Urban flood vulnerability assessment in a densely urbanized city using multi-factor analysis and machine learning algorithms

Parvin, Farhana; Ali, Sk Ajim; Całka, Beata; Bielecka, Elżbieta; Linh, Nguyễn Thị Thùy; Pham, Quoc Bao

doi:10.1007/s00704-022-04068-7

Cited by 27 publications

(13 citation statements)

References 142 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A post-analysis of computed results was carried out using an artificial neural network (ANN). ANN is a machine learning method that stands more independent in comparison than statistical methods (Ludin et al 2018;Parvin et al 2022). Several studies have used ANN to predict specific events (Mwale 2014).…”

Section: Discussionmentioning

confidence: 99%

“…Due to its predictive ability, this method was applied in this study as a post-analysis to predict the causes of flood vulnerability of the variables which were statistically tested using a combined P value package between UVFs and VCs. ANN comprises several nodes and interconnected programming elements (Mwale 2014;Parvin, et al 2022). It contains input layers, hidden layers and output layers (Ahmadi 2015) (Fig.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Flood vulnerability assessment in rural and urban informal settlements: case study of Karonga District and Lilongwe City in Malawi

Mwalwimba,

Manda,

Ngongondo

2024

Nat Hazards

View full text Add to dashboard Cite

Flood vulnerability assessment (FVA) informs the disaster risk reduction and preparedness process in both rural and urban areas. However, many flood-vulnerable regions like Malawi still lack FVA supporting frameworks in all phases (pre-trans-post disaster). Partly, this is attributed to lack of the evidence-based studies to inform the processes. This study was therefore aimed at assessing households’ flood vulnerability (HFV) in rural and urban informal areas of Malawi, using case studies of Traditional Authority (T/A) Kilupula of Karonga District (KD) and Mtandire Ward in Lilongwe City (LC). A household survey was used to collect data from a sample of 545 household participants. Vulnerability was explored through a combination of underlying vulnerability factors (UVFs)-physical-social-economic-environmental and cultural with vulnerability components (VCs)-exposure-susceptibility and resilience. The UVFs and VCs were agglomerated using binomial multiple logit regression model. Variance inflation factor (VIF) was used to check the multicollinearity of variables in the regression model. HFV was determined based on the flood vulnerability index (FVI). The data were analysed using Multiple Correspondence Analysis (MCA), artificial neural network (ANN) and STATA. The results reveal a total average score of high vulnerability (0.62) and moderate vulnerability (0.52) on MCA in T/A Kilupula of Karonga District and Mtandire Ward of Lilongwe City respectively. The FVI revealed very high vulnerability on enviroexposure factors (EEFs) ($$0.9$$ 0.9 ) in LC and$$(0.8$$ ( 0.8 ) in KD, followed by ecoresilience factors (ERFs) (0.8) in KD and$$(0.6$$ ( 0.6 ) in LC and physioexposure factors (PEFs) ($$0.5)$$ 0.5 ) in LC besides 0.6 in KD for the combined UVFs and VCs. The study concludes that the determinants of households’ flood vulnerability are place settlement, low-risk knowledge, communication accessibility, lack of early warning systems, and limited access to income of household heads. The study recommends that an FVA framework should be applied to strengthen the political, legal, social, and economic responsibilities of government for building the resilience of communities and supporting planning and decision-making processes in flood risk management.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Flood vulnerability assessment in rural and urban informal settlements: case study of Karonga District and Lilongwe City in Malawi

Mwalwimba,

Manda,

Ngongondo

2024

Nat Hazards

View full text Add to dashboard Cite

show abstract

“…A post analysis of computed results was carried using artificial neural network (ANN). ANN is a machine learning method that stands more independent in comparison than statistical methods (Ludin et al, 2018;Parvin et al, 2022). Several studies have used ANN to predict specific events (Abaryhouei et al 2013;Mwale 2014;Ray et al 2020).…”

Section: Discussionmentioning

confidence: 99%

“…Due to its predictive ability, this method was applied in this study as a post analysis to predict the causes of flood vulnerability of the variables which were statistically tested using combined Pvalue package between UVFs and VCs. ANN comprises several nodes and interconnected programming elements (Mwale, 2014;Parvin, et al 2022). It contains input layers, hidden layers and output layers (Ahmadi, 2015) (Figure 2).…”

Section: Discussionmentioning

confidence: 99%

“…FVA is an impetus in which science may help to build resilient society (Ran et al, 2018;Birkmann et al, 2013). In addition, FVA provides of metrics that can support decision-making process and policy interventions (Mwale et al, 2015;Ndanusa et al, 2014) and is a proactive task for pre-hazard management and planning activities (Parvin et al 2022). Nazir et al (2013) argues that FVA provides an association between theoretical conceptions of flood vulnerability and daily administrative process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Flood Vulnerability Assessment in Rural and Urban Informal Settlements: Case Study of Karonga District and Lilongwe City in Malawi

Mwalwimba,

Manda,

Ngongondo

2023

Preprint

View full text Add to dashboard Cite

Flood vulnerability assessment (FVA) informs the disaster risk reduction and preparedness process in both rural and urban areas. However, many floods vulnerable regions like Malawi still lack FVA supporting frameworks in all phases (pre-trans-post disaster). Partly, this is attributed to lack of the evidence-based studies to inform the processes. This study was therefore aimed at assessing households’ flood vulnerability (HFV) in rural and urban areas of Malawi, using case studies of Mtandire Ward in Lilongwe City (LC) and Traditional Authority (T/A) Kilupula of Karonga District (KD). A household survey was used to collect data from a sample of 545 households’ participants. Vulnerability was explored through a combination of underlying vulnerability factors (UVFs)-physical-social-economic-environmental and cultural with vulnerability components (VCs)-exposure-susceptibility and resilience. The UVFs and VCs were agglomerated using binomial multiple logit regression model. Variance independent factor (VIF) was used to check multicollinearity of variables in the regression model. HFV was determined based on flood vulnerability index (FVI). The data were analysed using Multiple Correspondence Analysis (MCA), artificial neural network (ANN) and STATA. The results reveal a total average score of high vulnerability (0.62) and moderate vulnerability (0.52) on MCA in T/A Kilupula and Mtandire Ward respectively. The results further found low vulnerability to very high vulnerability for the combined UVFs and VCs in the FVI scale range. The study concludes that the determinants of households’ flood vulnerability are in respective order of enviro-exposure, eco-resilience and physio-exposure factors in both study areas. The study recommends that a FVA framework should be applied to promote resilience of communities to mitigate flood risks and support planning and decision-making process in flood risk management.

show abstract

GIS-Based Disaster Risk Analysis of Floods Using Certainty Factor (CF) and Its Ensemble with Deep Learning Neural Network (DLNN): A Case Study of Dima Hasao District of Assam, India

2023

View full text Add to dashboard Cite

Urban flood vulnerability assessment in a densely urbanized city using multi-factor analysis and machine learning algorithms

Cited by 27 publications

References 142 publications

Flood vulnerability assessment in rural and urban informal settlements: case study of Karonga District and Lilongwe City in Malawi

Flood vulnerability assessment in rural and urban informal settlements: case study of Karonga District and Lilongwe City in Malawi

Flood Vulnerability Assessment in Rural and Urban Informal Settlements: Case Study of Karonga District and Lilongwe City in Malawi

GIS-Based Disaster Risk Analysis of Floods Using Certainty Factor (CF) and Its Ensemble with Deep Learning Neural Network (DLNN): A Case Study of Dima Hasao District of Assam, India

Contact Info

Product

Resources

About