Banca de QUALIFICAÇÃO: WESLEY JOSÉ DOS SANTOS MARINHO

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : WESLEY JOSÉ DOS SANTOS MARINHO
DATE: 30/01/2025
TIME: 15:00
LOCAL: Videoconferência na plataforma Google Meet: meet.google.com/cvf-rqca-sin
TITLE:

Detection of Erosive Processes Near Power Transmission Lines Using Machine Learning and the Universal Soil Loss Equation (USLE)

KEY WORDS:

Soil Erosion, Machine Learning, Universal Soil Loss Equation (USLE), Convolutional Neural Network (CNN), Unet, D-LinkNet, LinkNet.

PAGES: 74
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUBÁREA: Sistemas Elétricos de Potência
SUMMARY:

The research explores the detection of erosive processes through machine learning and the application of the Universal Soil Loss Equation (USLE). The central issue addressed is the identification and prevention of soil erosion, a significant environmental problem. Key objectives include implementing techniques to detect erosive processes near power transmission lines early, using the USLE as an additional validation factor. The study is motivated by the need to mitigate damage to power distribution networks caused by erosive processes and to develop effective methods for monitoring and preventing erosion.

The adopted methodology involves the use of machine learning algorithms, specifically Convolutional Neural Networks (CNN), to analyze satellite images and identify areas susceptible to erosive processes. Additionally, the USLE is applied as a tool to calculate soil loss, assisting in assessing the probability of erosion occurring in specific locations. The main contributions of the study include integrating machine learning technologies into erosion process detection and validating these techniques with the USLE, proving to be an effective tool in this context.

The results indicate the feasibility and accuracy of using machine learning for detecting erosive processes, as well as the importance of the USLE as a supplementary method. The study's conclusions highlight the practical relevance of these techniques for preserving power transmission lines and achieving more efficient monitoring of their surroundings. Future research directions include expanding the study to other regions and improving detection methodologies.

COMMITTEE MEMBERS:
Interno - 2579664 - ALLAN DE MEDEIROS MARTINS
Interno - 346287 - MANOEL FIRMINO DE MEDEIROS JUNIOR
Externa à Instituição - MARIA DE FATIMA ALVES DE MATOS - ISI
Presidente - 1242315 - PABLO JAVIER ALSINA