Banca de QUALIFICAÇÃO: GUILHERME FREITAS DA SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : GUILHERME FREITAS DA SILVA
DATE: 03/11/2023
TIME: 09:00
LOCAL: PPGMEG
TITLE:

Digital soil mapping in the Guandu-Mirim River Hydrological Planning Unit and coastal basins.

KEY WORDS:

Machine-Learning, Pedometry, Predictive Models, Geotechnology

PAGES: 33
BIG AREA: Ciências Exatas e da Terra
AREA: Geociências
SUBÁREA: Geologia
SPECIALTY: Cartografia Geológica
SUMMARY:

The exponential increase in the world's population puts pressure on the productive sectors, which in turn demand an ever-increasing use of natural resources. Planning the use of these renewable and non-renewable natural resources has therefore become an essential task for the existence and maintenance of today's society. The use of geotechnologies, such as digital cartography, geographic information systems (GIS), remote sensing and geoprocessing are part of this context due to their ability to work with large volumes of data of various types and origins, as well as the wide use of computational mathematics to work with this data (Pinheiro, 2015). The integration of data from different sources in a GIS environment has great potential for various types of environmental analysis, such as diagnosing soil vulnerability, mineral prospecting, mapping risk areas and areas of contamination and aquifer recharge, as well as predictive digital mapping of soil attributes and classes (Pinheiro, 2015; Santos, et al., 2005).

The Guandu Mirim River Basin covers around 260 km² and its source is in the Serra do Mendanha, under the name of Guandu-do-Sena. It is made up of several springs and changes its name a few times until it flows into the Sepetiba Bay. The area of the coastal basins is around 210 km² and is made up of a series of small rivers and canals, which eventually flow into Sepetiba Bay (COMITÊ GUANDU, 2018). To represent the political boundaries, access routes, hydrographic regions, basins and hydrological planning units (UHP), official data made available by the Guandu River Basin Committee was used on the SIGA Web - Guandu online platform (available at: http://54.94.199.16:8080/siga-guandu/map).

 

The general aim of this study is to apply machine-learning techniques to predict the spatial variability of total sand content in the topsoil of the HPU.

 

COMMITTEE MEMBERS:
Externo à Instituição - WALDIR DE CARVALHO JUNIOR - EMBRAPA