Development of a new integrated flood resilience model using machine learning with GIS-based multi-criteria decision analysis

Hussain, Muhammad; Tayyab, Muhammad; Ullah, Kashif; Ullah, Safi; Rahman, Zahid Ur; Zhang, Jiquan; Al-Shaibah, Bazel

doi:10.1016/j.uclim.2023.101589

Cited by 15 publications

(2 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These events may disrupt the normal operation of transportation systems and, in severe cases, impede emergency rescue operations and other critical city functions, profoundly affecting economic activities and residents' well-being [6][7][8]. As a vital transportation hub and industrial center in Northeast Asia, Changchun's development and the well-being of its residents are heavily reliant on the resilience of its transportation infrastructure [9,10]. In the face of this challenge, scientifically assessing and improving the resilience of urban transportation infrastructures under extreme rainfall conditions is not only crucial for ensuring the stability of urban transportation operations, but also important for enhancing the overall resilience of cities to extreme rainfall events [11,12].…”

Section: Introductionmentioning

confidence: 99%

Resilience Assessment and Enhancement Strategies for Urban Transportation Infrastructure to Cope with Extreme Rainfalls

Lang,

Wan,

Zhang

et al. 2024

Sustainability

Self Cite

View full text Add to dashboard Cite

As climate change intensifies, urban transportation infrastructure faces unprecedented challenges from extreme weather events, such as floods. This study investigates the resilience and vulnerability of such infrastructure under extreme rainfall conditions in Changchun City. Utilizing Multi-Criteria Decision-Making Analysis (MCDM) and Geographic Information System (GIS) techniques, we comprehensively assess the physical, functional, and service vulnerabilities of the transportation network. Our analysis reveals that only 3.57% of the area is classified as highly resilient, demonstrating effective flood management capabilities. In contrast, a significant 61.73% of the area exhibits very low resilience, highlighting substantial vulnerabilities that could impact urban operations. Based on our findings, we propose specific strategies to enhance resilience, including optimizing drainage systems, upgrading infrastructure standards, implementing green infrastructure initiatives, and integrating disaster risk factors into urban planning. These strategies and insights provide valuable references for global cities facing similar climatic challenges.

show abstract

Section: Introductionmentioning

confidence: 99%

Resilience Assessment and Enhancement Strategies for Urban Transportation Infrastructure to Cope with Extreme Rainfalls

Lang,

Wan,

Zhang

et al. 2024

Sustainability

Self Cite

View full text Add to dashboard Cite

show abstract

“…Consequently, flood susceptibility maps are drawn that greatly assist in flood mitigation and planning by providing regional planners and decision-makers with a better understanding of flood attributes thus, ensuring a sustainable and safe future (Youssef et al, 2016;Mahmood and Rahman, 2019;Hussain et al, 2021). Identifying flood-prone locations and mapping the flood hazard areas is key to its management and/or timely prevention (Hussain et al, 2023b). Alternatively, selecting areas that have less exposure to flooding may be an indication of ideal regions for residency and operation development (Hizbaron et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

GIS-based flood susceptibility mapping using bivariate statistical model in Swat River Basin, Eastern Hindukush region, Pakistan

Rahman

Ullah²,

Bai

et al. 2023

Front. Environ. Sci.

Self Cite

View full text Add to dashboard Cite

Frequent flooding can greatly jeopardize local people’s lives, properties, agriculture, economy, etc. The Swat River Basin (SRB), in the eastern Hindukush region of Pakistan, is a major flood-prone basin with a long history of devastating floods and substantial socioeconomic and physical damages. Here we produced a flood susceptibility map of the SRB, using the frequency ratio (FR) bivariate statistical model. A database was created that comprised flood inventory as a dependent variable and causative factors of the flood (slope, elevation, curvature, drainage density, topographic wetness index, stream power index, land use land cover, normalized difference vegetation index, and rainfall) as independent variables and the association between them were quantified. Data were collected using remote sensing sources, field surveys, and available literature, and all the studied variables were resampled to 30 m resolution and spatially distributed. The results show that about 26% of areas are very high and highly susceptible to flooding, 19% are moderate, whereas 55% are low and very low susceptible to flood in the SRB. Overall, the southern areas of the SRB were highly susceptible compared to their northern counterparts, while slope, elevation, and curvature were vital factors in flood susceptibility. Our model’s success and prediction rates were 91.6% and 90.3%, respectively, based on the ROC (receiver operating characteristic) curve. The findings of this study will lead to better management and control of flood risk in the SRB region. The study’s findings can assist the decision-makers to make appropriate sustainable management strategies for the mitigation of future damage in the study region.

show abstract

One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam

Hoa,

Binh,

Hong

et al. 2024

Earth Sci Inform

View full text Add to dashboard Cite

Flash floods rank among the most catastrophic natural disasters worldwide, inflicting severe socio-economic, environmental, and human impacts. Consequently, accurately identifying areas at potential risk is of paramount importance. This study investigates the efficacy of Deep 1D-Convolutional Neural Networks (Deep 1D-CNN) in spatially predicting flash floods, with a specific focus on the frequent tropical cyclone-induced flash floods in Thanh Hoa province, North Central Vietnam. The Deep 1D-CNN was structured with four convolutional layers, two pooling layers, one flattened layer, and two fully connected layers, employing the ADAM algorithm for optimization and Mean Squared Error (MSE) for loss calculation. A geodatabase containing 2540 flash flood locations and 12 influencing factors was compiled using multi-source geospatial data. The database was used to train and check the model. The results indicate that the Deep 1D-CNN model achieved high predictive accuracy (90.2%), along with a Kappa value of 0.804 and an AUC (Area Under the Curve) of 0.969, surpassing the benchmark models such as SVM (Support Vector Machine) and LR (Logistic Regression). The study concludes that the Deep 1D-CNN model is a highly effective tool for modeling flash floods.

show abstract

Development of a new integrated flood resilience model using machine learning with GIS-based multi-criteria decision analysis

Cited by 15 publications

References 72 publications

Resilience Assessment and Enhancement Strategies for Urban Transportation Infrastructure to Cope with Extreme Rainfalls

Resilience Assessment and Enhancement Strategies for Urban Transportation Infrastructure to Cope with Extreme Rainfalls

GIS-based flood susceptibility mapping using bivariate statistical model in Swat River Basin, Eastern Hindukush region, Pakistan

One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam

Contact Info

Product

Resources

About