Full text
| |
| Author(s): |
Thaís Passos Correia
Total Authors: 1
|
| Document type: | Master's Dissertation |
| Press: | São Paulo. |
| Institution: | Universidade de São Paulo (USP). Escola Politécnica (EP/BC) |
| Defense date: | 2021-02-11 |
| Examining board members: |
Jose Alberto Quintanilha;
Amarilis Lucia Casteli Figueiredo Gallardo;
Laercio Massaru Namikawa
|
| Advisor: | Jose Alberto Quintanilha |
| Abstract | |
The brazilian economic crisis, the appropriation of the best areas of the cities by the real estate market plus the lack of urbanized areas destined for popular housing, favors that low-income citizens occupy areas devalued by the market, as environmentally fragile areas, contributing to the increase of the danger both from these places and from the people who live in them. Floods and landslides are among the most common natural disasters in Brazil, which are responsible for social, environmental and economic damage, which can result in loss of life. Geotechnologies have become an option to assist the mapping of these events and, consequently, to assist in risk prediction, vulnerability assessment and loss quantification. Big Data techniques have also stood out for their ability to integrate a large number of databases from different sources and in different formats; and it collaborates to improve decision making, useful for the prevention of environmental disasters. This study focused on the surroundings of the Caieiras and Francisco Morato stations on Line 7 - Rubi of CPTM, in which these events are frequent and can affect the circulation of trains, in addition to causing economic losses and social damage to residents and workers in the region. Two indexes were created to identify the places with the greatest interference in the occurrence of natural disasters around the railway line (IISEF) and the places that have the highest concentration of communities vulnerable to these types of events (IVSDN) using the simple arithmetic mean, outliers and main component analysis of space objects methods. This research also identified the needs and difficulties of transferring data (structured and unstructured) in GIS to a Big Data environment, using the tools of Big Data Geospatial: GeoMesa and Google Earth Engine. This master thesis contributes to a better understanding of natural disasters, especially landslides and floods, and how they affect the rail system, its passengers and residents of the region. (AU) | |
| FAPESP's process: | 18/21279-7 - Structuring geospatial information in big data for decision support |
| Grantee: | Thaís Passos Correia |
| Support Opportunities: | Scholarships in Brazil - Master |