Contemporary Urban Space Philosophy in China Using Lightweight Deep Learning Model-Under Ecological Ethics

Area of Science:

• Urban planning and ecological ethics
• Deep learning applications in environmental science

Background:

• Contemporary ecological ethics principles and characteristics are explored.
• Convolutional Neural Network (CNN) image techniques within deep learning models are analyzed.

Purpose of the Study:

• To improve ecological civilization construction and foster urban-ecology development.
• To analyze and model contemporary urban spatial characteristics using ecological ethics.
• To optimize urban spatial philosophy through deep learning.

Main Methods:

• Utilizing deep convolutional neural networks (DCNN) for spatial analysis.
• Applying ecological ethics principles to urban and rural environments.
• Comparing ecological eigenvalues across different urban and rural land uses.

Main Results:

• Rural residential areas demonstrate higher consistency with ecological ethics than urban areas.
• Farmland and forest ecological eigenvalues are approximately 8 and 6, respectively.
• Urban areas like airports (max 9) and stadiums (max 8) have limited ecologically ethical construction scope.
• Urban business districts, particularly casinos, exhibit low ecological ethics eigenvalues (max 5 and 3).

Conclusions:

• Deep convolutional neural networks (DCNN) offer a valuable tool for analyzing urban spatial characteristics based on ecological ethics.
• Findings provide references for future ecological urban planning and the integrated development of urban areas and ecology.
• Optimizing urban spatial philosophy through DCNN enhances the alignment of urban development with ecological principles.