Landcover classification and change detection using remote sensing and machine learning: a case study of Western Fiji

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gurjar, Yadvendra, Wan, Ruoni, Farahbakhsh, Ehsan, Chandra, Rohitash
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916984475615232
author Gurjar, Yadvendra
Wan, Ruoni
Farahbakhsh, Ehsan
Chandra, Rohitash
author_facet Gurjar, Yadvendra
Wan, Ruoni
Farahbakhsh, Ehsan
Chandra, Rohitash
contents As a developing country, Fiji is facing rapid urbanisation, which is visible in the massive development projects that include housing, roads, and civil works. In this study, we present machine learning and remote sensing frameworks to compare land use and land cover change from 2013 to 2024 in Nadi, Fiji. The ultimate goal of this study is to provide technical support in land cover/land use modelling and change detection. We used Landsat-8 satellite image for the study region and created our training dataset with labels for supervised machine learning. We used Google Earth Engine and unsupervised machine learning via k-means clustering to generate the land cover map. We used convolutional neural networks to classify the selected regions' land cover types. We present a visualisation of change detection, highlighting urban area changes over time to monitor changes in the map.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13388
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Landcover classification and change detection using remote sensing and machine learning: a case study of Western Fiji
Gurjar, Yadvendra
Wan, Ruoni
Farahbakhsh, Ehsan
Chandra, Rohitash
Computer Vision and Pattern Recognition
Artificial Intelligence
Applications
As a developing country, Fiji is facing rapid urbanisation, which is visible in the massive development projects that include housing, roads, and civil works. In this study, we present machine learning and remote sensing frameworks to compare land use and land cover change from 2013 to 2024 in Nadi, Fiji. The ultimate goal of this study is to provide technical support in land cover/land use modelling and change detection. We used Landsat-8 satellite image for the study region and created our training dataset with labels for supervised machine learning. We used Google Earth Engine and unsupervised machine learning via k-means clustering to generate the land cover map. We used convolutional neural networks to classify the selected regions' land cover types. We present a visualisation of change detection, highlighting urban area changes over time to monitor changes in the map.
title Landcover classification and change detection using remote sensing and machine learning: a case study of Western Fiji
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Applications
url https://arxiv.org/abs/2509.13388