RESUMO: O estudo da análise de estabilidade de talude é de suma importância para evitar futuros deslocamentos de massa ocasionando perdas de vida humana e prejuízos financeiros. O trabalho objetiva analisar a estabilidade do talude da BR 267 pelos métodos determinístico e probabilístico, comparando os resultados obtidos. Foram realizados ensaios de resistência ao cisalhamento direto, gerando dados para a realização das análises. Traçou-se a reta de envoltória de resistência e, através do programa GEOSLOPE, foram obtidos os fatores de segurança para os dois métodos. A análise estatística dos dados pelo método probabilístico das estimativas pontuais foi feita no Microsoft EXCEL. Pela análise determinística, o fator de segurança do talude está próximo do mínimo, classificando-se como estável. Porém, com a análise probabilística, a probabilidade de ruptura obtida foi não satisfatória, estando maior que a máxima permitida por norma, sendo esse método mais aplicável para o caso analisado, uma vez que considera a variabilidade dos parâmetros estatisticamente.

No abstract

Landslides cause significant human and environmental damage, as well as unpredictable damage to structures and buildings. This paper presents the development and application of a web-based system for risk management in landslide-related emergency preparedness. This system allows for easy access to information, even in hard-to-reach regions, by integrating mobile internet devices, like cell phones and tablets, with GPS systems, without requiring cartography or geoprocessing for its operation. Furthermore, in cases of imminent risk, the system can help prioritize the emergency response, so that scarce response resources can be allocated to the most vulnerable areas. A case study is carried out, demonstrating the benefits and difficulties of implementing this system for emergency response decision-making in urban scenarios with geotechnical risks.

The intense urbanization process since the 1970s, coupled with the lack of adequate housing and social policies, has led large urban centers to disordered occupations and situations of geotechnical risk. These occupations were not implemented in a technically correct manner from the point of view of civil engineering, considering landscaping, drainage and paving, as well as edification. Areas at risk are regions where it is not recommended to build houses or facilities because they are very exposed to natural disasters, such as landslides and floods. In Brazil, the main institution responsible for monitoring areas at risk is the Civil Defense. There is a large database with history of occurrences of risk areas served by the Municipal Civil Defense, in Juiz de Fora city, Minas Gerais state-Brazil, from 1996 to 2017. Some important information contained in this database are the physical aspects of the soil, such as slope, geolocation, amplitude, curvature and accumulated flow, as well as processed data from the sliding risk susceptibility methodologies. The objective of this work is to apply machine learning techniques to identify, from the mentioned database, the susceptibility to the risk of environmental disasters in regions that have not yet participated in events attended by the municipal civil defense. This database is large and unbalanced, thus it is necessary to apply data analysis methodologies so that the machine learning model can correctly identify the standards with the least human intervention. In this study, areas were classified according to risk susceptibility. After the whole process, it was possible to analyze the performance of the algorithms and select some of them, which obtained the best results, with an accuracy of around 80%.

Resumo: Desastres ambientais fazem parte da realidade dos mais diversos países. A preparação das comunidades para a prevenção e o enfrentamento dos cenários de desastres é fundamental para estruturar cidades cada vez mais resilientes. Tendo em vista que a cidade de