AIR QUALITY PREDICTION USING LAND USE REGRESSION MODELLING, CASE STUDY: FERRARA

Date

2024-4-26

Author

Eren, Meriç

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

82
views

91
downloads

Cite This

Air pollution is a growing global concern due to its implications for both welfare of the community's health and the condition of the surroundings. As urbanization continues to rise, the demand for effective tools to assess and manage air quality becomes increasingly critical. Land Use Regression (LUR) models have become apparent as powerful instruments in this context, offering an understanding of the variability of air pollution within urban landscapes. This study underlines the vital role played by LUR models in capturing the complexities of air quality dynamics. By integrating diverse parameters such as traffic patterns, land use characteristics, and meteorological variables, these models provide a comprehensive view of the factors influencing air pollution concentrations at a localized level. Advanced statistical techniques enhance the accuracy and reliability of LUR models, allowing for precise estimations that contribute to a more thorough comprehension of the sources and patterns of air pollution. Furthermore, the study highlights the practical implications of LUR models in facilitating targeted interventions and policy formulation. The ability to generate fine-grained, location-specific data empowers decision-makers in urban planning to implement measures that address the causes of air pollution. Final models for PM2.5 and PM10 is highly correlated and has same predictors in final models. All five models has at least one land use type and heating system predictors. Models for O3, PM2.5 and PM10 included wind speed as a predictor variable. Precipitation, elevation, population density, junctions, arteries and industrial areas are not included in any model. Validation R2 scores of final models varies between 0.89 and 0.96. This results are compared with previous studies. This, in turn, aids in the development of sustainable land use practices and effective policies to combat the negative effects of air pollution on public health. In the face of escalating urbanization, integration of LUR models into environmental management strategies becomes important. These models not only assist in creating cleaner and healthier cities but also contribute to the establishment of more livable urban environments.

Subject Keywords

Land Use Regression, Air Pollution, Geographic Information Sciences

URI

https://hdl.handle.net/11511/109820

Collections

Graduate School of Natural and Applied Sciences, Thesis