https://repositorio.ifg.edu.br/handle/prefix/2156 Mon, 05 Oct 2026 05:06:23 GMT 2026-10-05T05:06:23Z https://repositorio.ifg.edu.br/handle/prefix/2763 Título: Avaliação da suscetibilidade à erosão linear e seus fatores condicionantes no cerrado goiano Autor(es): Pereira, Alessandra Cristina Primeiro Orientador: Cremon, Édipo Henrique Abstract: Gully erosion compromises ecosystems, reduces soil fertility, and affects agri-cultural productivity, in disagreement with the United Nations (UN) Sustainable Development Goals (SDGs). Gully erosion susceptibility mapping is essential for soil conservation strategies and territorial planning. This study investigates gully erosion susceptibility in the state of Goiás, employing machine learning techniques. Twenty-three variables related to erosion conditioning factors were considered, inclu-ding topographic attributes, land use and land cover, anthropogenic, geological, and hydrological factors, 11 of which were derived from the FathomDEM Digital Terrain Model (DTM). The dataset comprised 67,078 erosion samples, including gullies and ravines, which were partitioned for model training and testing. The prediction was conducted using a supervised classification approach based on the Random Forest Ranger algorithm (RF Ranger), calibrated through k-fold cross-validation (k = 10) and evaluated using the Areas Under the ROC Curve (AUC). The statistical asses-sment of the RF Ranger model indicated strong predictive performance, yielding an AUC of 0.8657. The variable importance ranking identified the Normalized Diffe-rence Vegetation Index (NDVI) as the most influential factor, followed by pasture and pasture age, reinforcing the role of vegetation alteration in erosion processes. The rainfall erosivity factor (R factor) and topographic variables related to surface roughness and terrain morphology were also relevant. The predictive map shows that areas with highest susceptibility are concentrated in drainage headwaters characterized by steep slopes and more erodible soils, whereas the lower susceptibility are associated with flat terrain and preserved vegetation. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Dissertação Wed, 11 Feb 2026 00:00:00 GMT https://repositorio.ifg.edu.br/handle/prefix/2763 2026-02-11T00:00:00Z https://repositorio.ifg.edu.br/handle/prefix/2721 Título: HospEnergy: Ferramenta Computacional para Análise Técnico-Econômica de Sistemas Fotovoltaicos com Armazenamento de Energia e Geradores a Diesel em Unidades de Saúde Autor(es): Silva, Markos Vinicius Pedroso da Primeiro Orientador: Pinheiro Neto, Daywes Abstract: The need for high reliability in the energy supply of hospital facilities, combined with cost reduction and sustainability objectives, requires robust techno-economic assessment tools for hybrid systems composed of a Grid-Connected Photovoltaic System (GCPS), Diesel Generator Set (DGS), and Battery Energy Storage System (BESS). In this context, this work presents the web-based platform HospEnergy, developed for the integrated analysis of these systems in hospitals, considering critical loads, stochastic modeling of grid outages, tariff structures for Groups A and B, and Law 14,300/2022. Through an interactive interface and remote access, the platform enables the simulation of different operational and financial scenarios, integrating the hourly energy balance among the GCPS, DGS, BESS, and the utility grid with an economic evaluation based on Net Present Value (NPV), Modified Internal Rate of Return (MIRR), and discounted Payback, including financing options. The application to a case study in a medium-sized hospital demonstrated economic feasibility in all evaluated scenarios, with positive NPV, MIRR above the minimum attractiveness rate, and reduced discounted Payback, in addition to eliminating unmet energy through the use of BESS and reducing costs via the strategic dispatch of the DGS during peak periods. Therefore, HospEnergy constitutes a decision-support tool for hospital energy planning, offering accessibility, flexibility, and practical applicability. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Dissertação Fri, 06 Mar 2026 00:00:00 GMT https://repositorio.ifg.edu.br/handle/prefix/2721 2026-03-06T00:00:00Z https://repositorio.ifg.edu.br/handle/prefix/2677 Título: Valoração multicritério e multinível com uso de geotecnologias e AHP: estudo de caso aplicado aos parques municipais de Goiânia-GO Autor(es): Silva, José Roberto da Primeiro Orientador: Santos, Alex Mota dos Abstract: The increasing Brazilian urbanization intensifies the need for maintaining and creating quality urban green spaces. This research proposes the development of a multicriteria analysis model for evaluating the quality of urban parks, using the AHP (Analytic Hierarchy Process) method as a decision support tool. The study focused on municipal parks and forests in Goiânia, capital of Goiás state, seeking to integrate multiple dimensions of quality of these spaces into a systematic and replicable methodology. The proposed model organizes evaluation parameters into two main indices: the Environmental Preservation Index (IPA), which encompasses environmental, conservation and management aspects; and the Public Attractiveness Index (IAP), which addresses infrastructure and accessibility. The research adopted a multicriteria and multilevel approach using geotechnologies for analyzing the 28 municipal parks officially listed by the city hall. Primary data collection was conducted through satellite image processing, while secondary data were obtained from competent municipal agencies. Results demonstrate significant heterogeneity in the quality of Goiânia’s municipal parks, with an average score of 4.39 points on a scale of 10. Only nine parks (32.1%) obtained scores above the general average, evidencing high variability in municipal parks performance. Hierarchical sensitivity analysis confirmed model stability, with an average coefficient of variation of 7.4%. As a technical product of the research, the ParkQualityAnalysis system was developed, a computational tool that materializes the practical application of the proposed methodology. The study concludes that the AHP method proved adequate for multicriteria evaluation of urban parks, allowing integration of quantitative and qualitativevariablesintoaconsistentmathematicalmodel.Resultsprovidetechnical support for public policies aimed at improving urban parks quality, contributing to sustainable urban planning and population quality of life. The developed methodology presents replication potential in other Brazilian cities, constituting a relevant methodological contribution to urban green spaces management. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Dissertação Thu, 10 Jul 2025 00:00:00 GMT https://repositorio.ifg.edu.br/handle/prefix/2677 2025-07-10T00:00:00Z https://repositorio.ifg.edu.br/handle/prefix/2676 Título: Inteligência artificial aplicada à previsão do potencial de geração de energia solar Autor(es): Messias, Leonardo Alves Primeiro Orientador: Gomes, Raphael de Aquino Abstract: The growing concern with environmental impacts from fossil fuel-based energy generation, coupled with the worsening of global warming, has driven e!orts toward a more sustainable energy matrix transition. In this scenario, solar energy plays a strategic role, establishing itself as one of the main renewable sources. In this context, the present work aims to model and predict the generation potential of photovoltaic systems in the state of Goiás, Brazil, using meteorological data combined with real generation records from existing photovoltaic systems, involving the development of predictive models that will be compared to consolidated approaches. Based on this approach, we seek to contribute to the advancement of planning, optimization, and energy management strategies for photovoltaic systems in a regional context, strengthening the technical-scientific understanding of the integration between meteorological variables and solar generation e"ciency. The results showed that the Random Forest (RF) model performed best in most plants, o!ering more stable predictions with 24-hour windows. RF achieved R2 values above 0.90 and the lowest mean errors (MAE and RMSE) in several plants. On the other hand, Long Short-Term Memory (LSTM) obtained good results when it had access to more historical data, especially with 48-hour windows. Even with meteorological stations located at considerable distances from the plants, ranging from 151.9 km to 4.0 km, the use of climatic variables still contributed positively to the improvement of predictions. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Dissertação Tue, 25 Mar 2025 00:00:00 GMT https://repositorio.ifg.edu.br/handle/prefix/2676 2025-03-25T00:00:00Z