A development in the approach of assessing the sensitivity of road networks to environmental hazards using functional machine learning algorithm and fractal methods

Hadi Nayyeri (), Lei Xu (), Atefeh Ahmadi Dehrashid () and Payam Mohammadi Khanghah
Additional contact information
Hadi Nayyeri: University of Kurdistan
Lei Xu: Zhejiang Geology and Mineral Technology Co., LTD
Atefeh Ahmadi Dehrashid: University of Kurdistan
Payam Mohammadi Khanghah: University of Kurdistan

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, 2024, vol. 26, issue 11, No 37, 28033-28061

Abstract: Abstract Natural hazards are considered one of the greatest challenges today. Preventing transformation processes that lead to risk and then, crisis need a structural-strategic approach. An approach that can identify the issues and challenges ahead in a systematic and comprehensive method by formulating an operational plan can provide resilience and reduce vulnerability of human settlements and urban infrastructures. The road networks as one of the most important urban elements having a crucial role in management of crisis during the occurrence of natural crises (such as earthquakes) aid in the transferring the injured and rescue forces. The main purpose of this study was to determine the vulnerability of urban road networks for earthquake risk with neural network and machines learning algorithms with a comparative and systematic approach. In order to identify the most accurate and efficient model, a comparative comparison between neural network model (ANN) and machine learning algorithms including ADTree and KNN was carried out. The results of the present study in evaluating the structural condition of the urban road network with Fractal Dimension on hazardous and vulnerable zones showed that these zones were of low fractal dimension, and the distribution and differentiation of roads were low, reducing the efficiency of the road network at times of crisis. Other results of the present research on the application of machine learning algorithms indicate that the accuracy of the ADTree algorithm was equal to 1. In addition, at the stage of measuring the efficiency of the model with the Classification metrics algorithm, the ADTree algorithm efficiency was equal to 1. However, the accuracy of the KNN algorithm (K-Nearest Neighbors) and the artificial neural network model in predicting the vulnerability of the internal road network was equal to 0.92% and 0.98%, respectively. Therefore, since the degree of accuracy of the ADTree algorithm was higher, it is the most accurate and efficient algorithm to predict the vulnerability of the road network at times of the occurrence of hazardous events, and it can be useful and effective in decision-making of policy makers and planners in pre-crisis management.

Keywords: Vulnerability; Crisis management; Environmental monitoring; Machine learning; Iran (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10668-023-03800-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:endesu:v:26:y:2024:i:11:d:10.1007_s10668-023-03800-1

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/10668

DOI: 10.1007/s10668-023-03800-1

Access Statistics for this article

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development is currently edited by Luc Hens

More articles in Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().