September 25, 2025Open Access

Ensemble Machine Learning And Deep Learning Framework For Flood Susceptibility Mapping In The Transboundary Rapti River Basin

View Full Paper

Ask AI

Bookmark

Authors

AKAnkur Kumar GPGovind Pandey RKRavindra Kale

Discussion

Member takes

Implication

This research demonstrates a hybrid ensemble method combining deep learning and traditional models, showing improved predictive accuracy for flood risk in transboundary areas.

Key Points

The hybrid ensemble method achieved a predictive ability score of AUC = 0.85 for flood susceptibility mapping.
With a 15–20% improvement in recall for flooded classes, this approach outperformed traditional single-model strategies.
Based on multiple data sources, it quantifies uncertainty and applies spatially blocked cross-validation for generalization.
The methodology can assist in flood risk zoning and climate adaptation in other monsoon-prone, data-scarce basins.

Cite This Study

Kumar et al. (2025) studied this question.

synapsesocial.com/papers/68d5e1ffbd7882ccb9b86497 https://doi.org/10.21203/rs.3.rs-7393798/v1

View Full Paper

Ask AI

Bookmark

Implication

This research demonstrates a hybrid ensemble method combining deep learning and traditional models, showing improved predictive accuracy for flood risk in transboundary areas.

Ensemble Machine Learning And Deep Learning Framework For Flood Susceptibility Mapping In The Transboundary Rapti River Basin

Discussion

Member takes

Implication

Key Points

Cite This Study

Ensemble Machine Learning And Deep Learning Framework For Flood Susceptibility Mapping In The Transboundary Rapti River Basin

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider