Cyclone surge inundation susceptibility assessment in Bangladesh coast through geospatial techniques and machine learning algorithms: a comparative study between an island and a mangrove protected area DOI Creative Commons
Abdullah Al Mamun, Li Zhang,

Yan Xuzhe

и другие.

Frontiers in Earth Science, Год журнала: 2025, Номер 13

Опубликована: Март 18, 2025

Tropical cyclones, including surge inundation, are a joint event in the coastal regions of Bangladesh. The washes out life and property within very short period. Besides, most cases, area remains flooded for several days. Prediction inundation susceptibility due to cyclone is one key issues reducing vulnerability. Surge can be analyzed effectively through geospatial techniques various algorithms. Two techniques, such as GIS-based Analytical Hierarchy Process (AHP) multi-criteria analysis bivariate Frequency Ratio (FR) three algorithms, i.e., Artificial Neural Network (ANN), k -nearest neighbor (KNN) Random Forest (RF), were applied understand comparative level between an island, Sandwip protected by mangrove, Dacope on Bangladesh coast. A total ten criteria considered influential flooding, Elevation, Slope, Topographic Wetness Index, Drainage density, Distance from river sea, Wind flow distance, LULC, NDVI, Precipitation, Soil types. Among them, distance sea (16.34%) elevation (15.01%) found crucial analysis, according AHP expert’s opinions. Similarly, precipitation (9.88) (6.92) LULC (4.16) NDVI (4.33) highest PR values FR analysis. factor maps final ArcGIS 10.8. categorized into five classes, low, moderate, high, high. Very high was around boundary island upper portion upazila. (45.07%) (49.41%) observed KNN ANN, respectively. receiver operating characteristic (ROC) all acceptable prediction; however, possessed better consistent under curve (AUC) value than algorithms both study sites. Policymakers professionals plan manage disaster reduction activities based outcomes.

Язык: Английский

Comparing the effectiveness of landslide susceptibility mapping by using the Frequency ratio and hybrid MCDM models DOI Creative Commons
Jonmenjoy Barman, Syed Sadath Ali,

Teachersunday Nongrem

и другие.

Results in Engineering, Год журнала: 2024, Номер unknown, С. 103205 - 103205

Опубликована: Окт. 1, 2024

Язык: Английский

Процитировано

6
Cyclone surge inundation susceptibility assessment in Bangladesh coast through geospatial techniques and machine learning algorithms: a comparative study between an island and a mangrove protected area DOI Creative Commons
Abdullah Al Mamun, Li Zhang,

Yan Xuzhe

и другие.

Frontiers in Earth Science, Год журнала: 2025, Номер 13

Опубликована: Март 18, 2025

Tropical cyclones, including surge inundation, are a joint event in the coastal regions of Bangladesh. The washes out life and property within very short period. Besides, most cases, area remains flooded for several days. Prediction inundation susceptibility due to cyclone is one key issues reducing vulnerability. Surge can be analyzed effectively through geospatial techniques various algorithms. Two techniques, such as GIS-based Analytical Hierarchy Process (AHP) multi-criteria analysis bivariate Frequency Ratio (FR) three algorithms, i.e., Artificial Neural Network (ANN), k -nearest neighbor (KNN) Random Forest (RF), were applied understand comparative level between an island, Sandwip protected by mangrove, Dacope on Bangladesh coast. A total ten criteria considered influential flooding, Elevation, Slope, Topographic Wetness Index, Drainage density, Distance from river sea, Wind flow distance, LULC, NDVI, Precipitation, Soil types. Among them, distance sea (16.34%) elevation (15.01%) found crucial analysis, according AHP expert’s opinions. Similarly, precipitation (9.88) (6.92) LULC (4.16) NDVI (4.33) highest PR values FR analysis. factor maps final ArcGIS 10.8. categorized into five classes, low, moderate, high, high. Very high was around boundary island upper portion upazila. (45.07%) (49.41%) observed KNN ANN, respectively. receiver operating characteristic (ROC) all acceptable prediction; however, possessed better consistent under curve (AUC) value than algorithms both study sites. Policymakers professionals plan manage disaster reduction activities based outcomes.

Язык: Английский

Процитировано

0