default author photo

Blythe Johnston

Government of the United States of America - Argonne National Laboratory

9700 S. Cass Avenue

Argonne, IL 60439

United States

  • Government of the United States of America - Argonne National Laboratory

SCHOLARLY PAPERS

1

DOWNLOADS

36

TOTAL CITATIONS

0

Scholarly Papers (1)

Actions:
Email selected abstracts
1.

What Really Matters for Automated Tornado Damage Assessment? Evidence from 2,300 Experiments Across 79 Open-Source Architectures with Cross-Event Generalization

Number of pages: 49 Posted: 09 Mar 2026
Robinson Umeike, Thang Dao, Shane Crawford, John W. van de Lindt, Blythe Johnston, Wanting (Lisa) Wang, Trung Do, Ajibola Mofikoya, Sarbesh Banjara and Cuong Pham
The University of Alabama, University of Alabama, The University of Alabama, affiliation not provided to SSRN, Government of the United States of America - Argonne National Laboratory, Old Dominion University, University of South Alabama, The University of Alabama, The University of Alabama and University of South Alabama
Downloads 36 (1,332,057)

Abstract:

Loading...

Deep Learning, Automated Damage Assessment, Vision transformers, Convolutional Neural Networks, Cross-Event Generalisation, Disaster Management