Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

District Vitality Index Using Machine Learning Methods for Urban Planners

Sylvain Marcoux, Jean-Sébastien Dessureault

TL;DR

This study develops two ML-driven indices, the Current Vitality Index (CVI) and the Long-Term Vitality Index (LVI), to monitor and forecast district vitality for urban planners. It implements a full pipeline including KNN imputation, Random Forest feature importance, k-means clustering into Urban/Residential/Commercial districts, and predictions for 2026 via MLP or Linear Regression, complemented by SHAP-based explainability and interactive geospatial visualizations. Results in Shawinigan show residential areas exhibiting higher vitality, while urban and commercial zones require targeted interventions; Linear Regression provides the most accurate 2026 forecasts among the tested models. The approach offers a practical, data-driven tool for prioritizing investments and improving citizens' quality of life, while acknowledging limitations from small-city data availability and the need for richer longitudinal indicators.

Abstract

City leaders face critical decisions regarding budget allocation and investment priorities. How can they identify which city districts require revitalization? To address this challenge, a Current Vitality Index and a Long-Term Vitality Index are proposed. These indexes are based on a carefully curated set of indicators. Missing data is handled using K-Nearest Neighbors imputation, while Random Forest is employed to identify the most reliable and significant features. Additionally, k-means clustering is utilized to generate meaningful data groupings for enhanced monitoring of Long-Term Vitality. Current vitality is visualized through an interactive map, while Long-Term Vitality is tracked over 15 years with predictions made using Multilayer Perceptron or Linear Regression. The results, approved by urban planners, are already promising and helpful, with the potential for further improvement as more data becomes available. This paper proposes leveraging machine learning methods to optimize urban planning and enhance citizens' quality of life.

District Vitality Index Using Machine Learning Methods for Urban Planners

TL;DR

This study develops two ML-driven indices, the Current Vitality Index (CVI) and the Long-Term Vitality Index (LVI), to monitor and forecast district vitality for urban planners. It implements a full pipeline including KNN imputation, Random Forest feature importance, k-means clustering into Urban/Residential/Commercial districts, and predictions for 2026 via MLP or Linear Regression, complemented by SHAP-based explainability and interactive geospatial visualizations. Results in Shawinigan show residential areas exhibiting higher vitality, while urban and commercial zones require targeted interventions; Linear Regression provides the most accurate 2026 forecasts among the tested models. The approach offers a practical, data-driven tool for prioritizing investments and improving citizens' quality of life, while acknowledging limitations from small-city data availability and the need for richer longitudinal indicators.

Abstract

City leaders face critical decisions regarding budget allocation and investment priorities. How can they identify which city districts require revitalization? To address this challenge, a Current Vitality Index and a Long-Term Vitality Index are proposed. These indexes are based on a carefully curated set of indicators. Missing data is handled using K-Nearest Neighbors imputation, while Random Forest is employed to identify the most reliable and significant features. Additionally, k-means clustering is utilized to generate meaningful data groupings for enhanced monitoring of Long-Term Vitality. Current vitality is visualized through an interactive map, while Long-Term Vitality is tracked over 15 years with predictions made using Multilayer Perceptron or Linear Regression. The results, approved by urban planners, are already promising and helpful, with the potential for further improvement as more data becomes available. This paper proposes leveraging machine learning methods to optimize urban planning and enhance citizens' quality of life.

Paper Structure

This paper contains 12 sections, 2 equations, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Current Vitality Index
  5. Variable Importance in Vitality Index
  6. Long-Term Vitality Index
  7. Explainability
  8. Results
  9. Current Vitality Index
  10. Long-Term Vitality Index
  11. Discussion
  12. Conclusion

Figures (7)

  • Figure 1: Method's architecture
  • Figure 2: SHAP impact on model output magnitude
  • Figure 3: Heat Map of Current Vitality Index
  • Figure 4: Residential cluster of K-means
  • Figure 5: Clustering consistency using Silhouette score
  • ...and 2 more figures