Machine learning for river flow modeling and flood prediction

• Grant number: 19/14011-0
• Support Opportunities: Scholarships in Brazil - Master
• Start date: August 01, 2019
• End date: July 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Mathematics - Applied Mathematics
• Principal Investigator: Mauro de Mesquita Spinola
• Grantee: Caio da Silva Azevedo
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 17/50343-2 - Institutional development plan in the area of digital transformation: advanced manufacturing and smart and sustainable cities (PDIp), AP.PDIP

Abstract

The object of the research are predictive mathematical models or prediction algorithms applied to data provided by sensor technology, radio frequency identification (RFID) and internet of things (IOT). These algorithms will be used in the monitoring of environmental variables with wireless sensor networks connected to the Internet of Things and prediction of hazards and natural disasters based on advanced tools and methods of Data Science including, but not limited to artificial neural network models and machine learning algorithms integrated with Big Data Analytics platforms.For intelligent cities, the prediction paradigm is of paramount importance because it is pointed out as the last step in its modernization whose goals, among other advances, are the control and prevention of natural disasters.Therefore, the central objective of this research is to identify the mathematical models with the best assertiveness rates and that result in early flood diagnosis.In addition, we will analyze the ways in which the data of the sensors are collected and how these data are related in order to decode the behavior of these natural phenomena as well as to identify the reasons that make a given model more assertive in relation to the too much. And, finally, to evaluate the impacts of this process of diagnostics in the so-called smart cities. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

AZEVEDO, CAIO DA SILVA; GONCALVES, RODRIGO FRANCO; GAVA, VAGNER LUIZ; SPINOLA, MAURO DE MESQUITA. A Benford's law based method for fraud detection using R Library. METHODSX, v. 8, 2021. (17/50343-2, 19/14011-0)

AZEVEDO, CAIO DA SILVA; GONCALVES, RODRIGO FRANCO; GAVA, VAGNER LUIZ; SPINOLA, MAURO DE MESQUITA. A Benford's Law based methodology for fraud detection in social welfare programs: Bolsa Familia analysis. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, v. 567, APR 1 2021. (19/14011-0, 17/50343-2)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

AZEVEDO, Caio da Silva. Use of artificial neural networks for shallow planar landslides mapping.. 2022. Master's Dissertation - Universidade de São Paulo (USP). Escola Politécnica (EP/BC) São Paulo.