Machine learning based urban sprawl assessment using integrated multi-hazard and environmental-economic impact.

Area of Science:

• Urban and Regional Planning
• Environmental Science
• Geographic Information Systems

Background:

• Urbanization driven by land development demand causes environmental issues.
• Uncontrolled urban sprawl creates an imbalance between resource supply and demand.
• Effective management strategies are needed for hazardous urban sprawl.

Purpose of the Study:

• To develop an integrated model for evaluating and prioritizing hazardous urban sprawl management.
• To create a unique urban sprawl priority index using remote sensing and machine learning.
• To identify high-priority areas for intervention in the Bandung metropolitan region.

Main Methods:

• Application of long-term remote sensing data.
• Utilizing machine learning techniques to formulate an urban sprawl priority index.
• Integrating human economic activity, environmental degradation, and multi-disaster levels into the index.

Main Results:

• The 1993-2008 period showed the highest increase in human economic activity (172,776 ha).
• The 1985-1993 period exhibited the highest environmental degradation.
• The 1993-2008 period had the highest concentration of multi-hazard locations.
• Outskirts of urban areas in West Bandung Regency, Cimahi, Bandung Regency, and East Bandung Regency were identified as highest priority.

Conclusions:

• The developed model and index provide a scientific basis for prioritizing hazardous urban sprawl management.
• High-priority regions require immediate government attention to mitigate negative impacts.
• The model supports sustainable urban development and natural resource preservation through efficient urban environment monitoring.