Semi-Automatic Satelliten Image Segmentation for Urban Expansion Analysis in Santa Cruz Island, Galápagos

Joan Daniel Rivas-Andrade; Paulina Vizcaino-Imacaña; Ivan Reyes-Chacón; Manuel Eugenio Morocho-Cayamcela

doi:10.2991/978-94-6239-803-0_24

<Previous Article In Volume

Next Article In Volume>

Semi-Automatic Satelliten Image Segmentation for Urban Expansion Analysis in Santa Cruz Island, Galápagos

Authors

Joan Daniel Rivas-Andrade¹, Paulina Vizcaino-Imacaña², Ivan Reyes-Chacón², Manuel Eugenio Morocho-Cayamcela¹^{, 2}^{, *}

¹School of Mathematical and Computational Sciences, DeepARC Research Group, Yachay Tech University, Had. San José s/n y Proyecto Yachay, Urcuquí, 100119, Ecuador

²Faculty of Digital Engineering and Emerging Technologies, International University of Ecuador (UIDE), Quito, 170411, Ecuador

^*Corresponding author. Email: mmorocho@yachaytech.edu.ec Email: mamorochoca@uide.edu.ec

Corresponding Author

Manuel Eugenio Morocho-Cayamcela

Available Online 16 October 2026.

DOI: 10.2991/978-94-6239-803-0_24 How to use a DOI?
Keywords: Geospatial communication; Satellite imagery; Urban expansion; Semantic segmentation; U-Net; Santa Cruz Island; Galápagos
Abstract: This paper presents a semi-automatic workflow for transforming multitemporal satellite imagery into interpretable geospatial communication outputs about urban expansion in Santa Cruz Island, Galápagos. The work is positioned as an applied communication technology because it converts visually complex remote-sensing data into binary masks, comparative maps, and quantitative indicators that can support environmental reporting, public communication, and decision-making in a sensitive island territory. Urban masks in the first iteration were produced with HSV-based segmentation, manually post-processed using a Python correction tool, and then fine-tuned over an ImageNet-pretrained EfficientNet-B0 encoder. For the rapid experiment, five image-mask pairs were selected and split into four training pairs and one validation pair. The best validation IoU: 0.6544, and F1 measure score: 0.7911 Based on the comparisons of urban pixel areas between 2013 and 2024, the predicted net increases in urban pixel area grew from a mere 5.66 million pixels to a substantial total of 14.43 million pixels, implying a relative net change of 154.76%. Results are reported as model-based pixel-area indicators because the current images are not georeferenced orthomosaics. Beyond the technical implementation, the study contributes a reproducible pipeline for visually communicating urban transformation in contexts where official spatial datasets may be limited.
Copyright: © 2026 The Author(s)
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the VI International Conference on Communication and Applied Technologies 2026 (ICOMTA 2026)
Series: Atlantis Highlights in Social Sciences, Education and Humanities
Publication Date: 16 October 2026
ISBN: 978-94-6239-803-0
ISSN: 2667-128X
DOI: 10.2991/978-94-6239-803-0_24 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Joan Daniel Rivas-Andrade
AU  - Paulina Vizcaino-Imacaña
AU  - Ivan Reyes-Chacón
AU  - Manuel Eugenio Morocho-Cayamcela
PY  - 2026
DA  - 2026/10/16
TI  - Semi-Automatic Satelliten Image Segmentation for Urban Expansion Analysis in Santa Cruz Island, Galápagos
BT  - Proceedings of the VI International Conference on Communication and Applied Technologies 2026 (ICOMTA 2026)
PB  - Atlantis Press
SP  - 257
EP  - 266
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-803-0_24
DO  - 10.2991/978-94-6239-803-0_24
ID  - Rivas-Andrade2026
ER  -

download .riscopy to clipboard