Daily Arxiv

This page organizes papers related to artificial intelligence published around the world.
This page is summarized using Google Gemini and is operated on a non-profit basis.
The copyright of the paper belongs to the author and the relevant institution. When sharing, simply cite the source.

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

Created by
  • Haebom

Author

Yadvendra Gurjar, Ruoni Wan, Ehsan Farahbakhsh, Rohitash Chandra

Outline

Fiji is undergoing rapid urbanization, leading to large-scale development projects such as housing, roads, and civil engineering projects. This study compares land use and land cover changes in the Nadi region of Fiji from 2013 to 2024, using machine learning and remote sensing frameworks. The goal is to provide technical support for land cover/land use modeling and change detection. Landsat-8 satellite imagery was used to create a training dataset for supervised learning. Unsupervised learning using Google Earth Engine and k-means clustering was used to generate land cover maps, and a convolutional neural network was used to classify land cover types in selected areas. Change detection visualizations were presented, highlighting urban changes over time.

Takeaways, Limitations

•
Takeaways:
◦
Applying machine learning and remote sensing techniques to analyze land use and land cover changes in the Nadi region of Fiji.
◦
Provides a framework for monitoring and modeling land cover/use changes.
◦
Presentation of change detection results that visually show changes according to urbanization trends.
•
Limitations:
◦
Lack of information about specific datasets, models, and accuracy evaluations.
◦
No mention of generalizability to other regions or wider time periods.
◦
Lack of discussion about the implications of the study for actual policy decisions.
👍
Made with Slashpage