Moniruzzaman (2026) Explainable Machine Learning for Assessing Urban Expansion and Flood Vulnerability: A Multi-Source Remote Sensing Assessment of Ten Global South Cities

Identification

• Journal: Mendeley Data
• Year: 2026
• Date: 2026-03-30
• Authors: Md Moniruzzaman
• DOI: 10.17632/vvy96f45dg.1

Research Groups

• Md Moniruzzaman

Short Summary

This data publication provides a multi-source remote sensing dataset, comprising 10 CSV files derived from Google Earth Engine, specifically designed to support explainable machine learning assessments of urban expansion and flood vulnerability in ten Global South cities.

Objective

• To provide a comprehensive, multi-source remote sensing dataset for assessing urban expansion and flood vulnerability using explainable machine learning techniques across ten selected Global South cities.

Study Configuration

• Spatial Scale: Ten urban areas located in the Global South.
• Temporal Scale: Not explicitly detailed in the provided text.

Methodology and Data

• Models used: Data exported from Google Earth Engine (GEE). The intended application involves Explainable Machine Learning.
• Data sources: Multi-source remote sensing data, processed and exported via Google Earth Engine (GEE).

Main Results

• The primary result is the provision of 10 CSV files, each containing remote sensing-derived data pertinent to urban expansion and flood vulnerability for one of the ten Global South cities.

Contributions

• This dataset offers a standardized, multi-source remote sensing resource specifically curated for explainable machine learning applications, enabling comparative studies on urban expansion and flood vulnerability across multiple Global South urban environments.

Funding

• Not explicitly detailed in the provided text.

Citation

@article{Moniruzzaman2026Explainable,
  author = {Moniruzzaman, Md},
  title = {Explainable Machine Learning for Assessing Urban Expansion and Flood Vulnerability: A Multi-Source Remote Sensing Assessment of Ten Global South Cities},
  journal = {Mendeley Data},
  year = {2026},
  doi = {10.17632/vvy96f45dg.1},
  url = {https://doi.org/10.17632/vvy96f45dg.1}
}