategies that enhance the participation and social mobilization and help to cultivate the dialogue of knowledge in discussions and decision-making processes, aiming an articulation of the current proposals to the study area. The survey also revealed that there is potential for governance and dialogue of knowledge to happen, given the existence of forums and instruments that seek to ensure the participation of different social actors in discussions of issues related to the Cantareira Water Supply System. Finally, it can be concluded that the governance and the dialogue of knowledge are important elements for Environmental Management and Water Resources Management in the Cantareira Water Supply System.

Submitted by Joana Azevedo (joanad@id.uff.br) on 2017-08-08T19:42:14Z No. of bitstreams: 1 Dissert Marcos Abi_Ramia Chimelli.pdf: 3115532 bytes, checksum: bfac767eeb94f694d96661c7f1948670 (MD5) / Approved for entry into archive by Biblioteca da Escola de Engenharia (bee@ndc.uff.br) on 2017-09-18T13:37:33Z (GMT) No. of bitstreams: 1 Dissert Marcos Abi_Ramia Chimelli.pdf: 3115532 bytes, checksum: bfac767eeb94f694d96661c7f1948670 (MD5) / Made available in DSpace on 2017-09-18T13:37:33Z (GMT). No. of bitstreams: 1 Dissert Marcos Abi_Ramia Chimelli.pdf: 3115532 bytes, checksum: bfac767eeb94f694d96661c7f1948670 (MD5) Previous issue date: 2016-10-20 / A água é um recurso imprescindível para a vida humana, para suas atividades econômicas, alimentação e sobrevivência. Como um dos recursos naturais de maior importância, é um dos que mais sofre com a degradação humana, tornando-se cada dia mais escasso, com redução preocupante em relação ao volume ainda potável para consumo humano. O presente trabalho tem como objetivo central, analisar o abastecimento de água na região de Itaboraí, município do Rio de Janeiro, apresentando ferramenta para redução de perdas e aumento da eficiência no sistema. Há uma demanda para que as companhias de abastecimento passem a otimizar seus sistemas, controlando os desperdícios e as perdas, podendo aumentar a eficiência do serviço, reduzir custos e otimizar receitas. Dentre as ferramentas mais utilizadas por diversas companhias de abastecimento, está a automatização do sistema, bem como o Método de Análise e Solução de Problemas de Perdas D’água e de Faturamento (MASPP), que é uma metodologia com base nos preceitos da melhoria contínua e da gestão de qualidade, que é aplicada em quase todos os grandes sistemas de abastecimento, como o da SABESP, em São Paulo e, ainda que apresentando resultados incipientes, demonstra potencial de eficiência e verdadeira redução das perdas e desperdícios. A justificativa para a escolha do tema se deu pela premência de tratar sobre a sustentabilidade dos recursos hídricos, da necessidade de se alcançar a eficiência e eficácia do atendimento à população, a melhoria de arrecadação que será revertida em melhorias na qualidade dos serviços pelas características de empresa pública, além da expectativa de contribuir para o âmbito acadêmico. O método de pesquisa empreendido segue natureza qualitativa, com pesquisa do tipo bibliográfica e exploratória. / Water is a vital resource for human life, economic activities, food and survival. As one of the natural resources of greater importance, is the one who suffers most from human degradation, becoming scarcer day with worrying reduction in relation to the volume still safe for human consumption. This study was aimed to analyze the water supply in Itaboraí region, municipality of Rio de Janeiro, presenting tool to reduce losses and increase efficiency in the system. There is a demand for the supply companies start to optimize their systems, controlling waste and losses and may increase service efficiency, reduce costs and optimize revenues. Among the tools most used by different supply companies, is the system automation, as well as the Analysis Method and Solution of Water Loss Issues and Billing (MASPP), which is a methodology based on the principles of continuous improvement and quality management, which is applied in almost all the major supply systems, such as SABESP in São Paulo and, although presenting incipient results, demonstrates efficiency potential and actual reduction of losses and waste. The rationale for the choice of subject was due to the urgency to address the sustainability of water resources, the need to achieve efficiency and effectiveness of services to the population, improvement of storage that will be reversed in improvements in the quality of services by feature public company, beyond expectation to contribute to the academic environment. The research method undertaken following qualitative nature, with the bibliographical research and exploratory.

O presente trabalho apresenta a previsão de demanda de água em sistemas urbanos de abastecimento através de Rede Neural Artificial (RNA) utilizando dados de consumo de água e variáveis meteorológicas e socioambientais. A RNA utilizada foi uma de três camadas chamada de rede de múltiplas camadas alimentadas adiante com o algoritmo de treinamento LLSSIM (Hsu et al., 1996). Neste estudo, foram utilizados os dados de consumo de água (SABESP) e meteorológicos (IAG/USP) para o período de 2001 a 2005 para Região Metropolitana de São Paulo (RMSP). As variáveis socioambientais e meteorológicas que podem afetar o consumo de água foram analisadas. A ETA Cantareira e o setor Itaim Paulista foram utilizados para avaliar a relação entre o consumo e as variáveis antrópicas e meteorológicas para o ano de 2005. Esses conjuntos de dados foram utilizados para o treinamento, o teste e a previsão da RNA. Para a ETA Cantareira, foram criados 8 modelos e para o setor Itaim Paulista 57, sendo que os modelos 9 a 57 correspondem à previsão ideal. O desempenho dos modelos foi avaliado pelo o erro médio, erro médio absoluto, erro médio quadrático, o coeficiente de correlação, exatidão, viés, POD, FAR, CSI e POFD. Para a ETA Cantareira o melhor desempenho ocorreu para a média de 12 horas e para o Itaim Paulista a média de 6 horas. Na previsão ideal observou-se que a memória do sistema é um fator importante, principalmente quando se tem dois intervalos de tempo anterior. Os resultados mostraram a importância da memória, pois ela ajuda a melhorar o desempenho da previsão A previsão horária foi obtida com níveis de erros aceitáveis. Comparando os resultados de todas as configurações dos modelos, observou-se que há uma tendência para pequenos erros. Finalmente, conclui-se que o método proposto pode ser utilizado para previsão de consumo obtendo uma boa previsão. / This work is concerned with the prediction of water demand in urban water supply systems using water consumption, meteorological and socioenvironmental variables in an Artificial Neural Network (ANN) system. The ANN is a three layer feed-forward network with the LLSSIM training algorithm (Hsu et. al., 1996). In this study, water consumption (SABESP) and meteorological (IAG USP) data sets between 2001 and 2005 were used for studying the Metropolitan Area São Paulo (MASP). Possible socio-environmental and meteorological conditions affecting water consumption in the MASP were analyzed. Two water treatment stations (ETA), namely, Cantareira and the Itaim Paulista were used to evaluate the relationship between water consumption against anthropic and meteorological conditions for the year 2005. These data sets were also used for training, testing and forecasting of the water consumption model with the ANN. For the Cantareira ETA, 8 model configurations were tested and 57 for the Itaim Paulista ETA. In this late case, configurations 9 to 57 were for ideal forecasts. The various model configurations were evaluated by the mean error, mean absolute error and mean square root error, correlation coefficient, bias, POD, FAR, CSI e POFD. The best performance for the Cantareira ETA was obtained for a 12-hour average of the input variables, and for the Itaim Paulista ETA, for the 6-hour average. The ANN model configurations fed with variables of previous three times steps (memory) performed best, followed by two previous time steps. The results indicate the importance of these memory to improving the performance of the forecasting. The hourly forecasting was obtained with acceptable error levels. Comparing the results of all model configurations, there is an overall tendency for minor errors. The proposed method can be used to demand forecast a good prediction.