DSpace Coleção:https://repositorio.ufms.br/handle/123456789/682026-04-09T22:47:54Z2026-04-09T22:47:54ZDEEP LEARNING APPLICATIONS FOR BUILDING IDENTIFICATION IN THE RURAL AREA OF THE PANTANALhttps://repositorio.ufms.br/handle/123456789/139992025-12-08T14:12:44Z2025-01-01T00:00:00ZTítulo: DEEP LEARNING APPLICATIONS FOR BUILDING IDENTIFICATION IN THE RURAL AREA OF THE PANTANAL
Abstract: Environmental disasters have become increasingly intense and frequent, resulting in significant impacts on biodiversity, the environment, and the economy, often leading to loss of life. The environmental disaster can be potentiated by anthropic activities or events combined with natural events. In the Pantanal biome, one of the best-preserved biomes in Brazil, a large-scale environmental disaster occurred in 2020, resulting in the worst fires in recent history. Due to its characteristics and preservation, access in this region can be challenging, particularly with air transport and navigation. In addition, a good part of its extension comprises rural properties where the headquarters and houses are practically isolated due to the extension of the properties. Combining these factors, this study intends to detect buildings through artificial intelligence with deep learning techniques (object detection, instance segmentation, and semantic segmentation). This information has the potential to serve as a basis, a guide, or a source of data and information, especially in situations of an environmental disaster.
Keywords: environmental disasters, object detection, semantic segmentation, rescue, Pantanal, buildings.
Tipo: Tese2025-01-01T00:00:00ZMETODOLOGIA APRIMORADA DE DIMENSIONAMENTO ECONÔMICO E HIDROENERGÉTICO EM RECALQUEhttps://repositorio.ufms.br/handle/123456789/137202025-12-03T22:22:26Z2025-01-01T00:00:00ZTítulo: METODOLOGIA APRIMORADA DE DIMENSIONAMENTO ECONÔMICO E HIDROENERGÉTICO EM RECALQUE
Abstract: This work presents a methodology for the economic sizing of water pumping systems powered by electricity from the Brazilian utility grid. The methodology was implemented in the development, of computer application, named Supply, using Visual Basic language. Employing computational resources to determine solutions saves planning time, prevents quantification errors, enables simulation of various implementation and operational scenarios, and, most importantly, enhances the system modeling. The hydraulic, electrical, and economic modeling of the system was refined following a comprehensive literature review on the subject. Sizing is performed through cost analysis using the trial-and-error method, guided by the Bresse equation to determine which pipeline diameters should be tested. Continuous head loss can be calculated using either the Darcy-Weissbach equation or the Hazen-Williams equation. Localized head loss can be determined using the equivalent length method, the direct method, estimationbased on continuous head loss or may be neglected. The economic diameter for the pipeline is the one that minimizes the total annual cost, which comprises both implementation and operating expenses, with particular emphasis on the impact of electricity costs. To maximaze economic efficiency alternative sizing techniques such as the use of frequency inverters, capacitor banks, and on-grid photovoltaic systems have been proposed. After its development, the Supply software was used to test several hypotheses raised regarding the optimization of the operational regime of water pumping systems and to assess the economic feasibility of the proposed alternative techniques. The hypotheses examined included the feasibility of using a frequency inverter to select the optimal operating point, the use of a capacitor bank and an on-grid photovoltaic system to reduce operating costs, the connection of medium-voltage consumers to the low-voltage grid to lower expenses, and increasing flow rates to reduce operating time and enhance the economic efficiency of continuously operating systems. The Supply application contributed to the validation of these hypotheses, demonstrating strong operational performance. It was concluded that this tool can significantly enhance the economic efficiency of both new projects and the renovation of existing systems, assisting engineers, technicians, and academics in determining optimal solutions and promoting the rational use of resources.
Keywords: Water pumping, Design, Economic efficiency, Solar energy, Power factor, Frequency inverter.
