The multi-objective spatial optimization of urban land use based on low-carbon city planning

As the spatial carrier of carbon emission from land ecosystems and human activities, land use plays an important role in representing the spatial distribution of carbon emissions and carbon sinks. The intension of CO2 emission is closely attached to the fundamental unit of urban form-land use patterns. The exploration of the low-carbon oriented spatial optimization provides new scope for solving the high carbon emission in the urban area through spatial planning. In this paper, Eindhoven in the Netherlands was selected as the case study to implement spatial optimization. A set of parameters containing the spatial attributes of buildings and vegetation were introduced to classify the land use patterns into six categories through a combined random forest algorithm and regression tree approach. The results show the geographic features of vegetation are the crucial factors for the carbon emission. The multi-objective spatial optimization model integrated carbon emission, population, and constraint conditions. It is solved with non-dominated sorting genetic algorithm-II (NSGA-II), in which each gene represents a specific type of land use category. The optimal solutions were incorporated with a regression model to analyze the impact of the variation in each land use category. Three categories were proved to be more influential on carbon emission performance. The optimized land use structure shows the potential to reduce the carbon emission and offer valuable consults to low carbon land use plan.

Automated summary

This study implemented spatial optimization in Eindhoven, Netherlands, classified land use patterns into six categories, and found that vegetation geographic features are crucial factors affecting carbon emissions. Through a multi-objective spatial optimization model, carbon emissions were successfully reduced, and the impact of different land use categories on carbon emissions was analyzed.