Banca de QUALIFICAÇÃO: ALAN VICTOR DOS SANTOS SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : ALAN VICTOR DOS SANTOS SILVA
DATE: 30/08/2022
TIME: 09:00
LOCAL: WEB CONFERÊNCIA
TITLE:

ANALYSIS OF AREAS SUSCEPTIBLE TO FLOODING IN THE WATER BASIN OF
SÃO MIGUEL RIVER, ALAGOAS STATE, BRAZIL

KEY WORDS:

Machine Learning; Urban; Impermeability; Flow superficial.

PAGES: 42
BIG AREA: Ciências Humanas
AREA: Geografia
SUMMARY:

Human activities that generate impacts on the environment have intensified in recent decades, reaching levels that should be considered relevant modifying agents of the environment. In the watersheds of the state of Alagoas there is a strong presence of agriculture, mainly sugarcane in the wetland, which promotes changes that contribute to the occurrence of natural disasters, such as floods and mass movements. Flood events account for about 60% of natural disasters that occur in Brazil. Added to this scenario are the effects of climate change, reinforcing the processes of frequency and intensity of precipitation, which are one of the main factors that trigger extreme events. Irregular occupations are in urban areas, which are highly susceptible to disasters. Therefore, studies that seek to understand the dynamics of hydrographic basins and the influences that human intervention exerts are of paramount importance. That said, this work seeks to employ machine learning algorithms to estimate the flow of the São Miguel River, and feed the HEC-RAS hydrological model with these estimated data in order to identify the floodable areas. The mapping of use and occupation will be carried out using the Google Earth Engine (GEE) platform, which has a satellite image bank and processing capacity. The estimation for the flow data will be made through artificial neural networks (ANN) with the neuralnet package that provides the tools for the development and training of the ANN, with daily flow data entry for the period 2016-2020. Finally, the estimated data and mapping of use and occupation will be used to feed the HECRAS hydrological model, in order to map areas subject to extreme events.

BANKING MEMBERS:
Externa à Instituição - DANIELE TORRES RODRIGUES - UFPI
Interno - 1292888 - JORIO BEZERRA CABRAL JUNIOR
Presidente - 1119902 - JOSE VICENTE FERREIRA NETO
Interno - 2501620 - MELCHIOR CARLOS DO NASCIMENTO