Tipo: Tese2025-01-01T00:00:00ZDESENVOLVIMENTO E DESEMPENHO DE EICHHORNIA CRASSIPES VISANDO A APLICAÇÃO EM SOLUÇÕES BASEADAS NA NATUREZA PARA O TRATAMENTO DE ÁGUA CINZA DOMÉSTICAhttps://repositorio.ufms.br/handle/123456789/130902025-11-15T22:49:12Z2025-01-01T00:00:00ZTítulo: DESENVOLVIMENTO E DESEMPENHO DE EICHHORNIA CRASSIPES VISANDO A APLICAÇÃO EM SOLUÇÕES BASEADAS NA NATUREZA PARA O TRATAMENTO DE ÁGUA CINZA DOMÉSTICA
Abstract: The anionic surfactant linear alkylbenzene sulfonic acid (LAS) is a widely used compound that, in addition to causing environmental harm, can produce adverse health effects even at low concentrations. In this context, it is essential to seek more sustainable treatment alternatives. Nature-Based Solutions (NbS), such as constructed wetlands (CWs), green walls and green roofs, have been widely studied because they combine environmental, economic and social benefits. In these systems, plants play a central role in bioremediation, directly influencing treatment efficiency through absorption, translocation and accumulation of pollutants. Appropriate selection of plant species is therefore crucial to optimize performance, since bioaccumulation and contaminant distribution vary among different plant structures. This study evaluated the free-floating aquatic macrophyte Eichhornia crassipes (water hyacinth), well known for its invasive potential, with respect to removal of anionic surfactants present in greywater and its development under different experimental conditions. The research was conducted in two stages: in the first, the plant was cultivated in mesocosm systems filled with crushed stone to assess evapotranspiration rates and the feasibility of growth on a support medium; in the second, a hydroponic system was used to investigate the species’ efficiency in removing the anionic surfactant. The choice of E. crassipes also considered its ornamental potential, which can favor social acceptance of NbS in urban areas.The results showed that E. crassipes established in mesocosms with crushed stone and that its performance was conditioned by light and nutrient availability: under higher solar radiation (392 lx) and nutrient supplementation the plant showed superior development (mean 35 ± 23 leaves and 15 ± 14 cm height) and higher evapotranspiration rates, whereas, even without supplementation under natural environmental conditions (wind, rain and temperature variation), the species maintained satisfactory growth (mean 9.4 ± 3.7 cm height and 9 ± 5 leaves). By contrast, low solar radiation (153 lx), even with nutrient supply, resulted in desiccation of E. crassipes. Regarding removal of the anionic surfactant LAS, in the absence of E. crassipes the average removal was 44% for Fortified Tap Water (FTW¹) and 90% for Greywater (GW¹), with half-life times of 19.72 days and 1.83 days, respectively. In treatments with the plant an acceleration of removal was observed, with mean characteristic times of 5.65 days (FTW) and 0.75 days (GW), resulting in removal efficiencies of 85% (FTW) and 100% (GW). Despite high removal, the concentrations of LAS accumulated in tissues were low: roots contained 0.009 mg·g⁻¹ in FTW and 0.00 mg·g⁻¹ in GW, and aerial parts contained 0.001 mg·g⁻¹ in FTW and 0.001 mg·g⁻¹ in GW, indicating that most of the LAS removed did not remain in the biomass, which is consistent with removal by biodegradation. With these results, this study aims to contribute to the advancement of sustainable, integrated solutions capable of improving water quality and harmonizing functionality and aesthetics in the urban environment.
Tipo: Tese2025-01-01T00:00:00ZINTELIGÊNCIA ARTIFICIAL APLICADA À GOVERNANÇA AMBIENTAL: PROPOSTAS PARA O CONTROLE DA POLUIÇÃO POR MICROPLÁSTICOS NO BRASILhttps://repositorio.ufms.br/handle/123456789/130672025-11-13T19:43:15Z2025-01-01T00:00:00ZTítulo: INTELIGÊNCIA ARTIFICIAL APLICADA À GOVERNANÇA AMBIENTAL: PROPOSTAS PARA O CONTROLE DA POLUIÇÃO POR MICROPLÁSTICOS NO BRASIL
Abstract: Microplastic pollution stands as one of the most challenging and emerging environmental threats today due to its ubiquity, persistence, and the still poorly understood effects on human health and ecosystems. In Brazil, the lack of specific public policies, institutional fragmentation, and scarcity of systematized data hinder the effectiveness of mitigation efforts. In response, this thesis proposes the enhancement of Brazilian public policies aimed at combating microplastic pollution through the application of artificial intelligence (AI)-based methodologies, with a focus on data-driven environmental governance. The research is aligned with the "Pollution Control Technologies" line of the Graduate Program in Environmental Technologies at UFMS and adopts an interdisciplinary approach integrating environmental science, data science, environmental law, and public policy.
The thesis is structured into four main chapters. The first presents an overview of the presence of microplastics in Brazilian ecosystems, identifying research gaps and future challenges. The second chapter offers a critical analysis of national public policies, comparing them with international practices and proposing AI-assisted recommendations. The third chapter describes the design, development, and validation of the GEPLA platform – Plastic Pollution Governance with AI, an intelligent decision-support system that integrates data mining, probabilistic modeling, and policy simulation. The fourth chapter proposes a Standardized Guideline for Microplastic Investigation in Brazil, based on international protocols and adapted to the national context, aiming to ensure comparability, reproducibility, and applicability of the data produced.
The main contributions of this work include: (i) a comprehensive and critical review of microplastic pollution in Brazil; (ii) an innovative AI-based environmental governance framework; and (iii) technical and institutional inputs to support the development of effective and sustainable public policies. By integrating knowledge and tools from multiple disciplines, the study demonstrates the potential of artificial intelligence as a strategic ally in addressing complex and diffuse environmental issues.
Tipo: Tese2025-01-01T00:00:00Z