Pierre Jehel

Vemula Sreenath, Filippo Gatti, Pierre Jehel

Ground motion models (GMMs) are critical for seismic risk mitigation and infrastructure design. Machine learning (ML) is increasingly applied to GMM development due to expanding strong motion databases. However, existing ML-based GMMs operate as 'black boxes,' creating opacity that undermines confidence in engineering decisions. Moreover, seismic datasets exhibit severe imbalance, with scarce large-magnitude near-field records causing systematic underprediction of critical high-hazard ground motions. Despite these limitations, research addressing both interpretability and data imbalance remains limited. This study develops an inherently interpretable neural network employing independent additive pathways with novel HazBinLoss and concurvity regularization. HazBinLoss integrates physics-constrained weighting with inverse bin count scaling to address underfitting in sparse, high-hazard regions. Concurvity regularization enforces pathway orthogonality, reducing inter-pathway correlation. The model achieves robust performance: mean squared error = 0.6235, mean absolute error = 0.6230, and coefficient of determination = 88.48%. Pathway scaling corroborates established seismological behaviors. Weighted hierarchical Student-t mixed-effects analysis demonstrates unbiased residuals with physically consistent variance partitioning: sigma components range from 0.26-0.38 (inter-event), 0.12-0.41 (inter-region), 0.58-0.71 (intra-event), and 0.68-0.89 (total). The lower inter-event and higher intra-event components have implications for non-ergodic hazard analysis. Predictions exhibit strong agreement with NGA-West2 GMMs across diverse conditions. This interpretable framework advances GMMs, establishing a transparent, physics-consistent foundation for seismic hazard and risk assessment.

Sreenath Vemula, Filippo Gatti, Pierre Jehel

Increasing flood frequency and severity due to climate change threatens infrastructure and demands improved susceptibility mapping techniques. While traditional machine learning (ML) approaches are widely used, they struggle to capture spatial dependencies and poor boundary delineation between susceptibility classes. This study introduces the first application of a graph transformer (GT) architecture for flood susceptibility mapping to the flood-prone French Riviera (e.g., 2020 Storm Alex) using topography, hydrology, geography, and environmental data. GT incorporates watershed topology using Laplacian positional encoders (PEs) and attention mechanisms. The developed GT model has an AUC-ROC (0.9739), slightly lower than XGBoost (0.9853). However, the GT model demonstrated better clustering and delineation with a higher Moran's I value (0.6119) compared to the random forest (0.5775) and XGBoost (0.5311) with p-value lower than 0.0001. Feature importance revealed a striking consistency across models, with elevation, slope, distance to channel, and convergence index being the critical factors. Dimensionality reduction on Laplacian PEs revealed partial clusters, indicating they could capture spatial information; however, their importance was lower than flood factors. Since climate and land use changes aggravate flood risk, susceptibility maps are developed for the 2050 year under different Representative Concentration Pathways (RCPs) and railway track vulnerability is assessed. All RCP scenarios revealed increased area across susceptibility classes, except for the very low category. RCP 8.5 projections indicate that 17.46% of the watershed area and 54% of railway length fall within very-high susceptible zones, compared to 6.19% and 35.61%, respectively, under current conditions. The developed maps can be integrated into a multi-hazard framework.