Exploring Urban Densification with Deep Learning: Integrating Remote Sensing and Electrical Infrastructure Data

EasyChair Preprint 15635

Abstract

Accelerated urban growth presents challenges for efficient city management, requiring the implementation of sustainable principles. In this scenario, the electricity sector faces significant changes with the introduction of new technologies, especially Artificial Intelligence (AI) and Deep Learning (DL), which are especially applied to urban remote sensing. This study investigates the urban growth of a Brazilian state using semantic segmentation based on Convolutional Neural Networks (CNNs) in satellite images. Two CNN architectures, LinkNet34 and DLinkNet34, were trained with RGB satellite images from Google Earth, covering geographic and environmental diversity. Both models showed similar performance, with LinkNet34 slightly superior with an accuracy of 0.8457. The segmentation analysis was correlated with electrical infrastructure data from the Distributor's Geographic Database (BDGD), with the aim of offering insights for sustainable urban development.

Keyphrases: Adensamento urbano, Infraestrutura Elétrica, Redes Neurais Convolucionais, Segmentação Semântica, Sensoriamento Remoto

@booklet{EasyChair:15635,
  author    = {Álisson de Oliveira Alves and Luisa Christina de Souza and Luiz Eduardo Nunes Cho Luck and Raniere Rodrigues Melo de Lima and Carlos Augusto Teixeira de Moura and Wesley José dos Santos Marinho and Rafael de Medeiros Mariz Capuano and Bruno Cesar Pereira da Costa and Marina de Siqueira and Arthur Diniz Flor Torquato Fernandes and Jesaias Carvalho Pereira Silva and Pablo Javier Alsina},
  title     = {Exploring Urban Densification with Deep Learning: Integrating Remote Sensing and Electrical Infrastructure Data},
  howpublished = {EasyChair Preprint 15635},
  year      = {EasyChair, 2025}}