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

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.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  2025-09-16

• Fields of study

  Computer Science, Mathematics, Engineering, Geography, Environmental Science

• Identifiers
  DOI 10.48550/arXiv.2509.13388arXiv 2509.13388
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Computing the characteristics of defects in wooden structures using image processing and CNN

  2024cited by this paper
• Dynamics of LULC Changes, LST, Vegetation Health and Climate Interactions in Wetland Buffer Zone: A Remote Sensing Perspective

  2024cited by this paper
• Remote sensing scene classification under scarcity of labelled samples - A survey of the state-of-the-arts

  2023cited by this paper
• Exploring sustainable mangrove management policy, challenges and structure: a case study of Nadi and Momi districts, Fiji Island

  2023cited by this paper
• Rapid method for yearly LULC classification using Random Forest and incorporating time-series NDVI and topography: a case study of Thanh Hoa province, Vietnam

  2022cited by this paper
• Machine learning in modelling land-use and land cover-change (LULCC): Current status, challenges and prospects.

  2022influential reference
• Design hybrid filter technique for mixed noise reduction from synthetic aperture radar imagery

  2022cited by this paper
• A Survey of Human-in-the-loop for Machine Learning

  2021cited by this paper
• Review on Convolutional Neural Networks (CNN) in vegetation remote sensing

  2021cited by this paper
• Comparison Between Random Forest and Support Vector Machine Algorithms for LULC Classification

  2021cited by this paper
• Progress and Trends in the Application of Google Earth and Google Earth Engine

  2021cited by this paper
• Google Earth Engine for geo-big data applications: A meta-analysis and systematic review

  2020cited by this paper
• Improved Mapping Results of 10 m Resolution Land Cover Classification in Guangdong, China Using Multisource Remote Sensing Data With Google Earth Engine

  2020cited by this paper
• Coastal resource management and tourism development in Fiji Islands: a conservation challenge

  2020cited by this paper
• Underwater Image Processing and Object Detection Based on Deep CNN Method

  2020cited by this paper
• Applications in Remote Sensing to Forest Ecology and Management

  2020cited by this paper
• A Review of Convolutional Neural Network Applied to Fruit Image Processing

  2020cited by this paper
• Unsupervised K-Means Clustering Algorithm

  2020cited by this paper
• Modeling flood plain wetland transformation in consequences of flow alteration in Punarbhaba river in India and Bangladesh

  2020cited by this paper
• Evaluation and comparison of eight machine learning models in land use/land cover mapping using Landsat 8 OLI: a case study of the northern region of Iran

  2019cited by this paper
• Performance of ANN, SVM and MLH techniques for land use/cover change detection at Sultan Marshes wetland, Turkey.

  2019cited by this paper
• Parameter Optimization in Convolutional Neural Networks Using Gradient Descent

  2019cited by this paper
• The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia: A Visual Analytics Approach

  2019influential reference
• Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images

  2019cited by this paper
• Novel Land Cover Change Detection Method Based on k-Means Clustering and Adaptive Majority Voting Using Bitemporal Remote Sensing Images

  2019cited by this paper
• Water-Quality Classification of Inland Lakes Using Landsat8 Images by Convolutional Neural Networks

  2019cited by this paper
• Feature Extraction using Convolution Neural Networks (CNN) and Deep Learning

  2018cited by this paper
• Fijian culture and the environment: a focus on the ecological and social interconnectedness of tourism development

  2018cited by this paper
• Google Earth Engine Applications Since Inception: Usage, Trends, and Potential

  2018cited by this paper
• Natural disasters and tourism-led economic growth: a case study of Fiji: 1980–2014

  2018cited by this paper
• Convolutional neural networks: an overview and application in radiology

  2018cited by this paper
• A new image classification method using CNN transfer learning and web data augmentation

  2018cited by this paper
• Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

  2017cited by this paper
• Developments in Landsat Land Cover Classification Methods: A Review

  2017influential reference
• A Review of Wetland Remote Sensing

  2017cited by this paper
• Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories

  2016cited by this paper
• Deep Learning

  2016cited by this paper
• Deconstructing vulnerability and adaptation in a coastal river basin ecosystem: a participatory analysis of flood risk in Nadi, Fiji Islands

  2016cited by this paper
• An Assessment of Algorithmic Parameters Affecting Image Classification Accuracy by Random Forests

  2016cited by this paper
• Does Land Lease Tenure Insecurity Cause Decreased Productivity and Investment in the Sugar Industry? Evidence from Fiji

  2016cited by this paper
• A Comparative Study on Approaches to Speckle Noise Reduction in Images

  2015cited by this paper
• Luxury tourism investment and flood risk: Case study on unsustainable development in Denarau island resort in Fiji ☆

  2015cited by this paper
• Automatic Labelling and Selection of Training Samples for High-Resolution Remote Sensing Image Classification over Urban Areas

  2015cited by this paper
• On-orbit radiometric characterization of OLI (Landsat-8) for applications in aquatic remote sensing

  2014cited by this paper
• Rainfall trends in Fiji

  2014cited by this paper
• Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers

  2014cited by this paper
• The uncertainty of biomass estimates from LiDAR and SAR across a boreal forest structure gradient

  2014cited by this paper
• The contribution of tourism to the development of Fiji and other Pacific Island countries

  2013cited by this paper
• Flood hazard modelling and risk assessment in the Nadi River Basin, Fiji, using GIS and MCDA

  2012cited by this paper
• Supervised Classification Approaches for the Development of Land-Cover Time Series

  2012cited by this paper
• Remote Sensing of Land Use and Land Cover : Principles and Applications

  2012cited by this paper
• Comparison of passive and active canopy sensors for the estimation of vine biomass production

  2010cited by this paper
• The European Land Use and Cover Area‐Frame Statistical Survey

  2010cited by this paper
• Evaluating supervised and unsupervised techniques for land cover mapping using remote sensing data

  2009cited by this paper
• The viability of Fiji's sugar industry

  2009cited by this paper
• Summary of Current Radiometric Calibration Coefficients for Landsat MSS, TM, ETM+, and EO-1 ALI Sensors

  2009cited by this paper
• Vulnerability assessment of sea-level rise in Viti Levu, Fiji Islands

  2008cited by this paper
• Using the satellite-derived NDVI to assess ecological responses to environmental change.

  2005cited by this paper
• Economic Importance of the Sugar Industry for Fiji

  2005cited by this paper
• Baseline Climatology of Viti Levu (Fiji) and Current Climatic Trends1

  2005cited by this paper
• PRINCIPLES OF REMOTE SENSING

  2005cited by this paper
• Remote sensing: land cover

  2004cited by this paper
• The global k-means clustering algorithm

  2003cited by this paper
• Use of normalized difference built-up index in automatically mapping urban areas from TM imagery

  2003cited by this paper
• Use of normalized di ff erence built-up index in automatically mapping urban areas from TM imagery

  2003cited by this paper
• Time Series Remote Sensing of Landscape-Vegetation Interactions in the Southern Great Plains

  2002cited by this paper
• Assessment of atmospheric correction methods for Landsat TM data applicable to Amazon basin LBA research

  2002cited by this paper
• Quantification of land cover change and its impact on hydro-geomorphic processes in the Upper Yangtze using multi-temporal Landsat imagery: an example of the Minjiang area

  2002cited by this paper
• ALTA OR NLTA: WHAT'S IN THE NAME? LAND TENURE DILEMMA AND THE FIJI SUGAR INDUSTRY

  2001cited by this paper
• Random Forests

  2001cited by this paper
• A review of wetlands remote sensing and defining new considerations

  2001cited by this paper
• Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences

  1998cited by this paper
• Bagging Predictors

  1996cited by this paper
• The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features

  1996cited by this paper
• A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery

  1995influential reference
• Least squares quantization in PCM

  1982cited by this paper
• Red and photographic infrared linear combinations for monitoring vegetation

  1979cited by this paper
• Land tenure in Fiji's sugar cane districts since the 1920s

  1978cited by this paper
• ISPRS Journal of Photogrammetry and Remote Sensing

  year unknowncited by this paper
• S I NDH U NIVERSITY R ESEARCH J OURNAL ( S CIENCE S ERIES ) K-Means and ISODATA Clustering Algorithms for Landcover Classification Using Remote Sensing

  year unknowncited by this paper

• No citing papers are available for this paper.