What question did this study set out to answer?

The research aims to develop an efficient urban pluvial flood prediction model integrating CNNs and SHAP-driven interpretability.

Urban Pluvial Flood Modeling Integrating Two-Dimensional CNN and SHAP-Driven Interpretability

View Full Paper

Ask AI

Bookmark

The research aims to develop an efficient urban pluvial flood prediction model integrating CNNs and SHAP-driven interpretability.
Developed flood prediction model using convolutional neural networks (CNNs) for improved efficiency.
Utilized high-resolution cellular-based flood models for dataset generation through systematic sampling.
Integrated analysis of topographic features and rainfall processes for simulation.
Implemented SHAP and Group Masking Analysis (GMA) for model interpretability and variable selection.
Validated model performance against conventional cellular models across multiple storm scenarios.
The CNN model significantly reduced simulation time from minutes to seconds compared to process-based methods.
Validation showed strong agreement with traditional models in water depth predictions across six storm scenarios.
SHAP and GMA analysis indicated significant contributions from topographic features like building and digital elevation model (DEM).

Authors

No takes yet. Share an insight, caveat, or question.

Analysis reveals effective urban flood modeling with data-driven CNNs in the context of climate effects, aiding rapid assessments.

Chen et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark