Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Applying Machine Learning Tools for Urban Resilience Against Floods

Mahla Ardebili Pour, Mohammad B. Ghiasi, Ali Karkehabadi

TL;DR

This work tackles flood resilience in Tehran by selecting the Climate Disaster Resilience Index (CDRI) as the baseline framework and enhancing it with temporal data and machine learning to produce a dynamic resilience assessment for 2025. It combines a literature-backed framework choice, GIS-informed reservoir siting considerations, and expert-driven, multi-dimensional data across 2013–2022 to forecast resilience with six ML techniques (including LSTM and VAR) across five dimensions. The results reveal temporal fluctuations—most notably a 2019 dip in economic and health resilience due to pandemic and inflation—demonstrating the value of a Temporal CDRI for proactive urban planning and flood risk management. Overall, the study provides a data-driven, temporally adaptive approach to urban resilience in a high-stakes district, offering actionable insights for policymakers and planners.

Abstract

Floods are among the most prevalent and destructive natural disasters, often leading to severe social and economic impacts in urban areas due to the high concentration of assets and population density. In Iran, particularly in Tehran, recurring flood events underscore the urgent need for robust urban resilience strategies. This paper explores flood resilience models to identify the most effective approach for District 6 in Tehran. Through an extensive literature review, various resilience models were analyzed, with the Climate Disaster Resilience Index (CDRI) emerging as the most suitable model for this district due to its comprehensive resilience dimensions: Physical, Social, Economic, Organizational, and Natural Health resilience. Although the CDRI model provides a structured approach to resilience measurement, it remains a static model focused on spatial characteristics and lacks temporal adaptability. An extensive literature review enhances the CDRI model by integrating data from 2013 to 2022 in three-year intervals and applying machine learning techniques to predict resilience dimensions for 2025. This integration enables a dynamic resilience model that can accommodate temporal changes, providing a more adaptable and data driven foundation for urban flood resilience planning. By employing artificial intelligence to reflect evolving urban conditions, this model offers valuable insights for policymakers and urban planners to enhance flood resilience in Tehrans critical District 6.

Applying Machine Learning Tools for Urban Resilience Against Floods

TL;DR

This work tackles flood resilience in Tehran by selecting the Climate Disaster Resilience Index (CDRI) as the baseline framework and enhancing it with temporal data and machine learning to produce a dynamic resilience assessment for 2025. It combines a literature-backed framework choice, GIS-informed reservoir siting considerations, and expert-driven, multi-dimensional data across 2013–2022 to forecast resilience with six ML techniques (including LSTM and VAR) across five dimensions. The results reveal temporal fluctuations—most notably a 2019 dip in economic and health resilience due to pandemic and inflation—demonstrating the value of a Temporal CDRI for proactive urban planning and flood risk management. Overall, the study provides a data-driven, temporally adaptive approach to urban resilience in a high-stakes district, offering actionable insights for policymakers and planners.

Abstract

Floods are among the most prevalent and destructive natural disasters, often leading to severe social and economic impacts in urban areas due to the high concentration of assets and population density. In Iran, particularly in Tehran, recurring flood events underscore the urgent need for robust urban resilience strategies. This paper explores flood resilience models to identify the most effective approach for District 6 in Tehran. Through an extensive literature review, various resilience models were analyzed, with the Climate Disaster Resilience Index (CDRI) emerging as the most suitable model for this district due to its comprehensive resilience dimensions: Physical, Social, Economic, Organizational, and Natural Health resilience. Although the CDRI model provides a structured approach to resilience measurement, it remains a static model focused on spatial characteristics and lacks temporal adaptability. An extensive literature review enhances the CDRI model by integrating data from 2013 to 2022 in three-year intervals and applying machine learning techniques to predict resilience dimensions for 2025. This integration enables a dynamic resilience model that can accommodate temporal changes, providing a more adaptable and data driven foundation for urban flood resilience planning. By employing artificial intelligence to reflect evolving urban conditions, this model offers valuable insights for policymakers and urban planners to enhance flood resilience in Tehrans critical District 6.

Paper Structure

This paper contains 10 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Materials and Methods
  4. Methodology
  5. Predicting Urban Resilience Features for 2025 by Using Machine Learning Models
  6. Data Collection and Structure
  7. Results
  8. Prediction Results for 2022 based on Machine Learning
  9. Model Performance Visualization
  10. Conclusion

Figures (4)

  • Figure 1: a) Iran, b) Tehran, c) Region 6 of Tehran
  • Figure 2: Illustrates scores across multiple dimensions over the assessment 2013 year
  • Figure 3: Depicts the reduction in loss during the LSTM model's training process, demonstrating how accuracy improves over time.
  • Figure 4: Visualizes the predicted resilience scores for each model, highlighting differences in forecasts for each resilience feature dimension.