September 26, 2025Scientific ReportsOpen Access

Machine learning model optimization for flood susceptibility zonation over the Kosi megafan, Himalayan foreland basin, India

View Full Paper

Ask AI

Bookmark

Authors

AAAman AroraUniversité Gustave Eiffel PGPurna Durga G MPManish Kumar PandeyChandigarh University

Discussion

Member takes

Implication

This analysis assesses five advanced machine learning algorithms for flood susceptibility in the Kosi Megafan, highlighting the effectiveness of ANN-MLP and MaxEnt.

Key Points

The ANN-MLP model achieved exceptional performance, with an accuracy of 0.982 and TSS of 0.964.
MaxEnt also performed strongly, confirming its robustness in flood susceptibility assessments.
Nineteen conditioning factors, including NDVI and distance to river, were critical in determining flood susceptibility.
The flood susceptibility maps generated can significantly enhance flood risk management strategies in dynamic environments.

Cite This Study

Arora et al. (2025) studied this question.

synapsesocial.com/papers/68d6964fcefa3de5aa871415 https://doi.org/10.1038/s41598-025-07403-w

View Full Paper

Ask AI

Bookmark

Implication

This analysis assesses five advanced machine learning algorithms for flood susceptibility in the Kosi Megafan, highlighting the effectiveness of ANN-MLP and MaxEnt.

Machine learning model optimization for flood susceptibility zonation over the Kosi megafan, Himalayan foreland basin, India

Discussion

Member takes

Implication

Key Points

Cite This Study

Machine learning model optimization for flood susceptibility zonation over the Kosi megafan, Himalayan foreland basin, India

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider