Milad Roohi

Milad Roohi, Eric M. Hernandez, David Rosowsky

The authors propose a methodology to perform seismic damage assessment of instrumented wood-frame buildings using response measurements. The proposed methodology employs a nonlinear model-based state observer that combines sparse acceleration measurements and a nonlinear structural model of a building to estimate the complete seismic response including displacements, velocity, acceleration and internal forces in all structural members. From the estimated seismic response and structural characteristics of each shear wall of the building, element-by-element seismic damage indices are computed and remaining useful life (pertaining to seismic effects) is predicted. The methodology is illustrated using measured data from the 2009 NEESWood Capstone full-scale shake table tests at the E-Defense facility in Japan.

Mahmuda Akhter Nishu, Chenyu Huang, Milad Roohi et al.

Wind hazards such as tornadoes and straight-line winds frequently affect vulnerable communities in the Great Plains of the United States, where limited infrastructure and sparse data coverage hinder effective emergency response. Existing forecasting systems focus primarily on meteorological elements and often fail to capture community-specific vulnerabilities, limiting their utility for localized risk assessment and resilience planning. To address this gap, we propose an interpretable dual-stream learning framework that integrates structured numerical weather data with unstructured textual event narratives. Our architecture combines a Random Forest and RoBERTa-based transformer through a late fusion mechanism, enabling robust and context-aware wind hazard prediction. The system is tailored for underserved tribal communities and supports block-level risk assessment. Experimental results show significant performance gains over traditional baselines. Furthermore, gradient-based sensitivity and ablation studies provide insight into the model's decision-making process, enhancing transparency and operational trust. The findings demonstrate both predictive effectiveness and practical value in supporting emergency preparedness and advancing community resilience.