Assessing and predicting green gentrification susceptibility using an integrated machine learning approach DOI
Rayan H. Assaad, Yasser Jezzini

Local Environment, Journal Year: 2024, Volume and Issue: 29(8), P. 1099 - 1127

Published: May 14, 2024

Greenery initiatives, such as green infrastructures (GIs), create sustainable and climate-resilient environments. However, they can also have unintended consequences, displacement gentrification in low-income areas. This paper proposes an integrated machine learning (ML) approach that combines both unsupervised supervised ML algorithms. First, 35 indicators contribute to were identified categorised into 7 categories: social, economic, demographic, housing, household, amenities, GIs. Second, data was collected for all census tracts New York City. Third, the susceptibility modelled 6 levels using k-means clustering analysis, which is model. Fourth, Technique Order of Preference by Similarity Ideal Solution (TOPSIS) used map their level. Finally, different algorithms trained tested predict susceptibility. The results showed artificial neural network (ANN) model most accurate classifying predicting with overall accuracy 96%. Moreover, outcomes Normal Difference Vegetation Index (NDVI), proximity GIs, GIs frequency, total area important Ultimately, proposed allows practitioners researchers perform micro-level (i.e. on census-tracts level) predictions inferences about more focused targeted mitigation actions be designed implemented affected communities, thus promoting environmental justice.

Language: Английский

Application of a fuzzy, indicator‐based methodology for investigating the functional vulnerability of critical infrastructures to flood hazards DOI Creative Commons
Negin Binesh, Giuseppe Tito Aronica, Emina Hadžić

et al.

Journal of Flood Risk Management, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Abstract Hazard vulnerability assessment of critical infrastructures (CIs) is crucial for ranking based on their level criticality, enabling the urban managers to prioritize CIs allocating funds in hazard mitigation/recovery process. This study aims provide a framework rapid and preliminary flood by introducing methodology classifying according riverine flooding. An indicator‐based curve calculated both quantitatively (using Fuzzy Logic Toolbox MATLAB) qualitatively susceptibility–exposure matrix), which prioritization accomplished with focus functional considering structural/nonstructural damages. Besides, this addresses consequences that damaged infrastructure may have rest estimates given additive impact surrounding failed interdependence. The was applied Berat (Albania) Sarajevo (Bosnia‐Herzegovina) findings compared those multi‐criteria decision‐making‐based approach commonly used CI literature. obtained results from methods represent roads are most vulnerable studied case Berat, while regarding city Sarajevo, road considered least floods bridges schools.

Language: Английский

Citations

0
Developing a Quantitative Modeling Framework for Risk Propagation Analysis: Application to Preconstruction Delays DOI

Ghadi Charbel,

Rayan H. Assaad,

Tulio Rodriguez Tejada

et al.

ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part A Civil Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: Feb. 11, 2025

Language: Английский

Citations

0
Modeling the Interdependencies between the Risk Factors Contributing to Preconstruction Delays in Construction Projects DOI

Ghadi Charbel,

Rayan H. Assaad,

Tulio Rodriguez Tejada

et al.

Journal of Construction Engineering and Management, Journal Year: 2025, Volume and Issue: 151(4)

Published: Feb. 14, 2025

Language: Английский

Citations

0
Assessing and predicting green gentrification susceptibility using an integrated machine learning approach DOI
Rayan H. Assaad, Yasser Jezzini

Local Environment, Journal Year: 2024, Volume and Issue: 29(8), P. 1099 - 1127

Published: May 14, 2024

Greenery initiatives, such as green infrastructures (GIs), create sustainable and climate-resilient environments. However, they can also have unintended consequences, displacement gentrification in low-income areas. This paper proposes an integrated machine learning (ML) approach that combines both unsupervised supervised ML algorithms. First, 35 indicators contribute to were identified categorised into 7 categories: social, economic, demographic, housing, household, amenities, GIs. Second, data was collected for all census tracts New York City. Third, the susceptibility modelled 6 levels using k-means clustering analysis, which is model. Fourth, Technique Order of Preference by Similarity Ideal Solution (TOPSIS) used map their level. Finally, different algorithms trained tested predict susceptibility. The results showed artificial neural network (ANN) model most accurate classifying predicting with overall accuracy 96%. Moreover, outcomes Normal Difference Vegetation Index (NDVI), proximity GIs, GIs frequency, total area important Ultimately, proposed allows practitioners researchers perform micro-level (i.e. on census-tracts level) predictions inferences about more focused targeted mitigation actions be designed implemented affected communities, thus promoting environmental justice.

Language: Английский

Citations

3