Mapping the multi-hazards risk index for coastal block of Sundarban, India using AHP and machine learning algorithms

Mandal, Pintu; Maiti, Arabinda; Paul, Sayantani; Bhattacharya, Subhasis; Sabatier, Paul

doi:10.1016/j.tcrr.2023.03.001

Cited by 9 publications

(1 citation statement)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are different methods for selecting the most vulnerable areas in the city. Researchers are investigating the use of participatory mapping and various machine learning algorithms and developing new methods based on artificial neural networks (ANNs) [8][9][10]. The use of these new methods makes it possible to supplement and confirm the results obtained with other methods, e.g., as part of a multi-criteria analysis with GIS models [10].…”

Section: Introductionmentioning

confidence: 99%

Delimitation and Prioritization of Climate-Affected Areas Using the Example of a Post-Industrial City

Bronder,

Kurianowicz,

Piasecka

et al. 2024

Sustainability

View full text Add to dashboard Cite

This study adapted and tested an approach to identifying areas that are particularly vulnerable to climate-related hazards using the example of the post-industrial city of Knurów in Poland. This study applied a multi-criteria method using the analytical hierarchy process based on GIS map data. The analysis was divided into statistical regions defined for the city. Fifteen attributes were defined for each statistical region. The applied methods provided verified spatial information related to specific climate change hazards. The results showed that the most vulnerable areas were the areas with intensive development in the city center and in the southwestern part of the city. Among the 15 attributes, the most significant were T1 (number of inhabitants in zones with a higher potential thermal risk index by statistical district) with a value of 0.163, G2 (percentage of the sum of tree-shaded areas in built-up areas within the territory of a given statistical district) with 0.143 and H3 (number of buildings in areas of drainless basins and 100-year water). This method effectively identified the most vulnerable areas. The use of such a method can help in the preparation of planning documents and urban adaptation plans by determining the thermally and hydrologically vulnerable areas with the least developed green infrastructure as an exposure-mitigating factor.

show abstract